Upload 15 files
Browse files- .gitattributes +1 -0
- wizardlm/README.md +70 -0
- wizardlm/adapter_config.json +34 -0
- wizardlm/adapter_model.safetensors +3 -0
- wizardlm/all_results.json +12 -0
- wizardlm/eval_results.json +7 -0
- wizardlm/special_tokens_map.json +34 -0
- wizardlm/tokenizer.json +3 -0
- wizardlm/tokenizer.model +3 -0
- wizardlm/tokenizer_config.json +2015 -0
- wizardlm/train_results.json +8 -0
- wizardlm/trainer_log.jsonl +447 -0
- wizardlm/trainer_state.json +3168 -0
- wizardlm/training_args.bin +3 -0
- wizardlm/training_eval_loss.png +0 -0
- wizardlm/training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -42,3 +42,4 @@ oasst1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 42 |
open_orca/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
science_literature/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
sharegpt/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 42 |
open_orca/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 43 |
science_literature/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 44 |
sharegpt/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
wizardlm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
wizardlm/README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: /cpfs01/user/zhangyiqun/models/gemma-2-2b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: other
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wizardlm
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# wizardlm
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/cpfs01/user/zhangyiqun/models/gemma-2-2b-it](https://huggingface.co//cpfs01/user/zhangyiqun/models/gemma-2-2b-it) on the wizardlm dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.8224
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 8
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 32
|
| 48 |
+
- total_eval_batch_size: 8
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 5.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.6341 | 1.1299 | 1000 | 0.7100 |
|
| 59 |
+
| 0.5528 | 2.2599 | 2000 | 0.7315 |
|
| 60 |
+
| 0.4847 | 3.3898 | 3000 | 0.7710 |
|
| 61 |
+
| 0.4261 | 4.5198 | 4000 | 0.8214 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- PEFT 0.12.0
|
| 67 |
+
- Transformers 4.44.2
|
| 68 |
+
- Pytorch 2.3.0+cu121
|
| 69 |
+
- Datasets 3.0.1
|
| 70 |
+
- Tokenizers 0.19.1
|
wizardlm/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "/cpfs01/user/zhangyiqun/models/gemma-2-2b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"down_proj",
|
| 24 |
+
"gate_proj",
|
| 25 |
+
"up_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"o_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
wizardlm/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:634245b82e4ec8639f3a5231b319c5da85309dc06863aa19196445ed2e6510b3
|
| 3 |
+
size 41581360
|
wizardlm/all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8224138021469116,
|
| 4 |
+
"eval_runtime": 16.3503,
|
| 5 |
+
"eval_samples_per_second": 91.191,
|
| 6 |
+
"eval_steps_per_second": 11.437,
|
| 7 |
+
"total_flos": 1.2071933436588196e+18,
|
| 8 |
+
"train_loss": 0.5702266787943867,
|
| 9 |
+
"train_runtime": 4287.601,
|
| 10 |
+
"train_samples_per_second": 33.024,
|
| 11 |
+
"train_steps_per_second": 1.032
|
| 12 |
+
}
|
wizardlm/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 0.8224138021469116,
|
| 4 |
+
"eval_runtime": 16.3503,
|
| 5 |
+
"eval_samples_per_second": 91.191,
|
| 6 |
+
"eval_steps_per_second": 11.437
|
| 7 |
+
}
|
wizardlm/special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<start_of_turn>",
|
| 4 |
+
"<end_of_turn>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<bos>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<pad>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
wizardlm/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
|
| 3 |
+
size 17525357
|
wizardlm/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
wizardlm/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2015 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<pad>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<eos>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "<bos>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"3": {
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"4": {
|
| 38 |
+
"content": "<mask>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": false
|
| 44 |
+
},
|
| 45 |
+
"5": {
|
| 46 |
+
"content": "<2mass>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": false
|
| 52 |
+
},
|
| 53 |
+
"6": {
|
| 54 |
+
"content": "[@BOS@]",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": false
|
| 60 |
+
},
|
| 61 |
+
"7": {
|
| 62 |
+
"content": "<unused0>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
"8": {
|
| 70 |
+
"content": "<unused1>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
+
},
|
| 77 |
+
"9": {
|
| 78 |
+
"content": "<unused2>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
+
},
|
| 85 |
+
"10": {
|
| 86 |
+
"content": "<unused3>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": false
|
| 92 |
+
},
|
| 93 |
+
"11": {
|
| 94 |
+
"content": "<unused4>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": false
|
| 100 |
+
},
|
| 101 |
+
"12": {
|
| 102 |
+
"content": "<unused5>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
+
},
|
| 109 |
+
"13": {
|
| 110 |
+
"content": "<unused6>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": false
|
| 116 |
+
},
|
| 117 |
+
"14": {
|
| 118 |
+
"content": "<unused7>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"15": {
|
| 126 |
+
"content": "<unused8>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"16": {
|
| 134 |
+
"content": "<unused9>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"17": {
|
| 142 |
+
"content": "<unused10>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"18": {
|
| 150 |
+
"content": "<unused11>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"19": {
|
| 158 |
+
"content": "<unused12>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"20": {
|
| 166 |
+
"content": "<unused13>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"21": {
|
| 174 |
+
"content": "<unused14>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"22": {
|
| 182 |
+
"content": "<unused15>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"23": {
|
| 190 |
+
"content": "<unused16>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"24": {
|
| 198 |
+
"content": "<unused17>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"25": {
|
| 206 |
+
"content": "<unused18>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"26": {
|
| 214 |
+
"content": "<unused19>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": false
|
| 220 |
+
},
|
| 221 |
+
"27": {
|
| 222 |
+
"content": "<unused20>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": false
|
| 228 |
+
},
|
| 229 |
+
"28": {
|
| 230 |
+
"content": "<unused21>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": false
|
| 236 |
+
},
|
| 237 |
+
"29": {
|
| 238 |
+
"content": "<unused22>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": false
|
| 244 |
+
},
|
| 245 |
+
"30": {
|
| 246 |
+
"content": "<unused23>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": false
|
| 252 |
+
},
|
| 253 |
+
"31": {
|
| 254 |
+
"content": "<unused24>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": false
|
| 260 |
+
},
|
| 261 |
+
"32": {
|
| 262 |
+
"content": "<unused25>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"33": {
|
| 270 |
+
"content": "<unused26>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": false
|
| 276 |
+
},
|
| 277 |
+
"34": {
|
| 278 |
+
"content": "<unused27>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": false
|
| 284 |
+
},
|
| 285 |
+
"35": {
|
| 286 |
+
"content": "<unused28>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": false
|
| 292 |
+
},
|
| 293 |
+
"36": {
|
| 294 |
+
"content": "<unused29>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": false
|
| 300 |
+
},
|
| 301 |
+
"37": {
|
| 302 |
+
"content": "<unused30>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": false
|
| 308 |
+
},
|
| 309 |
+
"38": {
|
| 310 |
+
"content": "<unused31>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": false
|
| 316 |
+
},
|
| 317 |
+
"39": {
|
| 318 |
+
"content": "<unused32>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": false
|
| 324 |
+
},
|
| 325 |
+
"40": {
|
| 326 |
+
"content": "<unused33>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": false
|
| 332 |
+
},
|
| 333 |
+
"41": {
|
| 334 |
+
"content": "<unused34>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": false
|
| 340 |
+
},
|
| 341 |
+
"42": {
|
| 342 |
+
"content": "<unused35>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": false
|
| 348 |
+
},
|
| 349 |
+
"43": {
|
| 350 |
+
"content": "<unused36>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": false
|
| 356 |
+
},
|
| 357 |
+
"44": {
|
| 358 |
+
"content": "<unused37>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": false
|
| 364 |
+
},
|
| 365 |
+
"45": {
|
| 366 |
+
"content": "<unused38>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": false
|
| 372 |
+
},
|
| 373 |
+
"46": {
|
| 374 |
+
"content": "<unused39>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": false
|
| 380 |
+
},
|
| 381 |
+
"47": {
|
| 382 |
+
"content": "<unused40>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": false
|
| 388 |
+
},
|
| 389 |
+
"48": {
|
| 390 |
+
"content": "<unused41>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": false
|
| 396 |
+
},
|
| 397 |
+
"49": {
|
| 398 |
+
"content": "<unused42>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": false
|
| 404 |
+
},
|
| 405 |
+
"50": {
|
| 406 |
+
"content": "<unused43>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": false
|
| 412 |
+
},
|
| 413 |
+
"51": {
|
| 414 |
+
"content": "<unused44>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": false
|
| 420 |
+
},
|
| 421 |
+
"52": {
|
| 422 |
+
"content": "<unused45>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": false
|
| 428 |
+
},
|
| 429 |
+
"53": {
|
| 430 |
+
"content": "<unused46>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": false
|
| 436 |
+
},
|
| 437 |
+
"54": {
|
| 438 |
+
"content": "<unused47>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": false
|
| 444 |
+
},
|
| 445 |
+
"55": {
|
| 446 |
+
"content": "<unused48>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": false
|
| 452 |
+
},
|
| 453 |
+
"56": {
|
| 454 |
+
"content": "<unused49>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": false
|
| 460 |
+
},
|
| 461 |
+
"57": {
|
| 462 |
+
"content": "<unused50>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": false
|
| 468 |
+
},
|
| 469 |
+
"58": {
|
| 470 |
+
"content": "<unused51>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": false
|
| 476 |
+
},
|
| 477 |
+
"59": {
|
| 478 |
+
"content": "<unused52>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": false
|
| 484 |
+
},
|
| 485 |
+
"60": {
|
| 486 |
+
"content": "<unused53>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": false
|
| 492 |
+
},
|
| 493 |
+
"61": {
|
| 494 |
+
"content": "<unused54>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
},
|
| 501 |
+
"62": {
|
| 502 |
+
"content": "<unused55>",
|
| 503 |
+
"lstrip": false,
|
| 504 |
+
"normalized": false,
|
| 505 |
+
"rstrip": false,
|
| 506 |
+
"single_word": false,
|
| 507 |
+
"special": false
|
| 508 |
+
},
|
| 509 |
+
"63": {
|
| 510 |
+
"content": "<unused56>",
|
| 511 |
+
"lstrip": false,
|
| 512 |
+
"normalized": false,
|
| 513 |
+
"rstrip": false,
|
| 514 |
+
"single_word": false,
|
| 515 |
+
"special": false
|
| 516 |
+
},
|
| 517 |
+
"64": {
|
| 518 |
+
"content": "<unused57>",
|
| 519 |
+
"lstrip": false,
|
| 520 |
+
"normalized": false,
|
| 521 |
+
"rstrip": false,
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"special": false
|
| 524 |
+
},
|
| 525 |
+
"65": {
|
| 526 |
+
"content": "<unused58>",
|
| 527 |
+
"lstrip": false,
|
| 528 |
+
"normalized": false,
|
| 529 |
+
"rstrip": false,
|
| 530 |
+
"single_word": false,
|
| 531 |
+
"special": false
|
| 532 |
+
},
|
| 533 |
+
"66": {
|
| 534 |
+
"content": "<unused59>",
|
| 535 |
+
"lstrip": false,
|
| 536 |
+
"normalized": false,
|
| 537 |
+
"rstrip": false,
|
| 538 |
+
"single_word": false,
|
| 539 |
+
"special": false
|
| 540 |
+
},
|
| 541 |
+
"67": {
|
| 542 |
+
"content": "<unused60>",
|
| 543 |
+
"lstrip": false,
|
| 544 |
+
"normalized": false,
|
| 545 |
+
"rstrip": false,
|
| 546 |
+
"single_word": false,
|
| 547 |
+
"special": false
|
| 548 |
+
},
|
| 549 |
+
"68": {
|
| 550 |
+
"content": "<unused61>",
|
| 551 |
+
"lstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"rstrip": false,
|
| 554 |
+
"single_word": false,
|
| 555 |
+
"special": false
|
| 556 |
+
},
|
| 557 |
+
"69": {
|
| 558 |
+
"content": "<unused62>",
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"normalized": false,
|
| 561 |
+
"rstrip": false,
|
| 562 |
+
"single_word": false,
|
| 563 |
+
"special": false
|
| 564 |
+
},
|
| 565 |
+
"70": {
|
| 566 |
+
"content": "<unused63>",
|
| 567 |
+
"lstrip": false,
|
| 568 |
+
"normalized": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"single_word": false,
|
| 571 |
+
"special": false
|
| 572 |
+
},
|
| 573 |
+
"71": {
|
| 574 |
+
"content": "<unused64>",
|
| 575 |
+
"lstrip": false,
|
| 576 |
+
"normalized": false,
|
| 577 |
+
"rstrip": false,
|
| 578 |
+
"single_word": false,
|
| 579 |
+
"special": false
|
| 580 |
+
},
|
| 581 |
+
"72": {
|
| 582 |
+
"content": "<unused65>",
|
| 583 |
+
"lstrip": false,
|
| 584 |
+
"normalized": false,
|
| 585 |
+
"rstrip": false,
|
| 586 |
+
"single_word": false,
|
| 587 |
+
"special": false
|
| 588 |
+
},
|
| 589 |
+
"73": {
|
| 590 |
+
"content": "<unused66>",
|
| 591 |
+
"lstrip": false,
|
| 592 |
+
"normalized": false,
|
| 593 |
+
"rstrip": false,
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"special": false
|
| 596 |
+
},
|
| 597 |
+
"74": {
|
| 598 |
+
"content": "<unused67>",
|
| 599 |
+
"lstrip": false,
|
| 600 |
+
"normalized": false,
|
| 601 |
+
"rstrip": false,
|
| 602 |
+
"single_word": false,
|
| 603 |
+
"special": false
|
| 604 |
+
},
|
| 605 |
+
"75": {
|
| 606 |
+
"content": "<unused68>",
|
| 607 |
+
"lstrip": false,
|
| 608 |
+
"normalized": false,
|
| 609 |
+
"rstrip": false,
|
| 610 |
+
"single_word": false,
|
| 611 |
+
"special": false
|
| 612 |
+
},
|
| 613 |
+
"76": {
|
| 614 |
+
"content": "<unused69>",
|
| 615 |
+
"lstrip": false,
|
| 616 |
+
"normalized": false,
|
| 617 |
+
"rstrip": false,
|
| 618 |
+
"single_word": false,
|
| 619 |
+
"special": false
|
| 620 |
+
},
|
| 621 |
+
"77": {
|
| 622 |
+
"content": "<unused70>",
|
| 623 |
+
"lstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"rstrip": false,
|
| 626 |
+
"single_word": false,
|
| 627 |
+
"special": false
|
| 628 |
+
},
|
| 629 |
+
"78": {
|
| 630 |
+
"content": "<unused71>",
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"normalized": false,
|
| 633 |
+
"rstrip": false,
|
| 634 |
+
"single_word": false,
|
| 635 |
+
"special": false
|
| 636 |
+
},
|
| 637 |
+
"79": {
|
| 638 |
+
"content": "<unused72>",
|
| 639 |
+
"lstrip": false,
|
| 640 |
+
"normalized": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"single_word": false,
|
| 643 |
+
"special": false
|
| 644 |
+
},
|
| 645 |
+
"80": {
|
| 646 |
+
"content": "<unused73>",
|
| 647 |
+
"lstrip": false,
|
| 648 |
+
"normalized": false,
|
| 649 |
+
"rstrip": false,
|
| 650 |
+
"single_word": false,
|
| 651 |
+
"special": false
|
| 652 |
+
},
|
| 653 |
+
"81": {
|
| 654 |
+
"content": "<unused74>",
|
| 655 |
+
"lstrip": false,
|
| 656 |
+
"normalized": false,
|
| 657 |
+
"rstrip": false,
|
| 658 |
+
"single_word": false,
|
| 659 |
+
"special": false
|
| 660 |
+
},
|
| 661 |
+
"82": {
|
| 662 |
+
"content": "<unused75>",
|
| 663 |
+
"lstrip": false,
|
| 664 |
+
"normalized": false,
|
| 665 |
+
"rstrip": false,
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"special": false
|
| 668 |
+
},
|
| 669 |
+
"83": {
|
| 670 |
+
"content": "<unused76>",
|
| 671 |
+
"lstrip": false,
|
| 672 |
+
"normalized": false,
|
| 673 |
+
"rstrip": false,
|
| 674 |
+
"single_word": false,
|
| 675 |
+
"special": false
|
| 676 |
+
},
|
| 677 |
+
"84": {
|
| 678 |
+
"content": "<unused77>",
|
| 679 |
+
"lstrip": false,
|
| 680 |
+
"normalized": false,
|
| 681 |
+
"rstrip": false,
|
| 682 |
+
"single_word": false,
|
| 683 |
+
"special": false
|
| 684 |
+
},
|
| 685 |
+
"85": {
|
| 686 |
+
"content": "<unused78>",
|
| 687 |
+
"lstrip": false,
|
| 688 |
+
"normalized": false,
|
| 689 |
+
"rstrip": false,
|
| 690 |
+
"single_word": false,
|
| 691 |
+
"special": false
|
| 692 |
+
},
|
| 693 |
+
"86": {
|
| 694 |
+
"content": "<unused79>",
|
| 695 |
+
"lstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"rstrip": false,
|
| 698 |
+
"single_word": false,
|
| 699 |
+
"special": false
|
| 700 |
+
},
|
| 701 |
+
"87": {
|
| 702 |
+
"content": "<unused80>",
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"normalized": false,
|
| 705 |
+
"rstrip": false,
|
| 706 |
+
"single_word": false,
|
| 707 |
+
"special": false
|
| 708 |
+
},
|
| 709 |
+
"88": {
|
| 710 |
+
"content": "<unused81>",
|
| 711 |
+
"lstrip": false,
|
| 712 |
+
"normalized": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"single_word": false,
|
| 715 |
+
"special": false
|
| 716 |
+
},
|
| 717 |
+
"89": {
|
| 718 |
+
"content": "<unused82>",
|
| 719 |
+
"lstrip": false,
|
| 720 |
+
"normalized": false,
|
| 721 |
+
"rstrip": false,
|
| 722 |
+
"single_word": false,
|
| 723 |
+
"special": false
|
| 724 |
+
},
|
| 725 |
+
"90": {
|
| 726 |
+
"content": "<unused83>",
|
| 727 |
+
"lstrip": false,
|
| 728 |
+
"normalized": false,
|
| 729 |
+
"rstrip": false,
|
| 730 |
+
"single_word": false,
|
| 731 |
+
"special": false
|
| 732 |
+
},
|
| 733 |
+
"91": {
|
| 734 |
+
"content": "<unused84>",
|
| 735 |
+
"lstrip": false,
|
| 736 |
+
"normalized": false,
|
| 737 |
+
"rstrip": false,
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"special": false
|
| 740 |
+
},
|
| 741 |
+
"92": {
|
| 742 |
+
"content": "<unused85>",
|
| 743 |
+
"lstrip": false,
|
| 744 |
+
"normalized": false,
|
| 745 |
+
"rstrip": false,
|
| 746 |
+
"single_word": false,
|
| 747 |
+
"special": false
|
| 748 |
+
},
|
| 749 |
+
"93": {
|
| 750 |
+
"content": "<unused86>",
|
| 751 |
+
"lstrip": false,
|
| 752 |
+
"normalized": false,
|
| 753 |
+
"rstrip": false,
|
| 754 |
+
"single_word": false,
|
| 755 |
+
"special": false
|
| 756 |
+
},
|
| 757 |
+
"94": {
|
| 758 |
+
"content": "<unused87>",
|
| 759 |
+
"lstrip": false,
|
| 760 |
+
"normalized": false,
|
| 761 |
+
"rstrip": false,
|
| 762 |
+
"single_word": false,
|
| 763 |
+
"special": false
|
| 764 |
+
},
|
| 765 |
+
"95": {
|
| 766 |
+
"content": "<unused88>",
|
| 767 |
+
"lstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"rstrip": false,
|
| 770 |
+
"single_word": false,
|
| 771 |
+
"special": false
|
| 772 |
+
},
|
| 773 |
+
"96": {
|
| 774 |
+
"content": "<unused89>",
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"normalized": false,
|
| 777 |
+
"rstrip": false,
|
| 778 |
+
"single_word": false,
|
| 779 |
+
"special": false
|
| 780 |
+
},
|
| 781 |
+
"97": {
|
| 782 |
+
"content": "<unused90>",
|
| 783 |
+
"lstrip": false,
|
| 784 |
+
"normalized": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"single_word": false,
|
| 787 |
+
"special": false
|
| 788 |
+
},
|
| 789 |
+
"98": {
|
| 790 |
+
"content": "<unused91>",
|
| 791 |
+
"lstrip": false,
|
| 792 |
+
"normalized": false,
|
| 793 |
+
"rstrip": false,
|
| 794 |
+
"single_word": false,
|
| 795 |
+
"special": false
|
| 796 |
+
},
|
| 797 |
+
"99": {
|
| 798 |
+
"content": "<unused92>",
|
| 799 |
+
"lstrip": false,
|
| 800 |
+
"normalized": false,
|
| 801 |
+
"rstrip": false,
|
| 802 |
+
"single_word": false,
|
| 803 |
+
"special": false
|
| 804 |
+
},
|
| 805 |
+
"100": {
|
| 806 |
+
"content": "<unused93>",
|
| 807 |
+
"lstrip": false,
|
| 808 |
+
"normalized": false,
|
| 809 |
+
"rstrip": false,
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"special": false
|
| 812 |
+
},
|
| 813 |
+
"101": {
|
| 814 |
+
"content": "<unused94>",
|
| 815 |
+
"lstrip": false,
|
| 816 |
+
"normalized": false,
|
| 817 |
+
"rstrip": false,
|
| 818 |
+
"single_word": false,
|
| 819 |
+
"special": false
|
| 820 |
+
},
|
| 821 |
+
"102": {
|
| 822 |
+
"content": "<unused95>",
|
| 823 |
+
"lstrip": false,
|
| 824 |
+
"normalized": false,
|
| 825 |
+
"rstrip": false,
|
| 826 |
+
"single_word": false,
|
| 827 |
+
"special": false
|
| 828 |
+
},
|
| 829 |
+
"103": {
|
| 830 |
+
"content": "<unused96>",
|
| 831 |
+
"lstrip": false,
|
| 832 |
+
"normalized": false,
|
| 833 |
+
"rstrip": false,
|
| 834 |
+
"single_word": false,
|
| 835 |
+
"special": false
|
| 836 |
+
},
|
| 837 |
+
"104": {
|
| 838 |
+
"content": "<unused97>",
|
| 839 |
+
"lstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"rstrip": false,
|
| 842 |
+
"single_word": false,
|
| 843 |
+
"special": false
|
| 844 |
+
},
|
| 845 |
+
"105": {
|
| 846 |
+
"content": "<unused98>",
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"normalized": false,
|
| 849 |
+
"rstrip": false,
|
| 850 |
+
"single_word": false,
|
| 851 |
+
"special": false
|
| 852 |
+
},
|
| 853 |
+
"106": {
|
| 854 |
+
"content": "<start_of_turn>",
|
| 855 |
+
"lstrip": false,
|
| 856 |
+
"normalized": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"single_word": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
"107": {
|
| 862 |
+
"content": "<end_of_turn>",
|
| 863 |
+
"lstrip": false,
|
| 864 |
+
"normalized": false,
|
| 865 |
+
"rstrip": false,
|
| 866 |
+
"single_word": false,
|
| 867 |
+
"special": true
|
| 868 |
+
},
|
| 869 |
+
"108": {
|
| 870 |
+
"content": "\n",
|
| 871 |
+
"lstrip": false,
|
| 872 |
+
"normalized": false,
|
| 873 |
+
"rstrip": false,
|
| 874 |
+
"single_word": false,
|
| 875 |
+
"special": false
|
| 876 |
+
},
|
| 877 |
+
"109": {
|
| 878 |
+
"content": "\n\n",
|
| 879 |
+
"lstrip": false,
|
| 880 |
+
"normalized": false,
|
| 881 |
+
"rstrip": false,
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"special": false
|
| 884 |
+
},
|
| 885 |
+
"110": {
|
| 886 |
+
"content": "\n\n\n",
|
| 887 |
+
"lstrip": false,
|
| 888 |
+
"normalized": false,
|
| 889 |
+
"rstrip": false,
|
| 890 |
+
"single_word": false,
|
| 891 |
+
"special": false
|
| 892 |
+
},
|
| 893 |
+
"111": {
|
| 894 |
+
"content": "\n\n\n\n",
|
| 895 |
+
"lstrip": false,
|
| 896 |
+
"normalized": false,
|
| 897 |
+
"rstrip": false,
|
| 898 |
+
"single_word": false,
|
| 899 |
+
"special": false
|
| 900 |
+
},
|
| 901 |
+
"112": {
|
| 902 |
+
"content": "\n\n\n\n\n",
|
| 903 |
+
"lstrip": false,
|
| 904 |
+
"normalized": false,
|
| 905 |
+
"rstrip": false,
|
| 906 |
+
"single_word": false,
|
| 907 |
+
"special": false
|
| 908 |
+
},
|
| 909 |
+
"113": {
|
| 910 |
+
"content": "\n\n\n\n\n\n",
|
| 911 |
+
"lstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"rstrip": false,
|
| 914 |
+
"single_word": false,
|
| 915 |
+
"special": false
|
| 916 |
+
},
|
| 917 |
+
"114": {
|
| 918 |
+
"content": "\n\n\n\n\n\n\n",
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"normalized": false,
|
| 921 |
+
"rstrip": false,
|
| 922 |
+
"single_word": false,
|
| 923 |
+
"special": false
|
| 924 |
+
},
|
| 925 |
+
"115": {
|
| 926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
| 927 |
+
"lstrip": false,
|
| 928 |
+
"normalized": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"single_word": false,
|
| 931 |
+
"special": false
|
| 932 |
+
},
|
| 933 |
+
"116": {
|
| 934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
| 935 |
+
"lstrip": false,
|
| 936 |
+
"normalized": false,
|
| 937 |
+
"rstrip": false,
|
| 938 |
+
"single_word": false,
|
| 939 |
+
"special": false
|
| 940 |
+
},
|
| 941 |
+
"117": {
|
| 942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
| 943 |
+
"lstrip": false,
|
| 944 |
+
"normalized": false,
|
| 945 |
+
"rstrip": false,
|
| 946 |
+
"single_word": false,
|
| 947 |
+
"special": false
|
| 948 |
+
},
|
| 949 |
+
"118": {
|
| 950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
| 951 |
+
"lstrip": false,
|
| 952 |
+
"normalized": false,
|
| 953 |
+
"rstrip": false,
|
| 954 |
+
"single_word": false,
|
| 955 |
+
"special": false
|
| 956 |
+
},
|
| 957 |
+
"119": {
|
| 958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 959 |
+
"lstrip": false,
|
| 960 |
+
"normalized": false,
|
| 961 |
+
"rstrip": false,
|
| 962 |
+
"single_word": false,
|
| 963 |
+
"special": false
|
| 964 |
+
},
|
| 965 |
+
"120": {
|
| 966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 967 |
+
"lstrip": false,
|
| 968 |
+
"normalized": false,
|
| 969 |
+
"rstrip": false,
|
| 970 |
+
"single_word": false,
|
| 971 |
+
"special": false
|
| 972 |
+
},
|
| 973 |
+
"121": {
|
| 974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 975 |
+
"lstrip": false,
|
| 976 |
+
"normalized": false,
|
| 977 |
+
"rstrip": false,
|
| 978 |
+
"single_word": false,
|
| 979 |
+
"special": false
|
| 980 |
+
},
|
| 981 |
+
"122": {
|
| 982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 983 |
+
"lstrip": false,
|
| 984 |
+
"normalized": false,
|
| 985 |
+
"rstrip": false,
|
| 986 |
+
"single_word": false,
|
| 987 |
+
"special": false
|
| 988 |
+
},
|
| 989 |
+
"123": {
|
| 990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 991 |
+
"lstrip": false,
|
| 992 |
+
"normalized": false,
|
| 993 |
+
"rstrip": false,
|
| 994 |
+
"single_word": false,
|
| 995 |
+
"special": false
|
| 996 |
+
},
|
| 997 |
+
"124": {
|
| 998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 999 |
+
"lstrip": false,
|
| 1000 |
+
"normalized": false,
|
| 1001 |
+
"rstrip": false,
|
| 1002 |
+
"single_word": false,
|
| 1003 |
+
"special": false
|
| 1004 |
+
},
|
| 1005 |
+
"125": {
|
| 1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1007 |
+
"lstrip": false,
|
| 1008 |
+
"normalized": false,
|
| 1009 |
+
"rstrip": false,
|
| 1010 |
+
"single_word": false,
|
| 1011 |
+
"special": false
|
| 1012 |
+
},
|
| 1013 |
+
"126": {
|
| 1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1015 |
+
"lstrip": false,
|
| 1016 |
+
"normalized": false,
|
| 1017 |
+
"rstrip": false,
|
| 1018 |
+
"single_word": false,
|
| 1019 |
+
"special": false
|
| 1020 |
+
},
|
| 1021 |
+
"127": {
|
| 1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1023 |
+
"lstrip": false,
|
| 1024 |
+
"normalized": false,
|
| 1025 |
+
"rstrip": false,
|
| 1026 |
+
"single_word": false,
|
| 1027 |
+
"special": false
|
| 1028 |
+
},
|
| 1029 |
+
"128": {
|
| 1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1031 |
+
"lstrip": false,
|
| 1032 |
+
"normalized": false,
|
| 1033 |
+
"rstrip": false,
|
| 1034 |
+
"single_word": false,
|
| 1035 |
+
"special": false
|
| 1036 |
+
},
|
| 1037 |
+
"129": {
|
| 1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1039 |
+
"lstrip": false,
|
| 1040 |
+
"normalized": false,
|
| 1041 |
+
"rstrip": false,
|
| 1042 |
+
"single_word": false,
|
| 1043 |
+
"special": false
|
| 1044 |
+
},
|
| 1045 |
+
"130": {
|
| 1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1047 |
+
"lstrip": false,
|
| 1048 |
+
"normalized": false,
|
| 1049 |
+
"rstrip": false,
|
| 1050 |
+
"single_word": false,
|
| 1051 |
+
"special": false
|
| 1052 |
+
},
|
| 1053 |
+
"131": {
|
| 1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1055 |
+
"lstrip": false,
|
| 1056 |
+
"normalized": false,
|
| 1057 |
+
"rstrip": false,
|
| 1058 |
+
"single_word": false,
|
| 1059 |
+
"special": false
|
| 1060 |
+
},
|
| 1061 |
+
"132": {
|
| 1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1063 |
+
"lstrip": false,
|
| 1064 |
+
"normalized": false,
|
| 1065 |
+
"rstrip": false,
|
| 1066 |
+
"single_word": false,
|
| 1067 |
+
"special": false
|
| 1068 |
+
},
|
| 1069 |
+
"133": {
|
| 1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1071 |
+
"lstrip": false,
|
| 1072 |
+
"normalized": false,
|
| 1073 |
+
"rstrip": false,
|
| 1074 |
+
"single_word": false,
|
| 1075 |
+
"special": false
|
| 1076 |
+
},
|
| 1077 |
+
"134": {
|
| 1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1079 |
+
"lstrip": false,
|
| 1080 |
+
"normalized": false,
|
| 1081 |
+
"rstrip": false,
|
| 1082 |
+
"single_word": false,
|
| 1083 |
+
"special": false
|
| 1084 |
+
},
|
| 1085 |
+
"135": {
|
| 1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1087 |
+
"lstrip": false,
|
| 1088 |
+
"normalized": false,
|
| 1089 |
+
"rstrip": false,
|
| 1090 |
+
"single_word": false,
|
| 1091 |
+
"special": false
|
| 1092 |
+
},
|
| 1093 |
+
"136": {
|
| 1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1095 |
+
"lstrip": false,
|
| 1096 |
+
"normalized": false,
|
| 1097 |
+
"rstrip": false,
|
| 1098 |
+
"single_word": false,
|
| 1099 |
+
"special": false
|
| 1100 |
+
},
|
| 1101 |
+
"137": {
|
| 1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1103 |
+
"lstrip": false,
|
| 1104 |
+
"normalized": false,
|
| 1105 |
+
"rstrip": false,
|
| 1106 |
+
"single_word": false,
|
| 1107 |
+
"special": false
|
| 1108 |
+
},
|
| 1109 |
+
"138": {
|
| 1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
| 1111 |
+
"lstrip": false,
|
| 1112 |
+
"normalized": false,
|
| 1113 |
+
"rstrip": false,
|
| 1114 |
+
"single_word": false,
|
| 1115 |
+
"special": false
|
| 1116 |
+
},
|
| 1117 |
+
"139": {
|
| 1118 |
+
"content": "▁▁",
|
| 1119 |
+
"lstrip": false,
|
| 1120 |
+
"normalized": false,
|
| 1121 |
+
"rstrip": false,
|
| 1122 |
+
"single_word": false,
|
| 1123 |
+
"special": false
|
| 1124 |
+
},
|
| 1125 |
+
"140": {
|
| 1126 |
+
"content": "▁▁▁",
|
| 1127 |
+
"lstrip": false,
|
| 1128 |
+
"normalized": false,
|
| 1129 |
+
"rstrip": false,
|
| 1130 |
+
"single_word": false,
|
| 1131 |
+
"special": false
|
| 1132 |
+
},
|
| 1133 |
+
"141": {
|
| 1134 |
+
"content": "▁▁▁▁",
|
| 1135 |
+
"lstrip": false,
|
| 1136 |
+
"normalized": false,
|
| 1137 |
+
"rstrip": false,
|
| 1138 |
+
"single_word": false,
|
| 1139 |
+
"special": false
|
| 1140 |
+
},
|
| 1141 |
+
"142": {
|
| 1142 |
+
"content": "▁▁▁▁▁",
|
| 1143 |
+
"lstrip": false,
|
| 1144 |
+
"normalized": false,
|
| 1145 |
+
"rstrip": false,
|
| 1146 |
+
"single_word": false,
|
| 1147 |
+
"special": false
|
| 1148 |
+
},
|
| 1149 |
+
"143": {
|
| 1150 |
+
"content": "▁▁▁▁▁▁",
|
| 1151 |
+
"lstrip": false,
|
| 1152 |
+
"normalized": false,
|
| 1153 |
+
"rstrip": false,
|
| 1154 |
+
"single_word": false,
|
| 1155 |
+
"special": false
|
| 1156 |
+
},
|
| 1157 |
+
"144": {
|
| 1158 |
+
"content": "▁▁▁▁▁▁▁",
|
| 1159 |
+
"lstrip": false,
|
| 1160 |
+
"normalized": false,
|
| 1161 |
+
"rstrip": false,
|
| 1162 |
+
"single_word": false,
|
| 1163 |
+
"special": false
|
| 1164 |
+
},
|
| 1165 |
+
"145": {
|
| 1166 |
+
"content": "▁▁▁▁▁▁▁▁",
|
| 1167 |
+
"lstrip": false,
|
| 1168 |
+
"normalized": false,
|
| 1169 |
+
"rstrip": false,
|
| 1170 |
+
"single_word": false,
|
| 1171 |
+
"special": false
|
| 1172 |
+
},
|
| 1173 |
+
"146": {
|
| 1174 |
+
"content": "▁▁▁▁▁▁▁▁▁",
|
| 1175 |
+
"lstrip": false,
|
| 1176 |
+
"normalized": false,
|
| 1177 |
+
"rstrip": false,
|
| 1178 |
+
"single_word": false,
|
| 1179 |
+
"special": false
|
| 1180 |
+
},
|
| 1181 |
+
"147": {
|
| 1182 |
+
"content": "▁▁▁▁▁▁▁▁▁▁",
|
| 1183 |
+
"lstrip": false,
|
| 1184 |
+
"normalized": false,
|
| 1185 |
+
"rstrip": false,
|
| 1186 |
+
"single_word": false,
|
| 1187 |
+
"special": false
|
| 1188 |
+
},
|
| 1189 |
+
"148": {
|
| 1190 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁",
|
| 1191 |
+
"lstrip": false,
|
| 1192 |
+
"normalized": false,
|
| 1193 |
+
"rstrip": false,
|
| 1194 |
+
"single_word": false,
|
| 1195 |
+
"special": false
|
| 1196 |
+
},
|
| 1197 |
+
"149": {
|
| 1198 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1199 |
+
"lstrip": false,
|
| 1200 |
+
"normalized": false,
|
| 1201 |
+
"rstrip": false,
|
| 1202 |
+
"single_word": false,
|
| 1203 |
+
"special": false
|
| 1204 |
+
},
|
| 1205 |
+
"150": {
|
| 1206 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1207 |
+
"lstrip": false,
|
| 1208 |
+
"normalized": false,
|
| 1209 |
+
"rstrip": false,
|
| 1210 |
+
"single_word": false,
|
| 1211 |
+
"special": false
|
| 1212 |
+
},
|
| 1213 |
+
"151": {
|
| 1214 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1215 |
+
"lstrip": false,
|
| 1216 |
+
"normalized": false,
|
| 1217 |
+
"rstrip": false,
|
| 1218 |
+
"single_word": false,
|
| 1219 |
+
"special": false
|
| 1220 |
+
},
|
| 1221 |
+
"152": {
|
| 1222 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1223 |
+
"lstrip": false,
|
| 1224 |
+
"normalized": false,
|
| 1225 |
+
"rstrip": false,
|
| 1226 |
+
"single_word": false,
|
| 1227 |
+
"special": false
|
| 1228 |
+
},
|
| 1229 |
+
"153": {
|
| 1230 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1231 |
+
"lstrip": false,
|
| 1232 |
+
"normalized": false,
|
| 1233 |
+
"rstrip": false,
|
| 1234 |
+
"single_word": false,
|
| 1235 |
+
"special": false
|
| 1236 |
+
},
|
| 1237 |
+
"154": {
|
| 1238 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1239 |
+
"lstrip": false,
|
| 1240 |
+
"normalized": false,
|
| 1241 |
+
"rstrip": false,
|
| 1242 |
+
"single_word": false,
|
| 1243 |
+
"special": false
|
| 1244 |
+
},
|
| 1245 |
+
"155": {
|
| 1246 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1247 |
+
"lstrip": false,
|
| 1248 |
+
"normalized": false,
|
| 1249 |
+
"rstrip": false,
|
| 1250 |
+
"single_word": false,
|
| 1251 |
+
"special": false
|
| 1252 |
+
},
|
| 1253 |
+
"156": {
|
| 1254 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1255 |
+
"lstrip": false,
|
| 1256 |
+
"normalized": false,
|
| 1257 |
+
"rstrip": false,
|
| 1258 |
+
"single_word": false,
|
| 1259 |
+
"special": false
|
| 1260 |
+
},
|
| 1261 |
+
"157": {
|
| 1262 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1263 |
+
"lstrip": false,
|
| 1264 |
+
"normalized": false,
|
| 1265 |
+
"rstrip": false,
|
| 1266 |
+
"single_word": false,
|
| 1267 |
+
"special": false
|
| 1268 |
+
},
|
| 1269 |
+
"158": {
|
| 1270 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1271 |
+
"lstrip": false,
|
| 1272 |
+
"normalized": false,
|
| 1273 |
+
"rstrip": false,
|
| 1274 |
+
"single_word": false,
|
| 1275 |
+
"special": false
|
| 1276 |
+
},
|
| 1277 |
+
"159": {
|
| 1278 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1279 |
+
"lstrip": false,
|
| 1280 |
+
"normalized": false,
|
| 1281 |
+
"rstrip": false,
|
| 1282 |
+
"single_word": false,
|
| 1283 |
+
"special": false
|
| 1284 |
+
},
|
| 1285 |
+
"160": {
|
| 1286 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1287 |
+
"lstrip": false,
|
| 1288 |
+
"normalized": false,
|
| 1289 |
+
"rstrip": false,
|
| 1290 |
+
"single_word": false,
|
| 1291 |
+
"special": false
|
| 1292 |
+
},
|
| 1293 |
+
"161": {
|
| 1294 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1295 |
+
"lstrip": false,
|
| 1296 |
+
"normalized": false,
|
| 1297 |
+
"rstrip": false,
|
| 1298 |
+
"single_word": false,
|
| 1299 |
+
"special": false
|
| 1300 |
+
},
|
| 1301 |
+
"162": {
|
| 1302 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1303 |
+
"lstrip": false,
|
| 1304 |
+
"normalized": false,
|
| 1305 |
+
"rstrip": false,
|
| 1306 |
+
"single_word": false,
|
| 1307 |
+
"special": false
|
| 1308 |
+
},
|
| 1309 |
+
"163": {
|
| 1310 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1311 |
+
"lstrip": false,
|
| 1312 |
+
"normalized": false,
|
| 1313 |
+
"rstrip": false,
|
| 1314 |
+
"single_word": false,
|
| 1315 |
+
"special": false
|
| 1316 |
+
},
|
| 1317 |
+
"164": {
|
| 1318 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1319 |
+
"lstrip": false,
|
| 1320 |
+
"normalized": false,
|
| 1321 |
+
"rstrip": false,
|
| 1322 |
+
"single_word": false,
|
| 1323 |
+
"special": false
|
| 1324 |
+
},
|
| 1325 |
+
"165": {
|
| 1326 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1327 |
+
"lstrip": false,
|
| 1328 |
+
"normalized": false,
|
| 1329 |
+
"rstrip": false,
|
| 1330 |
+
"single_word": false,
|
| 1331 |
+
"special": false
|
| 1332 |
+
},
|
| 1333 |
+
"166": {
|
| 1334 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1335 |
+
"lstrip": false,
|
| 1336 |
+
"normalized": false,
|
| 1337 |
+
"rstrip": false,
|
| 1338 |
+
"single_word": false,
|
| 1339 |
+
"special": false
|
| 1340 |
+
},
|
| 1341 |
+
"167": {
|
| 1342 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1343 |
+
"lstrip": false,
|
| 1344 |
+
"normalized": false,
|
| 1345 |
+
"rstrip": false,
|
| 1346 |
+
"single_word": false,
|
| 1347 |
+
"special": false
|
| 1348 |
+
},
|
| 1349 |
+
"168": {
|
| 1350 |
+
"content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
|
| 1351 |
+
"lstrip": false,
|
| 1352 |
+
"normalized": false,
|
| 1353 |
+
"rstrip": false,
|
| 1354 |
+
"single_word": false,
|
| 1355 |
+
"special": false
|
| 1356 |
+
},
|
| 1357 |
+
"169": {
|
| 1358 |
+
"content": "<table>",
|
| 1359 |
+
"lstrip": false,
|
| 1360 |
+
"normalized": false,
|
| 1361 |
+
"rstrip": false,
|
| 1362 |
+
"single_word": false,
|
| 1363 |
+
"special": false
|
| 1364 |
+
},
|
| 1365 |
+
"170": {
|
| 1366 |
+
"content": "<caption>",
|
| 1367 |
+
"lstrip": false,
|
| 1368 |
+
"normalized": false,
|
| 1369 |
+
"rstrip": false,
|
| 1370 |
+
"single_word": false,
|
| 1371 |
+
"special": false
|
| 1372 |
+
},
|
| 1373 |
+
"171": {
|
| 1374 |
+
"content": "<thead>",
|
| 1375 |
+
"lstrip": false,
|
| 1376 |
+
"normalized": false,
|
| 1377 |
+
"rstrip": false,
|
| 1378 |
+
"single_word": false,
|
| 1379 |
+
"special": false
|
| 1380 |
+
},
|
| 1381 |
+
"172": {
|
| 1382 |
+
"content": "<tbody>",
|
| 1383 |
+
"lstrip": false,
|
| 1384 |
+
"normalized": false,
|
| 1385 |
+
"rstrip": false,
|
| 1386 |
+
"single_word": false,
|
| 1387 |
+
"special": false
|
| 1388 |
+
},
|
| 1389 |
+
"173": {
|
| 1390 |
+
"content": "<tfoot>",
|
| 1391 |
+
"lstrip": false,
|
| 1392 |
+
"normalized": false,
|
| 1393 |
+
"rstrip": false,
|
| 1394 |
+
"single_word": false,
|
| 1395 |
+
"special": false
|
| 1396 |
+
},
|
| 1397 |
+
"174": {
|
| 1398 |
+
"content": "<tr>",
|
| 1399 |
+
"lstrip": false,
|
| 1400 |
+
"normalized": false,
|
| 1401 |
+
"rstrip": false,
|
| 1402 |
+
"single_word": false,
|
| 1403 |
+
"special": false
|
| 1404 |
+
},
|
| 1405 |
+
"175": {
|
| 1406 |
+
"content": "<th>",
|
| 1407 |
+
"lstrip": false,
|
| 1408 |
+
"normalized": false,
|
| 1409 |
+
"rstrip": false,
|
| 1410 |
+
"single_word": false,
|
| 1411 |
+
"special": false
|
| 1412 |
+
},
|
| 1413 |
+
"176": {
|
| 1414 |
+
"content": "<td>",
|
| 1415 |
+
"lstrip": false,
|
| 1416 |
+
"normalized": false,
|
| 1417 |
+
"rstrip": false,
|
| 1418 |
+
"single_word": false,
|
| 1419 |
+
"special": false
|
| 1420 |
+
},
|
| 1421 |
+
"177": {
|
| 1422 |
+
"content": "</table>",
|
| 1423 |
+
"lstrip": false,
|
| 1424 |
+
"normalized": false,
|
| 1425 |
+
"rstrip": false,
|
| 1426 |
+
"single_word": false,
|
| 1427 |
+
"special": false
|
| 1428 |
+
},
|
| 1429 |
+
"178": {
|
| 1430 |
+
"content": "</caption>",
|
| 1431 |
+
"lstrip": false,
|
| 1432 |
+
"normalized": false,
|
| 1433 |
+
"rstrip": false,
|
| 1434 |
+
"single_word": false,
|
| 1435 |
+
"special": false
|
| 1436 |
+
},
|
| 1437 |
+
"179": {
|
| 1438 |
+
"content": "</thead>",
|
| 1439 |
+
"lstrip": false,
|
| 1440 |
+
"normalized": false,
|
| 1441 |
+
"rstrip": false,
|
| 1442 |
+
"single_word": false,
|
| 1443 |
+
"special": false
|
| 1444 |
+
},
|
| 1445 |
+
"180": {
|
| 1446 |
+
"content": "</tbody>",
|
| 1447 |
+
"lstrip": false,
|
| 1448 |
+
"normalized": false,
|
| 1449 |
+
"rstrip": false,
|
| 1450 |
+
"single_word": false,
|
| 1451 |
+
"special": false
|
| 1452 |
+
},
|
| 1453 |
+
"181": {
|
| 1454 |
+
"content": "</tfoot>",
|
| 1455 |
+
"lstrip": false,
|
| 1456 |
+
"normalized": false,
|
| 1457 |
+
"rstrip": false,
|
| 1458 |
+
"single_word": false,
|
| 1459 |
+
"special": false
|
| 1460 |
+
},
|
| 1461 |
+
"182": {
|
| 1462 |
+
"content": "</tr>",
|
| 1463 |
+
"lstrip": false,
|
| 1464 |
+
"normalized": false,
|
| 1465 |
+
"rstrip": false,
|
| 1466 |
+
"single_word": false,
|
| 1467 |
+
"special": false
|
| 1468 |
+
},
|
| 1469 |
+
"183": {
|
| 1470 |
+
"content": "</th>",
|
| 1471 |
+
"lstrip": false,
|
| 1472 |
+
"normalized": false,
|
| 1473 |
+
"rstrip": false,
|
| 1474 |
+
"single_word": false,
|
| 1475 |
+
"special": false
|
| 1476 |
+
},
|
| 1477 |
+
"184": {
|
| 1478 |
+
"content": "</td>",
|
| 1479 |
+
"lstrip": false,
|
| 1480 |
+
"normalized": false,
|
| 1481 |
+
"rstrip": false,
|
| 1482 |
+
"single_word": false,
|
| 1483 |
+
"special": false
|
| 1484 |
+
},
|
| 1485 |
+
"185": {
|
| 1486 |
+
"content": "<h1>",
|
| 1487 |
+
"lstrip": false,
|
| 1488 |
+
"normalized": false,
|
| 1489 |
+
"rstrip": false,
|
| 1490 |
+
"single_word": false,
|
| 1491 |
+
"special": false
|
| 1492 |
+
},
|
| 1493 |
+
"186": {
|
| 1494 |
+
"content": "<h2>",
|
| 1495 |
+
"lstrip": false,
|
| 1496 |
+
"normalized": false,
|
| 1497 |
+
"rstrip": false,
|
| 1498 |
+
"single_word": false,
|
| 1499 |
+
"special": false
|
| 1500 |
+
},
|
| 1501 |
+
"187": {
|
| 1502 |
+
"content": "<h3>",
|
| 1503 |
+
"lstrip": false,
|
| 1504 |
+
"normalized": false,
|
| 1505 |
+
"rstrip": false,
|
| 1506 |
+
"single_word": false,
|
| 1507 |
+
"special": false
|
| 1508 |
+
},
|
| 1509 |
+
"188": {
|
| 1510 |
+
"content": "<h4>",
|
| 1511 |
+
"lstrip": false,
|
| 1512 |
+
"normalized": false,
|
| 1513 |
+
"rstrip": false,
|
| 1514 |
+
"single_word": false,
|
| 1515 |
+
"special": false
|
| 1516 |
+
},
|
| 1517 |
+
"189": {
|
| 1518 |
+
"content": "<h5>",
|
| 1519 |
+
"lstrip": false,
|
| 1520 |
+
"normalized": false,
|
| 1521 |
+
"rstrip": false,
|
| 1522 |
+
"single_word": false,
|
| 1523 |
+
"special": false
|
| 1524 |
+
},
|
| 1525 |
+
"190": {
|
| 1526 |
+
"content": "<h6>",
|
| 1527 |
+
"lstrip": false,
|
| 1528 |
+
"normalized": false,
|
| 1529 |
+
"rstrip": false,
|
| 1530 |
+
"single_word": false,
|
| 1531 |
+
"special": false
|
| 1532 |
+
},
|
| 1533 |
+
"191": {
|
| 1534 |
+
"content": "<blockquote>",
|
| 1535 |
+
"lstrip": false,
|
| 1536 |
+
"normalized": false,
|
| 1537 |
+
"rstrip": false,
|
| 1538 |
+
"single_word": false,
|
| 1539 |
+
"special": false
|
| 1540 |
+
},
|
| 1541 |
+
"192": {
|
| 1542 |
+
"content": "</h1>",
|
| 1543 |
+
"lstrip": false,
|
| 1544 |
+
"normalized": false,
|
| 1545 |
+
"rstrip": false,
|
| 1546 |
+
"single_word": false,
|
| 1547 |
+
"special": false
|
| 1548 |
+
},
|
| 1549 |
+
"193": {
|
| 1550 |
+
"content": "</h2>",
|
| 1551 |
+
"lstrip": false,
|
| 1552 |
+
"normalized": false,
|
| 1553 |
+
"rstrip": false,
|
| 1554 |
+
"single_word": false,
|
| 1555 |
+
"special": false
|
| 1556 |
+
},
|
| 1557 |
+
"194": {
|
| 1558 |
+
"content": "</h3>",
|
| 1559 |
+
"lstrip": false,
|
| 1560 |
+
"normalized": false,
|
| 1561 |
+
"rstrip": false,
|
| 1562 |
+
"single_word": false,
|
| 1563 |
+
"special": false
|
| 1564 |
+
},
|
| 1565 |
+
"195": {
|
| 1566 |
+
"content": "</h4>",
|
| 1567 |
+
"lstrip": false,
|
| 1568 |
+
"normalized": false,
|
| 1569 |
+
"rstrip": false,
|
| 1570 |
+
"single_word": false,
|
| 1571 |
+
"special": false
|
| 1572 |
+
},
|
| 1573 |
+
"196": {
|
| 1574 |
+
"content": "</h5>",
|
| 1575 |
+
"lstrip": false,
|
| 1576 |
+
"normalized": false,
|
| 1577 |
+
"rstrip": false,
|
| 1578 |
+
"single_word": false,
|
| 1579 |
+
"special": false
|
| 1580 |
+
},
|
| 1581 |
+
"197": {
|
| 1582 |
+
"content": "</h6>",
|
| 1583 |
+
"lstrip": false,
|
| 1584 |
+
"normalized": false,
|
| 1585 |
+
"rstrip": false,
|
| 1586 |
+
"single_word": false,
|
| 1587 |
+
"special": false
|
| 1588 |
+
},
|
| 1589 |
+
"198": {
|
| 1590 |
+
"content": "</blockquote>",
|
| 1591 |
+
"lstrip": false,
|
| 1592 |
+
"normalized": false,
|
| 1593 |
+
"rstrip": false,
|
| 1594 |
+
"single_word": false,
|
| 1595 |
+
"special": false
|
| 1596 |
+
},
|
| 1597 |
+
"199": {
|
| 1598 |
+
"content": "<strong>",
|
| 1599 |
+
"lstrip": false,
|
| 1600 |
+
"normalized": false,
|
| 1601 |
+
"rstrip": false,
|
| 1602 |
+
"single_word": false,
|
| 1603 |
+
"special": false
|
| 1604 |
+
},
|
| 1605 |
+
"200": {
|
| 1606 |
+
"content": "<em>",
|
| 1607 |
+
"lstrip": false,
|
| 1608 |
+
"normalized": false,
|
| 1609 |
+
"rstrip": false,
|
| 1610 |
+
"single_word": false,
|
| 1611 |
+
"special": false
|
| 1612 |
+
},
|
| 1613 |
+
"201": {
|
| 1614 |
+
"content": "<b>",
|
| 1615 |
+
"lstrip": false,
|
| 1616 |
+
"normalized": false,
|
| 1617 |
+
"rstrip": false,
|
| 1618 |
+
"single_word": false,
|
| 1619 |
+
"special": false
|
| 1620 |
+
},
|
| 1621 |
+
"202": {
|
| 1622 |
+
"content": "<i>",
|
| 1623 |
+
"lstrip": false,
|
| 1624 |
+
"normalized": false,
|
| 1625 |
+
"rstrip": false,
|
| 1626 |
+
"single_word": false,
|
| 1627 |
+
"special": false
|
| 1628 |
+
},
|
| 1629 |
+
"203": {
|
| 1630 |
+
"content": "<u>",
|
| 1631 |
+
"lstrip": false,
|
| 1632 |
+
"normalized": false,
|
| 1633 |
+
"rstrip": false,
|
| 1634 |
+
"single_word": false,
|
| 1635 |
+
"special": false
|
| 1636 |
+
},
|
| 1637 |
+
"204": {
|
| 1638 |
+
"content": "<s>",
|
| 1639 |
+
"lstrip": false,
|
| 1640 |
+
"normalized": false,
|
| 1641 |
+
"rstrip": false,
|
| 1642 |
+
"single_word": false,
|
| 1643 |
+
"special": false
|
| 1644 |
+
},
|
| 1645 |
+
"205": {
|
| 1646 |
+
"content": "<sub>",
|
| 1647 |
+
"lstrip": false,
|
| 1648 |
+
"normalized": false,
|
| 1649 |
+
"rstrip": false,
|
| 1650 |
+
"single_word": false,
|
| 1651 |
+
"special": false
|
| 1652 |
+
},
|
| 1653 |
+
"206": {
|
| 1654 |
+
"content": "<sup>",
|
| 1655 |
+
"lstrip": false,
|
| 1656 |
+
"normalized": false,
|
| 1657 |
+
"rstrip": false,
|
| 1658 |
+
"single_word": false,
|
| 1659 |
+
"special": false
|
| 1660 |
+
},
|
| 1661 |
+
"207": {
|
| 1662 |
+
"content": "<code>",
|
| 1663 |
+
"lstrip": false,
|
| 1664 |
+
"normalized": false,
|
| 1665 |
+
"rstrip": false,
|
| 1666 |
+
"single_word": false,
|
| 1667 |
+
"special": false
|
| 1668 |
+
},
|
| 1669 |
+
"208": {
|
| 1670 |
+
"content": "</strong>",
|
| 1671 |
+
"lstrip": false,
|
| 1672 |
+
"normalized": false,
|
| 1673 |
+
"rstrip": false,
|
| 1674 |
+
"single_word": false,
|
| 1675 |
+
"special": false
|
| 1676 |
+
},
|
| 1677 |
+
"209": {
|
| 1678 |
+
"content": "</em>",
|
| 1679 |
+
"lstrip": false,
|
| 1680 |
+
"normalized": false,
|
| 1681 |
+
"rstrip": false,
|
| 1682 |
+
"single_word": false,
|
| 1683 |
+
"special": false
|
| 1684 |
+
},
|
| 1685 |
+
"210": {
|
| 1686 |
+
"content": "</b>",
|
| 1687 |
+
"lstrip": false,
|
| 1688 |
+
"normalized": false,
|
| 1689 |
+
"rstrip": false,
|
| 1690 |
+
"single_word": false,
|
| 1691 |
+
"special": false
|
| 1692 |
+
},
|
| 1693 |
+
"211": {
|
| 1694 |
+
"content": "</i>",
|
| 1695 |
+
"lstrip": false,
|
| 1696 |
+
"normalized": false,
|
| 1697 |
+
"rstrip": false,
|
| 1698 |
+
"single_word": false,
|
| 1699 |
+
"special": false
|
| 1700 |
+
},
|
| 1701 |
+
"212": {
|
| 1702 |
+
"content": "</u>",
|
| 1703 |
+
"lstrip": false,
|
| 1704 |
+
"normalized": false,
|
| 1705 |
+
"rstrip": false,
|
| 1706 |
+
"single_word": false,
|
| 1707 |
+
"special": false
|
| 1708 |
+
},
|
| 1709 |
+
"213": {
|
| 1710 |
+
"content": "</s>",
|
| 1711 |
+
"lstrip": false,
|
| 1712 |
+
"normalized": false,
|
| 1713 |
+
"rstrip": false,
|
| 1714 |
+
"single_word": false,
|
| 1715 |
+
"special": false
|
| 1716 |
+
},
|
| 1717 |
+
"214": {
|
| 1718 |
+
"content": "</sub>",
|
| 1719 |
+
"lstrip": false,
|
| 1720 |
+
"normalized": false,
|
| 1721 |
+
"rstrip": false,
|
| 1722 |
+
"single_word": false,
|
| 1723 |
+
"special": false
|
| 1724 |
+
},
|
| 1725 |
+
"215": {
|
| 1726 |
+
"content": "</sup>",
|
| 1727 |
+
"lstrip": false,
|
| 1728 |
+
"normalized": false,
|
| 1729 |
+
"rstrip": false,
|
| 1730 |
+
"single_word": false,
|
| 1731 |
+
"special": false
|
| 1732 |
+
},
|
| 1733 |
+
"216": {
|
| 1734 |
+
"content": "</code>",
|
| 1735 |
+
"lstrip": false,
|
| 1736 |
+
"normalized": false,
|
| 1737 |
+
"rstrip": false,
|
| 1738 |
+
"single_word": false,
|
| 1739 |
+
"special": false
|
| 1740 |
+
},
|
| 1741 |
+
"255968": {
|
| 1742 |
+
"content": "[toxicity=0]",
|
| 1743 |
+
"lstrip": false,
|
| 1744 |
+
"normalized": false,
|
| 1745 |
+
"rstrip": false,
|
| 1746 |
+
"single_word": false,
|
| 1747 |
+
"special": false
|
| 1748 |
+
},
|
| 1749 |
+
"255969": {
|
| 1750 |
+
"content": "\t\t",
|
| 1751 |
+
"lstrip": false,
|
| 1752 |
+
"normalized": false,
|
| 1753 |
+
"rstrip": false,
|
| 1754 |
+
"single_word": false,
|
| 1755 |
+
"special": false
|
| 1756 |
+
},
|
| 1757 |
+
"255970": {
|
| 1758 |
+
"content": "\t\t\t",
|
| 1759 |
+
"lstrip": false,
|
| 1760 |
+
"normalized": false,
|
| 1761 |
+
"rstrip": false,
|
| 1762 |
+
"single_word": false,
|
| 1763 |
+
"special": false
|
| 1764 |
+
},
|
| 1765 |
+
"255971": {
|
| 1766 |
+
"content": "\t\t\t\t",
|
| 1767 |
+
"lstrip": false,
|
| 1768 |
+
"normalized": false,
|
| 1769 |
+
"rstrip": false,
|
| 1770 |
+
"single_word": false,
|
| 1771 |
+
"special": false
|
| 1772 |
+
},
|
| 1773 |
+
"255972": {
|
| 1774 |
+
"content": "\t\t\t\t\t",
|
| 1775 |
+
"lstrip": false,
|
| 1776 |
+
"normalized": false,
|
| 1777 |
+
"rstrip": false,
|
| 1778 |
+
"single_word": false,
|
| 1779 |
+
"special": false
|
| 1780 |
+
},
|
| 1781 |
+
"255973": {
|
| 1782 |
+
"content": "\t\t\t\t\t\t",
|
| 1783 |
+
"lstrip": false,
|
| 1784 |
+
"normalized": false,
|
| 1785 |
+
"rstrip": false,
|
| 1786 |
+
"single_word": false,
|
| 1787 |
+
"special": false
|
| 1788 |
+
},
|
| 1789 |
+
"255974": {
|
| 1790 |
+
"content": "\t\t\t\t\t\t\t",
|
| 1791 |
+
"lstrip": false,
|
| 1792 |
+
"normalized": false,
|
| 1793 |
+
"rstrip": false,
|
| 1794 |
+
"single_word": false,
|
| 1795 |
+
"special": false
|
| 1796 |
+
},
|
| 1797 |
+
"255975": {
|
| 1798 |
+
"content": "\t\t\t\t\t\t\t\t",
|
| 1799 |
+
"lstrip": false,
|
| 1800 |
+
"normalized": false,
|
| 1801 |
+
"rstrip": false,
|
| 1802 |
+
"single_word": false,
|
| 1803 |
+
"special": false
|
| 1804 |
+
},
|
| 1805 |
+
"255976": {
|
| 1806 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
| 1807 |
+
"lstrip": false,
|
| 1808 |
+
"normalized": false,
|
| 1809 |
+
"rstrip": false,
|
| 1810 |
+
"single_word": false,
|
| 1811 |
+
"special": false
|
| 1812 |
+
},
|
| 1813 |
+
"255977": {
|
| 1814 |
+
"content": "\t\t\t\t\t\t\t\t\t\t",
|
| 1815 |
+
"lstrip": false,
|
| 1816 |
+
"normalized": false,
|
| 1817 |
+
"rstrip": false,
|
| 1818 |
+
"single_word": false,
|
| 1819 |
+
"special": false
|
| 1820 |
+
},
|
| 1821 |
+
"255978": {
|
| 1822 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t",
|
| 1823 |
+
"lstrip": false,
|
| 1824 |
+
"normalized": false,
|
| 1825 |
+
"rstrip": false,
|
| 1826 |
+
"single_word": false,
|
| 1827 |
+
"special": false
|
| 1828 |
+
},
|
| 1829 |
+
"255979": {
|
| 1830 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1831 |
+
"lstrip": false,
|
| 1832 |
+
"normalized": false,
|
| 1833 |
+
"rstrip": false,
|
| 1834 |
+
"single_word": false,
|
| 1835 |
+
"special": false
|
| 1836 |
+
},
|
| 1837 |
+
"255980": {
|
| 1838 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1839 |
+
"lstrip": false,
|
| 1840 |
+
"normalized": false,
|
| 1841 |
+
"rstrip": false,
|
| 1842 |
+
"single_word": false,
|
| 1843 |
+
"special": false
|
| 1844 |
+
},
|
| 1845 |
+
"255981": {
|
| 1846 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1847 |
+
"lstrip": false,
|
| 1848 |
+
"normalized": false,
|
| 1849 |
+
"rstrip": false,
|
| 1850 |
+
"single_word": false,
|
| 1851 |
+
"special": false
|
| 1852 |
+
},
|
| 1853 |
+
"255982": {
|
| 1854 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1855 |
+
"lstrip": false,
|
| 1856 |
+
"normalized": false,
|
| 1857 |
+
"rstrip": false,
|
| 1858 |
+
"single_word": false,
|
| 1859 |
+
"special": false
|
| 1860 |
+
},
|
| 1861 |
+
"255983": {
|
| 1862 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1863 |
+
"lstrip": false,
|
| 1864 |
+
"normalized": false,
|
| 1865 |
+
"rstrip": false,
|
| 1866 |
+
"single_word": false,
|
| 1867 |
+
"special": false
|
| 1868 |
+
},
|
| 1869 |
+
"255984": {
|
| 1870 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1871 |
+
"lstrip": false,
|
| 1872 |
+
"normalized": false,
|
| 1873 |
+
"rstrip": false,
|
| 1874 |
+
"single_word": false,
|
| 1875 |
+
"special": false
|
| 1876 |
+
},
|
| 1877 |
+
"255985": {
|
| 1878 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1879 |
+
"lstrip": false,
|
| 1880 |
+
"normalized": false,
|
| 1881 |
+
"rstrip": false,
|
| 1882 |
+
"single_word": false,
|
| 1883 |
+
"special": false
|
| 1884 |
+
},
|
| 1885 |
+
"255986": {
|
| 1886 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1887 |
+
"lstrip": false,
|
| 1888 |
+
"normalized": false,
|
| 1889 |
+
"rstrip": false,
|
| 1890 |
+
"single_word": false,
|
| 1891 |
+
"special": false
|
| 1892 |
+
},
|
| 1893 |
+
"255987": {
|
| 1894 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1895 |
+
"lstrip": false,
|
| 1896 |
+
"normalized": false,
|
| 1897 |
+
"rstrip": false,
|
| 1898 |
+
"single_word": false,
|
| 1899 |
+
"special": false
|
| 1900 |
+
},
|
| 1901 |
+
"255988": {
|
| 1902 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1903 |
+
"lstrip": false,
|
| 1904 |
+
"normalized": false,
|
| 1905 |
+
"rstrip": false,
|
| 1906 |
+
"single_word": false,
|
| 1907 |
+
"special": false
|
| 1908 |
+
},
|
| 1909 |
+
"255989": {
|
| 1910 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1911 |
+
"lstrip": false,
|
| 1912 |
+
"normalized": false,
|
| 1913 |
+
"rstrip": false,
|
| 1914 |
+
"single_word": false,
|
| 1915 |
+
"special": false
|
| 1916 |
+
},
|
| 1917 |
+
"255990": {
|
| 1918 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1919 |
+
"lstrip": false,
|
| 1920 |
+
"normalized": false,
|
| 1921 |
+
"rstrip": false,
|
| 1922 |
+
"single_word": false,
|
| 1923 |
+
"special": false
|
| 1924 |
+
},
|
| 1925 |
+
"255991": {
|
| 1926 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1927 |
+
"lstrip": false,
|
| 1928 |
+
"normalized": false,
|
| 1929 |
+
"rstrip": false,
|
| 1930 |
+
"single_word": false,
|
| 1931 |
+
"special": false
|
| 1932 |
+
},
|
| 1933 |
+
"255992": {
|
| 1934 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1935 |
+
"lstrip": false,
|
| 1936 |
+
"normalized": false,
|
| 1937 |
+
"rstrip": false,
|
| 1938 |
+
"single_word": false,
|
| 1939 |
+
"special": false
|
| 1940 |
+
},
|
| 1941 |
+
"255993": {
|
| 1942 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1943 |
+
"lstrip": false,
|
| 1944 |
+
"normalized": false,
|
| 1945 |
+
"rstrip": false,
|
| 1946 |
+
"single_word": false,
|
| 1947 |
+
"special": false
|
| 1948 |
+
},
|
| 1949 |
+
"255994": {
|
| 1950 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1951 |
+
"lstrip": false,
|
| 1952 |
+
"normalized": false,
|
| 1953 |
+
"rstrip": false,
|
| 1954 |
+
"single_word": false,
|
| 1955 |
+
"special": false
|
| 1956 |
+
},
|
| 1957 |
+
"255995": {
|
| 1958 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1959 |
+
"lstrip": false,
|
| 1960 |
+
"normalized": false,
|
| 1961 |
+
"rstrip": false,
|
| 1962 |
+
"single_word": false,
|
| 1963 |
+
"special": false
|
| 1964 |
+
},
|
| 1965 |
+
"255996": {
|
| 1966 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1967 |
+
"lstrip": false,
|
| 1968 |
+
"normalized": false,
|
| 1969 |
+
"rstrip": false,
|
| 1970 |
+
"single_word": false,
|
| 1971 |
+
"special": false
|
| 1972 |
+
},
|
| 1973 |
+
"255997": {
|
| 1974 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1975 |
+
"lstrip": false,
|
| 1976 |
+
"normalized": false,
|
| 1977 |
+
"rstrip": false,
|
| 1978 |
+
"single_word": false,
|
| 1979 |
+
"special": false
|
| 1980 |
+
},
|
| 1981 |
+
"255998": {
|
| 1982 |
+
"content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
|
| 1983 |
+
"lstrip": false,
|
| 1984 |
+
"normalized": false,
|
| 1985 |
+
"rstrip": false,
|
| 1986 |
+
"single_word": false,
|
| 1987 |
+
"special": false
|
| 1988 |
+
},
|
| 1989 |
+
"255999": {
|
| 1990 |
+
"content": "<unused99>",
|
| 1991 |
+
"lstrip": false,
|
| 1992 |
+
"normalized": false,
|
| 1993 |
+
"rstrip": false,
|
| 1994 |
+
"single_word": false,
|
| 1995 |
+
"special": false
|
| 1996 |
+
}
|
| 1997 |
+
},
|
| 1998 |
+
"additional_special_tokens": [
|
| 1999 |
+
"<start_of_turn>",
|
| 2000 |
+
"<end_of_turn>"
|
| 2001 |
+
],
|
| 2002 |
+
"bos_token": "<bos>",
|
| 2003 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
| 2004 |
+
"clean_up_tokenization_spaces": false,
|
| 2005 |
+
"eos_token": "<eos>",
|
| 2006 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2007 |
+
"pad_token": "<pad>",
|
| 2008 |
+
"padding_side": "right",
|
| 2009 |
+
"sp_model_kwargs": {},
|
| 2010 |
+
"spaces_between_special_tokens": false,
|
| 2011 |
+
"split_special_tokens": false,
|
| 2012 |
+
"tokenizer_class": "GemmaTokenizer",
|
| 2013 |
+
"unk_token": "<unk>",
|
| 2014 |
+
"use_default_system_prompt": false
|
| 2015 |
+
}
|
wizardlm/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1.2071933436588196e+18,
|
| 4 |
+
"train_loss": 0.5702266787943867,
|
| 5 |
+
"train_runtime": 4287.601,
|
| 6 |
+
"train_samples_per_second": 33.024,
|
| 7 |
+
"train_steps_per_second": 1.032
|
| 8 |
+
}
|
wizardlm/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 4425, "loss": 1.0465, "learning_rate": 4.5146726862302485e-06, "epoch": 0.011299435028248588, "percentage": 0.23, "elapsed_time": "0:00:12", "remaining_time": "1:33:00"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 4425, "loss": 1.0939, "learning_rate": 9.029345372460497e-06, "epoch": 0.022598870056497175, "percentage": 0.45, "elapsed_time": "0:00:21", "remaining_time": "1:18:50"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 4425, "loss": 1.0292, "learning_rate": 1.3544018058690747e-05, "epoch": 0.03389830508474576, "percentage": 0.68, "elapsed_time": "0:00:30", "remaining_time": "1:15:12"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 4425, "loss": 0.995, "learning_rate": 1.8058690744920994e-05, "epoch": 0.04519774011299435, "percentage": 0.9, "elapsed_time": "0:00:41", "remaining_time": "1:14:54"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 4425, "loss": 0.896, "learning_rate": 2.2573363431151244e-05, "epoch": 0.05649717514124294, "percentage": 1.13, "elapsed_time": "0:00:51", "remaining_time": "1:15:33"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 4425, "loss": 0.8037, "learning_rate": 2.7088036117381494e-05, "epoch": 0.06779661016949153, "percentage": 1.36, "elapsed_time": "0:01:00", "remaining_time": "1:13:29"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 4425, "loss": 0.7872, "learning_rate": 3.1602708803611745e-05, "epoch": 0.07909604519774012, "percentage": 1.58, "elapsed_time": "0:01:09", "remaining_time": "1:12:04"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 4425, "loss": 0.7697, "learning_rate": 3.611738148984199e-05, "epoch": 0.0903954802259887, "percentage": 1.81, "elapsed_time": "0:01:19", "remaining_time": "1:11:43"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 4425, "loss": 0.7481, "learning_rate": 4.063205417607224e-05, "epoch": 0.1016949152542373, "percentage": 2.03, "elapsed_time": "0:01:29", "remaining_time": "1:11:47"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 4425, "loss": 0.7166, "learning_rate": 4.514672686230249e-05, "epoch": 0.11299435028248588, "percentage": 2.26, "elapsed_time": "0:01:39", "remaining_time": "1:11:25"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 4425, "loss": 0.7455, "learning_rate": 4.966139954853273e-05, "epoch": 0.12429378531073447, "percentage": 2.49, "elapsed_time": "0:01:49", "remaining_time": "1:11:38"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 4425, "loss": 0.7451, "learning_rate": 5.417607223476299e-05, "epoch": 0.13559322033898305, "percentage": 2.71, "elapsed_time": "0:01:59", "remaining_time": "1:11:11"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 4425, "loss": 0.7235, "learning_rate": 5.869074492099323e-05, "epoch": 0.14689265536723164, "percentage": 2.94, "elapsed_time": "0:02:08", "remaining_time": "1:10:51"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 4425, "loss": 0.7201, "learning_rate": 6.320541760722349e-05, "epoch": 0.15819209039548024, "percentage": 3.16, "elapsed_time": "0:02:17", "remaining_time": "1:10:14"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 4425, "loss": 0.7199, "learning_rate": 6.772009029345373e-05, "epoch": 0.1694915254237288, "percentage": 3.39, "elapsed_time": "0:02:27", "remaining_time": "1:10:00"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 4425, "loss": 0.7134, "learning_rate": 7.223476297968398e-05, "epoch": 0.1807909604519774, "percentage": 3.62, "elapsed_time": "0:02:37", "remaining_time": "1:09:47"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 4425, "loss": 0.7193, "learning_rate": 7.674943566591423e-05, "epoch": 0.192090395480226, "percentage": 3.84, "elapsed_time": "0:02:47", "remaining_time": "1:09:46"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 4425, "loss": 0.7049, "learning_rate": 8.126410835214448e-05, "epoch": 0.2033898305084746, "percentage": 4.07, "elapsed_time": "0:02:55", "remaining_time": "1:09:06"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 4425, "loss": 0.719, "learning_rate": 8.577878103837473e-05, "epoch": 0.21468926553672316, "percentage": 4.29, "elapsed_time": "0:03:05", "remaining_time": "1:08:44"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 4425, "loss": 0.7077, "learning_rate": 9.029345372460498e-05, "epoch": 0.22598870056497175, "percentage": 4.52, "elapsed_time": "0:03:15", "remaining_time": "1:08:41"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 4425, "loss": 0.7301, "learning_rate": 9.480812641083521e-05, "epoch": 0.23728813559322035, "percentage": 4.75, "elapsed_time": "0:03:24", "remaining_time": "1:08:26"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 4425, "loss": 0.7174, "learning_rate": 9.932279909706546e-05, "epoch": 0.24858757062146894, "percentage": 4.97, "elapsed_time": "0:03:34", "remaining_time": "1:08:15"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 4425, "loss": 0.7163, "learning_rate": 0.00010383747178329573, "epoch": 0.2598870056497175, "percentage": 5.2, "elapsed_time": "0:03:44", "remaining_time": "1:08:18"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 4425, "loss": 0.7206, "learning_rate": 0.00010835214446952598, "epoch": 0.2711864406779661, "percentage": 5.42, "elapsed_time": "0:03:53", "remaining_time": "1:07:47"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 4425, "loss": 0.7198, "learning_rate": 0.00011286681715575623, "epoch": 0.2824858757062147, "percentage": 5.65, "elapsed_time": "0:04:02", "remaining_time": "1:07:23"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 4425, "loss": 0.6791, "learning_rate": 0.00011738148984198646, "epoch": 0.2937853107344633, "percentage": 5.88, "elapsed_time": "0:04:11", "remaining_time": "1:07:04"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 4425, "loss": 0.7379, "learning_rate": 0.00012189616252821671, "epoch": 0.3050847457627119, "percentage": 6.1, "elapsed_time": "0:04:20", "remaining_time": "1:06:41"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 4425, "loss": 0.7146, "learning_rate": 0.00012641083521444698, "epoch": 0.3163841807909605, "percentage": 6.33, "elapsed_time": "0:04:28", "remaining_time": "1:06:19"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 4425, "loss": 0.6855, "learning_rate": 0.00013092550790067722, "epoch": 0.327683615819209, "percentage": 6.55, "elapsed_time": "0:04:38", "remaining_time": "1:06:18"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 4425, "loss": 0.7169, "learning_rate": 0.00013544018058690745, "epoch": 0.3389830508474576, "percentage": 6.78, "elapsed_time": "0:04:49", "remaining_time": "1:06:19"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 4425, "loss": 0.7079, "learning_rate": 0.00013995485327313772, "epoch": 0.3502824858757062, "percentage": 7.01, "elapsed_time": "0:04:59", "remaining_time": "1:06:18"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 4425, "loss": 0.68, "learning_rate": 0.00014446952595936795, "epoch": 0.3615819209039548, "percentage": 7.23, "elapsed_time": "0:05:09", "remaining_time": "1:06:05"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 4425, "loss": 0.7247, "learning_rate": 0.00014898419864559822, "epoch": 0.3728813559322034, "percentage": 7.46, "elapsed_time": "0:05:17", "remaining_time": "1:05:45"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 4425, "loss": 0.6753, "learning_rate": 0.00015349887133182845, "epoch": 0.384180790960452, "percentage": 7.68, "elapsed_time": "0:05:27", "remaining_time": "1:05:30"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 4425, "loss": 0.6616, "learning_rate": 0.0001580135440180587, "epoch": 0.3954802259887006, "percentage": 7.91, "elapsed_time": "0:05:37", "remaining_time": "1:05:33"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 4425, "loss": 0.686, "learning_rate": 0.00016252821670428895, "epoch": 0.4067796610169492, "percentage": 8.14, "elapsed_time": "0:05:47", "remaining_time": "1:05:24"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 4425, "loss": 0.7086, "learning_rate": 0.0001670428893905192, "epoch": 0.4180790960451977, "percentage": 8.36, "elapsed_time": "0:05:57", "remaining_time": "1:05:16"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 4425, "loss": 0.6966, "learning_rate": 0.00017155756207674945, "epoch": 0.4293785310734463, "percentage": 8.59, "elapsed_time": "0:06:07", "remaining_time": "1:05:09"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 4425, "loss": 0.7406, "learning_rate": 0.0001760722347629797, "epoch": 0.4406779661016949, "percentage": 8.81, "elapsed_time": "0:06:16", "remaining_time": "1:04:50"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 4425, "loss": 0.6772, "learning_rate": 0.00018058690744920995, "epoch": 0.4519774011299435, "percentage": 9.04, "elapsed_time": "0:06:25", "remaining_time": "1:04:39"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 4425, "loss": 0.6843, "learning_rate": 0.0001851015801354402, "epoch": 0.4632768361581921, "percentage": 9.27, "elapsed_time": "0:06:37", "remaining_time": "1:04:57"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 4425, "loss": 0.7206, "learning_rate": 0.00018961625282167043, "epoch": 0.4745762711864407, "percentage": 9.49, "elapsed_time": "0:06:47", "remaining_time": "1:04:42"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 4425, "loss": 0.6879, "learning_rate": 0.0001941309255079007, "epoch": 0.4858757062146893, "percentage": 9.72, "elapsed_time": "0:06:55", "remaining_time": "1:04:20"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 4425, "loss": 0.7032, "learning_rate": 0.00019864559819413093, "epoch": 0.4971751412429379, "percentage": 9.94, "elapsed_time": "0:07:05", "remaining_time": "1:04:10"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 4425, "loss": 0.7086, "learning_rate": 0.00019999847502678901, "epoch": 0.5084745762711864, "percentage": 10.17, "elapsed_time": "0:07:14", "remaining_time": "1:03:59"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 4425, "loss": 0.6709, "learning_rate": 0.00019999100588221217, "epoch": 0.519774011299435, "percentage": 10.4, "elapsed_time": "0:07:26", "remaining_time": "1:04:06"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 4425, "loss": 0.6901, "learning_rate": 0.00019997731293347473, "epoch": 0.5310734463276836, "percentage": 10.62, "elapsed_time": "0:07:36", "remaining_time": "1:03:57"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 4425, "loss": 0.6748, "learning_rate": 0.00019995739703287558, "epoch": 0.5423728813559322, "percentage": 10.85, "elapsed_time": "0:07:45", "remaining_time": "1:03:47"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 4425, "loss": 0.6908, "learning_rate": 0.00019993125942005297, "epoch": 0.5536723163841808, "percentage": 11.07, "elapsed_time": "0:07:55", "remaining_time": "1:03:40"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 4425, "loss": 0.6961, "learning_rate": 0.00019989890172190697, "epoch": 0.5649717514124294, "percentage": 11.3, "elapsed_time": "0:08:05", "remaining_time": "1:03:32"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 4425, "loss": 0.6741, "learning_rate": 0.00019986032595249855, "epoch": 0.576271186440678, "percentage": 11.53, "elapsed_time": "0:08:16", "remaining_time": "1:03:29"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 4425, "loss": 0.6681, "learning_rate": 0.00019981553451292396, "epoch": 0.5875706214689266, "percentage": 11.75, "elapsed_time": "0:08:26", "remaining_time": "1:03:21"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 4425, "loss": 0.7027, "learning_rate": 0.00019976453019116547, "epoch": 0.5988700564971752, "percentage": 11.98, "elapsed_time": "0:08:35", "remaining_time": "1:03:05"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 4425, "loss": 0.6955, "learning_rate": 0.00019970731616191772, "epoch": 0.6101694915254238, "percentage": 12.2, "elapsed_time": "0:08:43", "remaining_time": "1:02:49"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 4425, "loss": 0.6617, "learning_rate": 0.00019964389598639012, "epoch": 0.6214689265536724, "percentage": 12.43, "elapsed_time": "0:08:53", "remaining_time": "1:02:40"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 4425, "loss": 0.6896, "learning_rate": 0.00019957427361208522, "epoch": 0.632768361581921, "percentage": 12.66, "elapsed_time": "0:09:03", "remaining_time": "1:02:32"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 4425, "loss": 0.6786, "learning_rate": 0.00019949845337255306, "epoch": 0.6440677966101694, "percentage": 12.88, "elapsed_time": "0:09:12", "remaining_time": "1:02:19"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 4425, "loss": 0.685, "learning_rate": 0.00019941643998712128, "epoch": 0.655367231638418, "percentage": 13.11, "elapsed_time": "0:09:22", "remaining_time": "1:02:07"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 4425, "loss": 0.691, "learning_rate": 0.00019932823856060153, "epoch": 0.6666666666666666, "percentage": 13.33, "elapsed_time": "0:09:31", "remaining_time": "1:01:53"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 4425, "loss": 0.7076, "learning_rate": 0.00019923385458297168, "epoch": 0.6779661016949152, "percentage": 13.56, "elapsed_time": "0:09:40", "remaining_time": "1:01:39"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 4425, "loss": 0.6628, "learning_rate": 0.00019913329392903396, "epoch": 0.6892655367231638, "percentage": 13.79, "elapsed_time": "0:09:50", "remaining_time": "1:01:30"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 4425, "loss": 0.6973, "learning_rate": 0.00019902656285804954, "epoch": 0.7005649717514124, "percentage": 14.01, "elapsed_time": "0:09:59", "remaining_time": "1:01:21"}
|
| 63 |
+
{"current_steps": 630, "total_steps": 4425, "loss": 0.668, "learning_rate": 0.0001989136680133488, "epoch": 0.711864406779661, "percentage": 14.24, "elapsed_time": "0:10:09", "remaining_time": "1:01:12"}
|
| 64 |
+
{"current_steps": 640, "total_steps": 4425, "loss": 0.6839, "learning_rate": 0.00019879461642191774, "epoch": 0.7231638418079096, "percentage": 14.46, "elapsed_time": "0:10:21", "remaining_time": "1:01:17"}
|
| 65 |
+
{"current_steps": 650, "total_steps": 4425, "loss": 0.6929, "learning_rate": 0.00019866941549396075, "epoch": 0.7344632768361582, "percentage": 14.69, "elapsed_time": "0:10:30", "remaining_time": "1:01:02"}
|
| 66 |
+
{"current_steps": 660, "total_steps": 4425, "loss": 0.701, "learning_rate": 0.0001985380730224393, "epoch": 0.7457627118644068, "percentage": 14.92, "elapsed_time": "0:10:40", "remaining_time": "1:00:51"}
|
| 67 |
+
{"current_steps": 670, "total_steps": 4425, "loss": 0.7222, "learning_rate": 0.00019840059718258693, "epoch": 0.7570621468926554, "percentage": 15.14, "elapsed_time": "0:10:49", "remaining_time": "1:00:38"}
|
| 68 |
+
{"current_steps": 680, "total_steps": 4425, "loss": 0.6919, "learning_rate": 0.00019825699653140032, "epoch": 0.768361581920904, "percentage": 15.37, "elapsed_time": "0:10:58", "remaining_time": "1:00:26"}
|
| 69 |
+
{"current_steps": 690, "total_steps": 4425, "loss": 0.6859, "learning_rate": 0.0001981072800071066, "epoch": 0.7796610169491526, "percentage": 15.59, "elapsed_time": "0:11:07", "remaining_time": "1:00:11"}
|
| 70 |
+
{"current_steps": 700, "total_steps": 4425, "loss": 0.666, "learning_rate": 0.00019795145692860726, "epoch": 0.7909604519774012, "percentage": 15.82, "elapsed_time": "0:11:17", "remaining_time": "1:00:02"}
|
| 71 |
+
{"current_steps": 710, "total_steps": 4425, "loss": 0.6587, "learning_rate": 0.00019778953699489785, "epoch": 0.8022598870056498, "percentage": 16.05, "elapsed_time": "0:11:26", "remaining_time": "0:59:52"}
|
| 72 |
+
{"current_steps": 720, "total_steps": 4425, "loss": 0.6766, "learning_rate": 0.0001976215302844644, "epoch": 0.8135593220338984, "percentage": 16.27, "elapsed_time": "0:11:35", "remaining_time": "0:59:38"}
|
| 73 |
+
{"current_steps": 730, "total_steps": 4425, "loss": 0.6836, "learning_rate": 0.00019744744725465617, "epoch": 0.8248587570621468, "percentage": 16.5, "elapsed_time": "0:11:44", "remaining_time": "0:59:25"}
|
| 74 |
+
{"current_steps": 740, "total_steps": 4425, "loss": 0.6729, "learning_rate": 0.00019726729874103448, "epoch": 0.8361581920903954, "percentage": 16.72, "elapsed_time": "0:11:53", "remaining_time": "0:59:14"}
|
| 75 |
+
{"current_steps": 750, "total_steps": 4425, "loss": 0.6811, "learning_rate": 0.00019708109595669858, "epoch": 0.847457627118644, "percentage": 16.95, "elapsed_time": "0:12:02", "remaining_time": "0:59:01"}
|
| 76 |
+
{"current_steps": 760, "total_steps": 4425, "loss": 0.7353, "learning_rate": 0.00019688885049158752, "epoch": 0.8587570621468926, "percentage": 17.18, "elapsed_time": "0:12:12", "remaining_time": "0:58:51"}
|
| 77 |
+
{"current_steps": 770, "total_steps": 4425, "loss": 0.6938, "learning_rate": 0.0001966905743117588, "epoch": 0.8700564971751412, "percentage": 17.4, "elapsed_time": "0:12:21", "remaining_time": "0:58:39"}
|
| 78 |
+
{"current_steps": 780, "total_steps": 4425, "loss": 0.6724, "learning_rate": 0.00019648627975864355, "epoch": 0.8813559322033898, "percentage": 17.63, "elapsed_time": "0:12:30", "remaining_time": "0:58:26"}
|
| 79 |
+
{"current_steps": 790, "total_steps": 4425, "loss": 0.6901, "learning_rate": 0.00019627597954827833, "epoch": 0.8926553672316384, "percentage": 17.85, "elapsed_time": "0:12:40", "remaining_time": "0:58:19"}
|
| 80 |
+
{"current_steps": 800, "total_steps": 4425, "loss": 0.7008, "learning_rate": 0.00019605968677051378, "epoch": 0.903954802259887, "percentage": 18.08, "elapsed_time": "0:12:49", "remaining_time": "0:58:04"}
|
| 81 |
+
{"current_steps": 810, "total_steps": 4425, "loss": 0.6567, "learning_rate": 0.0001958374148881996, "epoch": 0.9152542372881356, "percentage": 18.31, "elapsed_time": "0:12:58", "remaining_time": "0:57:55"}
|
| 82 |
+
{"current_steps": 820, "total_steps": 4425, "loss": 0.6756, "learning_rate": 0.00019560917773634676, "epoch": 0.9265536723163842, "percentage": 18.53, "elapsed_time": "0:13:07", "remaining_time": "0:57:40"}
|
| 83 |
+
{"current_steps": 830, "total_steps": 4425, "loss": 0.6958, "learning_rate": 0.00019537498952126642, "epoch": 0.9378531073446328, "percentage": 18.76, "elapsed_time": "0:13:17", "remaining_time": "0:57:32"}
|
| 84 |
+
{"current_steps": 840, "total_steps": 4425, "loss": 0.6871, "learning_rate": 0.00019513486481968545, "epoch": 0.9491525423728814, "percentage": 18.98, "elapsed_time": "0:13:25", "remaining_time": "0:57:17"}
|
| 85 |
+
{"current_steps": 850, "total_steps": 4425, "loss": 0.6956, "learning_rate": 0.00019488881857783935, "epoch": 0.96045197740113, "percentage": 19.21, "elapsed_time": "0:13:34", "remaining_time": "0:57:05"}
|
| 86 |
+
{"current_steps": 860, "total_steps": 4425, "loss": 0.6865, "learning_rate": 0.00019463686611054172, "epoch": 0.9717514124293786, "percentage": 19.44, "elapsed_time": "0:13:45", "remaining_time": "0:57:00"}
|
| 87 |
+
{"current_steps": 870, "total_steps": 4425, "loss": 0.6845, "learning_rate": 0.00019437902310023126, "epoch": 0.9830508474576272, "percentage": 19.66, "elapsed_time": "0:13:54", "remaining_time": "0:56:49"}
|
| 88 |
+
{"current_steps": 880, "total_steps": 4425, "loss": 0.6589, "learning_rate": 0.0001941153055959954, "epoch": 0.9943502824858758, "percentage": 19.89, "elapsed_time": "0:14:04", "remaining_time": "0:56:41"}
|
| 89 |
+
{"current_steps": 890, "total_steps": 4425, "loss": 0.671, "learning_rate": 0.00019384573001257155, "epoch": 1.0056497175141244, "percentage": 20.11, "elapsed_time": "0:14:14", "remaining_time": "0:56:34"}
|
| 90 |
+
{"current_steps": 900, "total_steps": 4425, "loss": 0.608, "learning_rate": 0.0001935703131293252, "epoch": 1.0169491525423728, "percentage": 20.34, "elapsed_time": "0:14:24", "remaining_time": "0:56:27"}
|
| 91 |
+
{"current_steps": 910, "total_steps": 4425, "loss": 0.6457, "learning_rate": 0.00019328907208920567, "epoch": 1.0282485875706215, "percentage": 20.56, "elapsed_time": "0:14:32", "remaining_time": "0:56:11"}
|
| 92 |
+
{"current_steps": 920, "total_steps": 4425, "loss": 0.6105, "learning_rate": 0.00019300202439767898, "epoch": 1.03954802259887, "percentage": 20.79, "elapsed_time": "0:14:42", "remaining_time": "0:56:03"}
|
| 93 |
+
{"current_steps": 930, "total_steps": 4425, "loss": 0.6221, "learning_rate": 0.00019270918792163827, "epoch": 1.0508474576271187, "percentage": 21.02, "elapsed_time": "0:14:52", "remaining_time": "0:55:52"}
|
| 94 |
+
{"current_steps": 940, "total_steps": 4425, "loss": 0.6465, "learning_rate": 0.00019241058088829166, "epoch": 1.0621468926553672, "percentage": 21.24, "elapsed_time": "0:15:03", "remaining_time": "0:55:50"}
|
| 95 |
+
{"current_steps": 950, "total_steps": 4425, "loss": 0.6374, "learning_rate": 0.00019210622188402788, "epoch": 1.073446327683616, "percentage": 21.47, "elapsed_time": "0:15:12", "remaining_time": "0:55:36"}
|
| 96 |
+
{"current_steps": 960, "total_steps": 4425, "loss": 0.6226, "learning_rate": 0.00019179612985325908, "epoch": 1.0847457627118644, "percentage": 21.69, "elapsed_time": "0:15:21", "remaining_time": "0:55:25"}
|
| 97 |
+
{"current_steps": 970, "total_steps": 4425, "loss": 0.6604, "learning_rate": 0.000191480324097242, "epoch": 1.0960451977401129, "percentage": 21.92, "elapsed_time": "0:15:30", "remaining_time": "0:55:15"}
|
| 98 |
+
{"current_steps": 980, "total_steps": 4425, "loss": 0.6466, "learning_rate": 0.00019115882427287638, "epoch": 1.1073446327683616, "percentage": 22.15, "elapsed_time": "0:15:39", "remaining_time": "0:55:04"}
|
| 99 |
+
{"current_steps": 990, "total_steps": 4425, "loss": 0.6315, "learning_rate": 0.00019083165039148153, "epoch": 1.11864406779661, "percentage": 22.37, "elapsed_time": "0:15:51", "remaining_time": "0:55:02"}
|
| 100 |
+
{"current_steps": 1000, "total_steps": 4425, "loss": 0.6341, "learning_rate": 0.00019049882281755066, "epoch": 1.1299435028248588, "percentage": 22.6, "elapsed_time": "0:16:00", "remaining_time": "0:54:50"}
|
| 101 |
+
{"current_steps": 1000, "total_steps": 4425, "eval_loss": 0.7100452184677124, "epoch": 1.1299435028248588, "percentage": 22.6, "elapsed_time": "0:16:17", "remaining_time": "0:55:47"}
|
| 102 |
+
{"current_steps": 1010, "total_steps": 4425, "loss": 0.6144, "learning_rate": 0.00019016036226748346, "epoch": 1.1412429378531073, "percentage": 22.82, "elapsed_time": "0:16:29", "remaining_time": "0:55:45"}
|
| 103 |
+
{"current_steps": 1020, "total_steps": 4425, "loss": 0.6458, "learning_rate": 0.00018981628980829652, "epoch": 1.152542372881356, "percentage": 23.05, "elapsed_time": "0:16:39", "remaining_time": "0:55:35"}
|
| 104 |
+
{"current_steps": 1030, "total_steps": 4425, "loss": 0.6417, "learning_rate": 0.00018946662685631203, "epoch": 1.1638418079096045, "percentage": 23.28, "elapsed_time": "0:16:48", "remaining_time": "0:55:24"}
|
| 105 |
+
{"current_steps": 1040, "total_steps": 4425, "loss": 0.6355, "learning_rate": 0.0001891113951758249, "epoch": 1.1751412429378532, "percentage": 23.5, "elapsed_time": "0:16:57", "remaining_time": "0:55:11"}
|
| 106 |
+
{"current_steps": 1050, "total_steps": 4425, "loss": 0.6332, "learning_rate": 0.0001887506168777479, "epoch": 1.1864406779661016, "percentage": 23.73, "elapsed_time": "0:17:06", "remaining_time": "0:54:58"}
|
| 107 |
+
{"current_steps": 1060, "total_steps": 4425, "loss": 0.6445, "learning_rate": 0.00018838431441823547, "epoch": 1.1977401129943503, "percentage": 23.95, "elapsed_time": "0:17:18", "remaining_time": "0:54:55"}
|
| 108 |
+
{"current_steps": 1070, "total_steps": 4425, "loss": 0.6314, "learning_rate": 0.00018801251059728604, "epoch": 1.2090395480225988, "percentage": 24.18, "elapsed_time": "0:17:27", "remaining_time": "0:54:44"}
|
| 109 |
+
{"current_steps": 1080, "total_steps": 4425, "loss": 0.6232, "learning_rate": 0.00018763522855732266, "epoch": 1.2203389830508475, "percentage": 24.41, "elapsed_time": "0:17:38", "remaining_time": "0:54:36"}
|
| 110 |
+
{"current_steps": 1090, "total_steps": 4425, "loss": 0.6561, "learning_rate": 0.00018725249178175286, "epoch": 1.231638418079096, "percentage": 24.63, "elapsed_time": "0:17:46", "remaining_time": "0:54:24"}
|
| 111 |
+
{"current_steps": 1100, "total_steps": 4425, "loss": 0.6066, "learning_rate": 0.0001868643240935066, "epoch": 1.2429378531073447, "percentage": 24.86, "elapsed_time": "0:17:57", "remaining_time": "0:54:16"}
|
| 112 |
+
{"current_steps": 1110, "total_steps": 4425, "loss": 0.6367, "learning_rate": 0.0001864707496535537, "epoch": 1.2542372881355932, "percentage": 25.08, "elapsed_time": "0:18:07", "remaining_time": "0:54:08"}
|
| 113 |
+
{"current_steps": 1120, "total_steps": 4425, "loss": 0.6278, "learning_rate": 0.00018607179295939983, "epoch": 1.2655367231638417, "percentage": 25.31, "elapsed_time": "0:18:17", "remaining_time": "0:53:59"}
|
| 114 |
+
{"current_steps": 1130, "total_steps": 4425, "loss": 0.6209, "learning_rate": 0.00018566747884356182, "epoch": 1.2768361581920904, "percentage": 25.54, "elapsed_time": "0:18:27", "remaining_time": "0:53:49"}
|
| 115 |
+
{"current_steps": 1140, "total_steps": 4425, "loss": 0.6525, "learning_rate": 0.00018525783247202188, "epoch": 1.288135593220339, "percentage": 25.76, "elapsed_time": "0:18:37", "remaining_time": "0:53:41"}
|
| 116 |
+
{"current_steps": 1150, "total_steps": 4425, "loss": 0.6367, "learning_rate": 0.00018484287934266122, "epoch": 1.2994350282485876, "percentage": 25.99, "elapsed_time": "0:18:47", "remaining_time": "0:53:30"}
|
| 117 |
+
{"current_steps": 1160, "total_steps": 4425, "loss": 0.6499, "learning_rate": 0.00018442264528367304, "epoch": 1.310734463276836, "percentage": 26.21, "elapsed_time": "0:18:56", "remaining_time": "0:53:19"}
|
| 118 |
+
{"current_steps": 1170, "total_steps": 4425, "loss": 0.6478, "learning_rate": 0.0001839971564519547, "epoch": 1.3220338983050848, "percentage": 26.44, "elapsed_time": "0:19:05", "remaining_time": "0:53:07"}
|
| 119 |
+
{"current_steps": 1180, "total_steps": 4425, "loss": 0.6382, "learning_rate": 0.00018356643933147986, "epoch": 1.3333333333333333, "percentage": 26.67, "elapsed_time": "0:19:16", "remaining_time": "0:52:59"}
|
| 120 |
+
{"current_steps": 1190, "total_steps": 4425, "loss": 0.6373, "learning_rate": 0.00018313052073164982, "epoch": 1.344632768361582, "percentage": 26.89, "elapsed_time": "0:19:26", "remaining_time": "0:52:49"}
|
| 121 |
+
{"current_steps": 1200, "total_steps": 4425, "loss": 0.6231, "learning_rate": 0.00018268942778562494, "epoch": 1.3559322033898304, "percentage": 27.12, "elapsed_time": "0:19:36", "remaining_time": "0:52:41"}
|
| 122 |
+
{"current_steps": 1210, "total_steps": 4425, "loss": 0.6659, "learning_rate": 0.0001822431879486357, "epoch": 1.3672316384180792, "percentage": 27.34, "elapsed_time": "0:19:45", "remaining_time": "0:52:29"}
|
| 123 |
+
{"current_steps": 1220, "total_steps": 4425, "loss": 0.6467, "learning_rate": 0.00018179182899627386, "epoch": 1.3785310734463276, "percentage": 27.57, "elapsed_time": "0:19:55", "remaining_time": "0:52:20"}
|
| 124 |
+
{"current_steps": 1230, "total_steps": 4425, "loss": 0.6479, "learning_rate": 0.00018133537902276342, "epoch": 1.3898305084745763, "percentage": 27.8, "elapsed_time": "0:20:04", "remaining_time": "0:52:09"}
|
| 125 |
+
{"current_steps": 1240, "total_steps": 4425, "loss": 0.613, "learning_rate": 0.0001808738664392122, "epoch": 1.4011299435028248, "percentage": 28.02, "elapsed_time": "0:20:14", "remaining_time": "0:51:59"}
|
| 126 |
+
{"current_steps": 1250, "total_steps": 4425, "loss": 0.6308, "learning_rate": 0.0001804073199718432, "epoch": 1.4124293785310735, "percentage": 28.25, "elapsed_time": "0:20:23", "remaining_time": "0:51:48"}
|
| 127 |
+
{"current_steps": 1260, "total_steps": 4425, "loss": 0.6412, "learning_rate": 0.0001799357686602068, "epoch": 1.423728813559322, "percentage": 28.47, "elapsed_time": "0:20:31", "remaining_time": "0:51:34"}
|
| 128 |
+
{"current_steps": 1270, "total_steps": 4425, "loss": 0.6242, "learning_rate": 0.00017945924185537295, "epoch": 1.4350282485875705, "percentage": 28.7, "elapsed_time": "0:20:41", "remaining_time": "0:51:24"}
|
| 129 |
+
{"current_steps": 1280, "total_steps": 4425, "loss": 0.6269, "learning_rate": 0.00017897776921810453, "epoch": 1.4463276836158192, "percentage": 28.93, "elapsed_time": "0:20:49", "remaining_time": "0:51:11"}
|
| 130 |
+
{"current_steps": 1290, "total_steps": 4425, "loss": 0.6206, "learning_rate": 0.00017849138071701092, "epoch": 1.457627118644068, "percentage": 29.15, "elapsed_time": "0:21:00", "remaining_time": "0:51:02"}
|
| 131 |
+
{"current_steps": 1300, "total_steps": 4425, "loss": 0.6398, "learning_rate": 0.0001780001066266829, "epoch": 1.4689265536723164, "percentage": 29.38, "elapsed_time": "0:21:09", "remaining_time": "0:50:50"}
|
| 132 |
+
{"current_steps": 1310, "total_steps": 4425, "loss": 0.6299, "learning_rate": 0.00017750397752580796, "epoch": 1.4802259887005649, "percentage": 29.6, "elapsed_time": "0:21:18", "remaining_time": "0:50:40"}
|
| 133 |
+
{"current_steps": 1320, "total_steps": 4425, "loss": 0.6511, "learning_rate": 0.00017700302429526723, "epoch": 1.4915254237288136, "percentage": 29.83, "elapsed_time": "0:21:27", "remaining_time": "0:50:27"}
|
| 134 |
+
{"current_steps": 1330, "total_steps": 4425, "loss": 0.6564, "learning_rate": 0.00017649727811621315, "epoch": 1.5028248587570623, "percentage": 30.06, "elapsed_time": "0:21:37", "remaining_time": "0:50:18"}
|
| 135 |
+
{"current_steps": 1340, "total_steps": 4425, "loss": 0.6186, "learning_rate": 0.0001759867704681288, "epoch": 1.5141242937853108, "percentage": 30.28, "elapsed_time": "0:21:45", "remaining_time": "0:50:06"}
|
| 136 |
+
{"current_steps": 1350, "total_steps": 4425, "loss": 0.6372, "learning_rate": 0.00017547153312686832, "epoch": 1.5254237288135593, "percentage": 30.51, "elapsed_time": "0:21:55", "remaining_time": "0:49:56"}
|
| 137 |
+
{"current_steps": 1360, "total_steps": 4425, "loss": 0.6442, "learning_rate": 0.00017495159816267929, "epoch": 1.536723163841808, "percentage": 30.73, "elapsed_time": "0:22:05", "remaining_time": "0:49:47"}
|
| 138 |
+
{"current_steps": 1370, "total_steps": 4425, "loss": 0.6363, "learning_rate": 0.00017442699793820631, "epoch": 1.5480225988700564, "percentage": 30.96, "elapsed_time": "0:22:15", "remaining_time": "0:49:37"}
|
| 139 |
+
{"current_steps": 1380, "total_steps": 4425, "loss": 0.6399, "learning_rate": 0.00017389776510647688, "epoch": 1.559322033898305, "percentage": 31.19, "elapsed_time": "0:22:25", "remaining_time": "0:49:28"}
|
| 140 |
+
{"current_steps": 1390, "total_steps": 4425, "loss": 0.6073, "learning_rate": 0.0001733639326088688, "epoch": 1.5706214689265536, "percentage": 31.41, "elapsed_time": "0:22:35", "remaining_time": "0:49:19"}
|
| 141 |
+
{"current_steps": 1400, "total_steps": 4425, "loss": 0.65, "learning_rate": 0.00017282553367305975, "epoch": 1.5819209039548023, "percentage": 31.64, "elapsed_time": "0:22:43", "remaining_time": "0:49:06"}
|
| 142 |
+
{"current_steps": 1410, "total_steps": 4425, "loss": 0.626, "learning_rate": 0.00017228260181095925, "epoch": 1.5932203389830508, "percentage": 31.86, "elapsed_time": "0:22:53", "remaining_time": "0:48:57"}
|
| 143 |
+
{"current_steps": 1420, "total_steps": 4425, "loss": 0.6565, "learning_rate": 0.00017173517081662255, "epoch": 1.6045197740112993, "percentage": 32.09, "elapsed_time": "0:23:03", "remaining_time": "0:48:48"}
|
| 144 |
+
{"current_steps": 1430, "total_steps": 4425, "loss": 0.6555, "learning_rate": 0.00017118327476414735, "epoch": 1.615819209039548, "percentage": 32.32, "elapsed_time": "0:23:13", "remaining_time": "0:48:38"}
|
| 145 |
+
{"current_steps": 1440, "total_steps": 4425, "loss": 0.6431, "learning_rate": 0.0001706269480055528, "epoch": 1.6271186440677967, "percentage": 32.54, "elapsed_time": "0:23:22", "remaining_time": "0:48:27"}
|
| 146 |
+
{"current_steps": 1450, "total_steps": 4425, "loss": 0.6383, "learning_rate": 0.00017006622516864127, "epoch": 1.6384180790960452, "percentage": 32.77, "elapsed_time": "0:23:32", "remaining_time": "0:48:18"}
|
| 147 |
+
{"current_steps": 1460, "total_steps": 4425, "loss": 0.6304, "learning_rate": 0.00016950114115484315, "epoch": 1.6497175141242937, "percentage": 32.99, "elapsed_time": "0:23:42", "remaining_time": "0:48:08"}
|
| 148 |
+
{"current_steps": 1470, "total_steps": 4425, "loss": 0.6647, "learning_rate": 0.0001689317311370442, "epoch": 1.6610169491525424, "percentage": 33.22, "elapsed_time": "0:23:51", "remaining_time": "0:47:56"}
|
| 149 |
+
{"current_steps": 1480, "total_steps": 4425, "loss": 0.6288, "learning_rate": 0.0001683580305573966, "epoch": 1.672316384180791, "percentage": 33.45, "elapsed_time": "0:23:59", "remaining_time": "0:47:45"}
|
| 150 |
+
{"current_steps": 1490, "total_steps": 4425, "loss": 0.6067, "learning_rate": 0.0001677800751251126, "epoch": 1.6836158192090396, "percentage": 33.67, "elapsed_time": "0:24:09", "remaining_time": "0:47:35"}
|
| 151 |
+
{"current_steps": 1500, "total_steps": 4425, "loss": 0.6438, "learning_rate": 0.00016719790081424192, "epoch": 1.694915254237288, "percentage": 33.9, "elapsed_time": "0:24:20", "remaining_time": "0:47:28"}
|
| 152 |
+
{"current_steps": 1510, "total_steps": 4425, "loss": 0.6269, "learning_rate": 0.0001666115438614328, "epoch": 1.7062146892655368, "percentage": 34.12, "elapsed_time": "0:24:29", "remaining_time": "0:47:17"}
|
| 153 |
+
{"current_steps": 1520, "total_steps": 4425, "loss": 0.6397, "learning_rate": 0.00016602104076367624, "epoch": 1.7175141242937855, "percentage": 34.35, "elapsed_time": "0:24:39", "remaining_time": "0:47:06"}
|
| 154 |
+
{"current_steps": 1530, "total_steps": 4425, "loss": 0.6402, "learning_rate": 0.0001654264282760343, "epoch": 1.7288135593220337, "percentage": 34.58, "elapsed_time": "0:24:47", "remaining_time": "0:46:54"}
|
| 155 |
+
{"current_steps": 1540, "total_steps": 4425, "loss": 0.626, "learning_rate": 0.00016482774340935267, "epoch": 1.7401129943502824, "percentage": 34.8, "elapsed_time": "0:24:56", "remaining_time": "0:46:43"}
|
| 156 |
+
{"current_steps": 1550, "total_steps": 4425, "loss": 0.6542, "learning_rate": 0.00016422502342795648, "epoch": 1.7514124293785311, "percentage": 35.03, "elapsed_time": "0:25:06", "remaining_time": "0:46:33"}
|
| 157 |
+
{"current_steps": 1560, "total_steps": 4425, "loss": 0.6472, "learning_rate": 0.00016361830584733124, "epoch": 1.7627118644067796, "percentage": 35.25, "elapsed_time": "0:25:15", "remaining_time": "0:46:23"}
|
| 158 |
+
{"current_steps": 1570, "total_steps": 4425, "loss": 0.6304, "learning_rate": 0.00016300762843178754, "epoch": 1.774011299435028, "percentage": 35.48, "elapsed_time": "0:25:24", "remaining_time": "0:46:12"}
|
| 159 |
+
{"current_steps": 1580, "total_steps": 4425, "loss": 0.6161, "learning_rate": 0.00016239302919211052, "epoch": 1.7853107344632768, "percentage": 35.71, "elapsed_time": "0:25:33", "remaining_time": "0:46:00"}
|
| 160 |
+
{"current_steps": 1590, "total_steps": 4425, "loss": 0.6428, "learning_rate": 0.0001617745463831939, "epoch": 1.7966101694915255, "percentage": 35.93, "elapsed_time": "0:25:43", "remaining_time": "0:45:51"}
|
| 161 |
+
{"current_steps": 1600, "total_steps": 4425, "loss": 0.6661, "learning_rate": 0.00016115221850165892, "epoch": 1.807909604519774, "percentage": 36.16, "elapsed_time": "0:25:52", "remaining_time": "0:45:40"}
|
| 162 |
+
{"current_steps": 1610, "total_steps": 4425, "loss": 0.6293, "learning_rate": 0.0001605260842834581, "epoch": 1.8192090395480225, "percentage": 36.38, "elapsed_time": "0:26:02", "remaining_time": "0:45:31"}
|
| 163 |
+
{"current_steps": 1620, "total_steps": 4425, "loss": 0.6368, "learning_rate": 0.00015989618270146423, "epoch": 1.8305084745762712, "percentage": 36.61, "elapsed_time": "0:26:11", "remaining_time": "0:45:20"}
|
| 164 |
+
{"current_steps": 1630, "total_steps": 4425, "loss": 0.6297, "learning_rate": 0.00015926255296304454, "epoch": 1.84180790960452, "percentage": 36.84, "elapsed_time": "0:26:20", "remaining_time": "0:45:10"}
|
| 165 |
+
{"current_steps": 1640, "total_steps": 4425, "loss": 0.6817, "learning_rate": 0.00015862523450762032, "epoch": 1.8531073446327684, "percentage": 37.06, "elapsed_time": "0:26:30", "remaining_time": "0:45:00"}
|
| 166 |
+
{"current_steps": 1650, "total_steps": 4425, "loss": 0.6586, "learning_rate": 0.00015798426700421196, "epoch": 1.8644067796610169, "percentage": 37.29, "elapsed_time": "0:26:38", "remaining_time": "0:44:49"}
|
| 167 |
+
{"current_steps": 1660, "total_steps": 4425, "loss": 0.6466, "learning_rate": 0.0001573396903489699, "epoch": 1.8757062146892656, "percentage": 37.51, "elapsed_time": "0:26:48", "remaining_time": "0:44:39"}
|
| 168 |
+
{"current_steps": 1670, "total_steps": 4425, "loss": 0.6448, "learning_rate": 0.00015669154466269137, "epoch": 1.8870056497175143, "percentage": 37.74, "elapsed_time": "0:26:57", "remaining_time": "0:44:28"}
|
| 169 |
+
{"current_steps": 1680, "total_steps": 4425, "loss": 0.6385, "learning_rate": 0.00015603987028832303, "epoch": 1.8983050847457628, "percentage": 37.97, "elapsed_time": "0:27:05", "remaining_time": "0:44:16"}
|
| 170 |
+
{"current_steps": 1690, "total_steps": 4425, "loss": 0.6368, "learning_rate": 0.00015538470778844995, "epoch": 1.9096045197740112, "percentage": 38.19, "elapsed_time": "0:27:14", "remaining_time": "0:44:05"}
|
| 171 |
+
{"current_steps": 1700, "total_steps": 4425, "loss": 0.6341, "learning_rate": 0.00015472609794277083, "epoch": 1.92090395480226, "percentage": 38.42, "elapsed_time": "0:27:23", "remaining_time": "0:43:53"}
|
| 172 |
+
{"current_steps": 1710, "total_steps": 4425, "loss": 0.619, "learning_rate": 0.00015406408174555976, "epoch": 1.9322033898305084, "percentage": 38.64, "elapsed_time": "0:27:32", "remaining_time": "0:43:44"}
|
| 173 |
+
{"current_steps": 1720, "total_steps": 4425, "loss": 0.6591, "learning_rate": 0.00015339870040311448, "epoch": 1.943502824858757, "percentage": 38.87, "elapsed_time": "0:27:42", "remaining_time": "0:43:33"}
|
| 174 |
+
{"current_steps": 1730, "total_steps": 4425, "loss": 0.645, "learning_rate": 0.00015272999533119162, "epoch": 1.9548022598870056, "percentage": 39.1, "elapsed_time": "0:27:52", "remaining_time": "0:43:24"}
|
| 175 |
+
{"current_steps": 1740, "total_steps": 4425, "loss": 0.625, "learning_rate": 0.0001520580081524289, "epoch": 1.9661016949152543, "percentage": 39.32, "elapsed_time": "0:28:02", "remaining_time": "0:43:15"}
|
| 176 |
+
{"current_steps": 1750, "total_steps": 4425, "loss": 0.6481, "learning_rate": 0.00015138278069375423, "epoch": 1.9774011299435028, "percentage": 39.55, "elapsed_time": "0:28:10", "remaining_time": "0:43:04"}
|
| 177 |
+
{"current_steps": 1760, "total_steps": 4425, "loss": 0.6482, "learning_rate": 0.00015070435498378243, "epoch": 1.9887005649717513, "percentage": 39.77, "elapsed_time": "0:28:21", "remaining_time": "0:42:56"}
|
| 178 |
+
{"current_steps": 1770, "total_steps": 4425, "loss": 0.623, "learning_rate": 0.00015002277325019904, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:28:31", "remaining_time": "0:42:46"}
|
| 179 |
+
{"current_steps": 1780, "total_steps": 4425, "loss": 0.573, "learning_rate": 0.00014933807791713203, "epoch": 2.0112994350282487, "percentage": 40.23, "elapsed_time": "0:28:40", "remaining_time": "0:42:36"}
|
| 180 |
+
{"current_steps": 1790, "total_steps": 4425, "loss": 0.6054, "learning_rate": 0.00014865031160251116, "epoch": 2.022598870056497, "percentage": 40.45, "elapsed_time": "0:28:50", "remaining_time": "0:42:28"}
|
| 181 |
+
{"current_steps": 1800, "total_steps": 4425, "loss": 0.5724, "learning_rate": 0.0001479595171154152, "epoch": 2.0338983050847457, "percentage": 40.68, "elapsed_time": "0:29:00", "remaining_time": "0:42:18"}
|
| 182 |
+
{"current_steps": 1810, "total_steps": 4425, "loss": 0.5536, "learning_rate": 0.00014726573745340747, "epoch": 2.0451977401129944, "percentage": 40.9, "elapsed_time": "0:29:09", "remaining_time": "0:42:07"}
|
| 183 |
+
{"current_steps": 1820, "total_steps": 4425, "loss": 0.5591, "learning_rate": 0.00014656901579985934, "epoch": 2.056497175141243, "percentage": 41.13, "elapsed_time": "0:29:19", "remaining_time": "0:41:58"}
|
| 184 |
+
{"current_steps": 1830, "total_steps": 4425, "loss": 0.5467, "learning_rate": 0.00014586939552126255, "epoch": 2.0677966101694913, "percentage": 41.36, "elapsed_time": "0:29:27", "remaining_time": "0:41:46"}
|
| 185 |
+
{"current_steps": 1840, "total_steps": 4425, "loss": 0.5548, "learning_rate": 0.0001451669201645298, "epoch": 2.07909604519774, "percentage": 41.58, "elapsed_time": "0:29:37", "remaining_time": "0:41:37"}
|
| 186 |
+
{"current_steps": 1850, "total_steps": 4425, "loss": 0.5464, "learning_rate": 0.00014446163345428411, "epoch": 2.0903954802259888, "percentage": 41.81, "elapsed_time": "0:29:48", "remaining_time": "0:41:29"}
|
| 187 |
+
{"current_steps": 1860, "total_steps": 4425, "loss": 0.5658, "learning_rate": 0.00014375357929013763, "epoch": 2.1016949152542375, "percentage": 42.03, "elapsed_time": "0:29:58", "remaining_time": "0:41:20"}
|
| 188 |
+
{"current_steps": 1870, "total_steps": 4425, "loss": 0.5657, "learning_rate": 0.00014304280174395862, "epoch": 2.1129943502824857, "percentage": 42.26, "elapsed_time": "0:30:07", "remaining_time": "0:41:09"}
|
| 189 |
+
{"current_steps": 1880, "total_steps": 4425, "loss": 0.5488, "learning_rate": 0.00014232934505712877, "epoch": 2.1242937853107344, "percentage": 42.49, "elapsed_time": "0:30:16", "remaining_time": "0:40:59"}
|
| 190 |
+
{"current_steps": 1890, "total_steps": 4425, "loss": 0.5536, "learning_rate": 0.00014161325363778914, "epoch": 2.135593220338983, "percentage": 42.71, "elapsed_time": "0:30:26", "remaining_time": "0:40:50"}
|
| 191 |
+
{"current_steps": 1900, "total_steps": 4425, "loss": 0.5518, "learning_rate": 0.00014089457205807614, "epoch": 2.146892655367232, "percentage": 42.94, "elapsed_time": "0:30:35", "remaining_time": "0:40:39"}
|
| 192 |
+
{"current_steps": 1910, "total_steps": 4425, "loss": 0.5493, "learning_rate": 0.00014017334505134722, "epoch": 2.15819209039548, "percentage": 43.16, "elapsed_time": "0:30:44", "remaining_time": "0:40:29"}
|
| 193 |
+
{"current_steps": 1920, "total_steps": 4425, "loss": 0.5685, "learning_rate": 0.00013944961750939644, "epoch": 2.169491525423729, "percentage": 43.39, "elapsed_time": "0:30:54", "remaining_time": "0:40:19"}
|
| 194 |
+
{"current_steps": 1930, "total_steps": 4425, "loss": 0.5385, "learning_rate": 0.00013872343447966033, "epoch": 2.1807909604519775, "percentage": 43.62, "elapsed_time": "0:31:04", "remaining_time": "0:40:10"}
|
| 195 |
+
{"current_steps": 1940, "total_steps": 4425, "loss": 0.5601, "learning_rate": 0.00013799484116241382, "epoch": 2.1920903954802258, "percentage": 43.84, "elapsed_time": "0:31:13", "remaining_time": "0:39:59"}
|
| 196 |
+
{"current_steps": 1950, "total_steps": 4425, "loss": 0.5547, "learning_rate": 0.00013726388290795697, "epoch": 2.2033898305084745, "percentage": 44.07, "elapsed_time": "0:31:23", "remaining_time": "0:39:50"}
|
| 197 |
+
{"current_steps": 1960, "total_steps": 4425, "loss": 0.5627, "learning_rate": 0.00013653060521379216, "epoch": 2.214689265536723, "percentage": 44.29, "elapsed_time": "0:31:33", "remaining_time": "0:39:41"}
|
| 198 |
+
{"current_steps": 1970, "total_steps": 4425, "loss": 0.5797, "learning_rate": 0.0001357950537217921, "epoch": 2.225988700564972, "percentage": 44.52, "elapsed_time": "0:31:42", "remaining_time": "0:39:31"}
|
| 199 |
+
{"current_steps": 1980, "total_steps": 4425, "loss": 0.5644, "learning_rate": 0.00013505727421535892, "epoch": 2.23728813559322, "percentage": 44.75, "elapsed_time": "0:31:51", "remaining_time": "0:39:20"}
|
| 200 |
+
{"current_steps": 1990, "total_steps": 4425, "loss": 0.5446, "learning_rate": 0.00013431731261657462, "epoch": 2.248587570621469, "percentage": 44.97, "elapsed_time": "0:32:00", "remaining_time": "0:39:10"}
|
| 201 |
+
{"current_steps": 2000, "total_steps": 4425, "loss": 0.5528, "learning_rate": 0.0001335752149833424, "epoch": 2.2598870056497176, "percentage": 45.2, "elapsed_time": "0:32:11", "remaining_time": "0:39:01"}
|
| 202 |
+
{"current_steps": 2000, "total_steps": 4425, "eval_loss": 0.731483519077301, "epoch": 2.2598870056497176, "percentage": 45.2, "elapsed_time": "0:32:28", "remaining_time": "0:39:22"}
|
| 203 |
+
{"current_steps": 2010, "total_steps": 4425, "loss": 0.5476, "learning_rate": 0.00013283102750652007, "epoch": 2.2711864406779663, "percentage": 45.42, "elapsed_time": "0:32:38", "remaining_time": "0:39:13"}
|
| 204 |
+
{"current_steps": 2020, "total_steps": 4425, "loss": 0.5839, "learning_rate": 0.00013208479650704503, "epoch": 2.2824858757062145, "percentage": 45.65, "elapsed_time": "0:32:47", "remaining_time": "0:39:02"}
|
| 205 |
+
{"current_steps": 2030, "total_steps": 4425, "loss": 0.5791, "learning_rate": 0.00013133656843305078, "epoch": 2.2937853107344632, "percentage": 45.88, "elapsed_time": "0:32:55", "remaining_time": "0:38:51"}
|
| 206 |
+
{"current_steps": 2040, "total_steps": 4425, "loss": 0.5389, "learning_rate": 0.00013058638985697618, "epoch": 2.305084745762712, "percentage": 46.1, "elapsed_time": "0:33:06", "remaining_time": "0:38:42"}
|
| 207 |
+
{"current_steps": 2050, "total_steps": 4425, "loss": 0.5417, "learning_rate": 0.0001298343074726663, "epoch": 2.3163841807909606, "percentage": 46.33, "elapsed_time": "0:33:15", "remaining_time": "0:38:32"}
|
| 208 |
+
{"current_steps": 2060, "total_steps": 4425, "loss": 0.544, "learning_rate": 0.00012908036809246623, "epoch": 2.327683615819209, "percentage": 46.55, "elapsed_time": "0:33:25", "remaining_time": "0:38:22"}
|
| 209 |
+
{"current_steps": 2070, "total_steps": 4425, "loss": 0.5429, "learning_rate": 0.0001283246186443073, "epoch": 2.3389830508474576, "percentage": 46.78, "elapsed_time": "0:33:34", "remaining_time": "0:38:11"}
|
| 210 |
+
{"current_steps": 2080, "total_steps": 4425, "loss": 0.5466, "learning_rate": 0.00012756710616878593, "epoch": 2.3502824858757063, "percentage": 47.01, "elapsed_time": "0:33:44", "remaining_time": "0:38:02"}
|
| 211 |
+
{"current_steps": 2090, "total_steps": 4425, "loss": 0.5894, "learning_rate": 0.00012680787781623582, "epoch": 2.361581920903955, "percentage": 47.23, "elapsed_time": "0:33:54", "remaining_time": "0:37:52"}
|
| 212 |
+
{"current_steps": 2100, "total_steps": 4425, "loss": 0.5504, "learning_rate": 0.00012604698084379322, "epoch": 2.3728813559322033, "percentage": 47.46, "elapsed_time": "0:34:02", "remaining_time": "0:37:41"}
|
| 213 |
+
{"current_steps": 2110, "total_steps": 4425, "loss": 0.5522, "learning_rate": 0.00012528446261245515, "epoch": 2.384180790960452, "percentage": 47.68, "elapsed_time": "0:34:11", "remaining_time": "0:37:31"}
|
| 214 |
+
{"current_steps": 2120, "total_steps": 4425, "loss": 0.5674, "learning_rate": 0.00012452037058413194, "epoch": 2.3954802259887007, "percentage": 47.91, "elapsed_time": "0:34:20", "remaining_time": "0:37:20"}
|
| 215 |
+
{"current_steps": 2130, "total_steps": 4425, "loss": 0.5814, "learning_rate": 0.00012375475231869249, "epoch": 2.406779661016949, "percentage": 48.14, "elapsed_time": "0:34:29", "remaining_time": "0:37:09"}
|
| 216 |
+
{"current_steps": 2140, "total_steps": 4425, "loss": 0.5663, "learning_rate": 0.00012298765547100445, "epoch": 2.4180790960451977, "percentage": 48.36, "elapsed_time": "0:34:38", "remaining_time": "0:36:59"}
|
| 217 |
+
{"current_steps": 2150, "total_steps": 4425, "loss": 0.5476, "learning_rate": 0.0001222191277879678, "epoch": 2.4293785310734464, "percentage": 48.59, "elapsed_time": "0:34:48", "remaining_time": "0:36:50"}
|
| 218 |
+
{"current_steps": 2160, "total_steps": 4425, "loss": 0.5818, "learning_rate": 0.00012144921710554278, "epoch": 2.440677966101695, "percentage": 48.81, "elapsed_time": "0:34:58", "remaining_time": "0:36:40"}
|
| 219 |
+
{"current_steps": 2170, "total_steps": 4425, "loss": 0.5878, "learning_rate": 0.00012067797134577275, "epoch": 2.4519774011299433, "percentage": 49.04, "elapsed_time": "0:35:08", "remaining_time": "0:36:31"}
|
| 220 |
+
{"current_steps": 2180, "total_steps": 4425, "loss": 0.5602, "learning_rate": 0.00011990543851380094, "epoch": 2.463276836158192, "percentage": 49.27, "elapsed_time": "0:35:18", "remaining_time": "0:36:21"}
|
| 221 |
+
{"current_steps": 2190, "total_steps": 4425, "loss": 0.5692, "learning_rate": 0.00011913166669488278, "epoch": 2.4745762711864407, "percentage": 49.49, "elapsed_time": "0:35:26", "remaining_time": "0:36:10"}
|
| 222 |
+
{"current_steps": 2200, "total_steps": 4425, "loss": 0.5698, "learning_rate": 0.00011835670405139272, "epoch": 2.4858757062146895, "percentage": 49.72, "elapsed_time": "0:35:37", "remaining_time": "0:36:01"}
|
| 223 |
+
{"current_steps": 2210, "total_steps": 4425, "loss": 0.567, "learning_rate": 0.00011758059881982639, "epoch": 2.4971751412429377, "percentage": 49.94, "elapsed_time": "0:35:46", "remaining_time": "0:35:51"}
|
| 224 |
+
{"current_steps": 2220, "total_steps": 4425, "loss": 0.5528, "learning_rate": 0.00011680339930779843, "epoch": 2.5084745762711864, "percentage": 50.17, "elapsed_time": "0:35:55", "remaining_time": "0:35:40"}
|
| 225 |
+
{"current_steps": 2230, "total_steps": 4425, "loss": 0.57, "learning_rate": 0.00011602515389103529, "epoch": 2.519774011299435, "percentage": 50.4, "elapsed_time": "0:36:04", "remaining_time": "0:35:30"}
|
| 226 |
+
{"current_steps": 2240, "total_steps": 4425, "loss": 0.5731, "learning_rate": 0.00011524591101036446, "epoch": 2.5310734463276834, "percentage": 50.62, "elapsed_time": "0:36:13", "remaining_time": "0:35:19"}
|
| 227 |
+
{"current_steps": 2250, "total_steps": 4425, "loss": 0.5603, "learning_rate": 0.00011446571916869917, "epoch": 2.542372881355932, "percentage": 50.85, "elapsed_time": "0:36:22", "remaining_time": "0:35:09"}
|
| 228 |
+
{"current_steps": 2260, "total_steps": 4425, "loss": 0.5508, "learning_rate": 0.00011368462692801944, "epoch": 2.553672316384181, "percentage": 51.07, "elapsed_time": "0:36:30", "remaining_time": "0:34:58"}
|
| 229 |
+
{"current_steps": 2270, "total_steps": 4425, "loss": 0.5695, "learning_rate": 0.00011290268290634943, "epoch": 2.5649717514124295, "percentage": 51.3, "elapsed_time": "0:36:39", "remaining_time": "0:34:48"}
|
| 230 |
+
{"current_steps": 2280, "total_steps": 4425, "loss": 0.5812, "learning_rate": 0.00011211993577473121, "epoch": 2.576271186440678, "percentage": 51.53, "elapsed_time": "0:36:50", "remaining_time": "0:34:39"}
|
| 231 |
+
{"current_steps": 2290, "total_steps": 4425, "loss": 0.5775, "learning_rate": 0.00011133643425419531, "epoch": 2.5875706214689265, "percentage": 51.75, "elapsed_time": "0:36:59", "remaining_time": "0:34:29"}
|
| 232 |
+
{"current_steps": 2300, "total_steps": 4425, "loss": 0.5932, "learning_rate": 0.0001105522271127283, "epoch": 2.598870056497175, "percentage": 51.98, "elapsed_time": "0:37:09", "remaining_time": "0:34:19"}
|
| 233 |
+
{"current_steps": 2310, "total_steps": 4425, "loss": 0.5803, "learning_rate": 0.00010976736316223698, "epoch": 2.610169491525424, "percentage": 52.2, "elapsed_time": "0:37:18", "remaining_time": "0:34:09"}
|
| 234 |
+
{"current_steps": 2320, "total_steps": 4425, "loss": 0.5939, "learning_rate": 0.00010898189125551052, "epoch": 2.621468926553672, "percentage": 52.43, "elapsed_time": "0:37:26", "remaining_time": "0:33:58"}
|
| 235 |
+
{"current_steps": 2330, "total_steps": 4425, "loss": 0.5762, "learning_rate": 0.0001081958602831794, "epoch": 2.632768361581921, "percentage": 52.66, "elapsed_time": "0:37:36", "remaining_time": "0:33:48"}
|
| 236 |
+
{"current_steps": 2340, "total_steps": 4425, "loss": 0.5455, "learning_rate": 0.00010740931917067231, "epoch": 2.6440677966101696, "percentage": 52.88, "elapsed_time": "0:37:44", "remaining_time": "0:33:37"}
|
| 237 |
+
{"current_steps": 2350, "total_steps": 4425, "loss": 0.5697, "learning_rate": 0.00010662231687517112, "epoch": 2.655367231638418, "percentage": 53.11, "elapsed_time": "0:37:55", "remaining_time": "0:33:28"}
|
| 238 |
+
{"current_steps": 2360, "total_steps": 4425, "loss": 0.5544, "learning_rate": 0.00010583490238256322, "epoch": 2.6666666666666665, "percentage": 53.33, "elapsed_time": "0:38:05", "remaining_time": "0:33:19"}
|
| 239 |
+
{"current_steps": 2370, "total_steps": 4425, "loss": 0.5603, "learning_rate": 0.00010504712470439266, "epoch": 2.6779661016949152, "percentage": 53.56, "elapsed_time": "0:38:16", "remaining_time": "0:33:10"}
|
| 240 |
+
{"current_steps": 2380, "total_steps": 4425, "loss": 0.5555, "learning_rate": 0.00010425903287480969, "epoch": 2.689265536723164, "percentage": 53.79, "elapsed_time": "0:38:25", "remaining_time": "0:33:00"}
|
| 241 |
+
{"current_steps": 2390, "total_steps": 4425, "loss": 0.5374, "learning_rate": 0.0001034706759475182, "epoch": 2.7005649717514126, "percentage": 54.01, "elapsed_time": "0:38:34", "remaining_time": "0:32:50"}
|
| 242 |
+
{"current_steps": 2400, "total_steps": 4425, "loss": 0.5499, "learning_rate": 0.00010268210299272294, "epoch": 2.711864406779661, "percentage": 54.24, "elapsed_time": "0:38:43", "remaining_time": "0:32:40"}
|
| 243 |
+
{"current_steps": 2410, "total_steps": 4425, "loss": 0.5692, "learning_rate": 0.00010189336309407492, "epoch": 2.7231638418079096, "percentage": 54.46, "elapsed_time": "0:38:52", "remaining_time": "0:32:30"}
|
| 244 |
+
{"current_steps": 2420, "total_steps": 4425, "loss": 0.5858, "learning_rate": 0.00010110450534561629, "epoch": 2.7344632768361583, "percentage": 54.69, "elapsed_time": "0:39:04", "remaining_time": "0:32:22"}
|
| 245 |
+
{"current_steps": 2430, "total_steps": 4425, "loss": 0.5577, "learning_rate": 0.00010031557884872471, "epoch": 2.7457627118644066, "percentage": 54.92, "elapsed_time": "0:39:14", "remaining_time": "0:32:13"}
|
| 246 |
+
{"current_steps": 2440, "total_steps": 4425, "loss": 0.543, "learning_rate": 9.952663270905691e-05, "epoch": 2.7570621468926553, "percentage": 55.14, "elapsed_time": "0:39:25", "remaining_time": "0:32:04"}
|
| 247 |
+
{"current_steps": 2450, "total_steps": 4425, "loss": 0.5673, "learning_rate": 9.873771603349229e-05, "epoch": 2.768361581920904, "percentage": 55.37, "elapsed_time": "0:39:35", "remaining_time": "0:31:55"}
|
| 248 |
+
{"current_steps": 2460, "total_steps": 4425, "loss": 0.5759, "learning_rate": 9.79488779270763e-05, "epoch": 2.7796610169491527, "percentage": 55.59, "elapsed_time": "0:39:45", "remaining_time": "0:31:45"}
|
| 249 |
+
{"current_steps": 2470, "total_steps": 4425, "loss": 0.5804, "learning_rate": 9.716016748996397e-05, "epoch": 2.7909604519774014, "percentage": 55.82, "elapsed_time": "0:39:53", "remaining_time": "0:31:34"}
|
| 250 |
+
{"current_steps": 2480, "total_steps": 4425, "loss": 0.573, "learning_rate": 9.637163381436368e-05, "epoch": 2.8022598870056497, "percentage": 56.05, "elapsed_time": "0:40:02", "remaining_time": "0:31:24"}
|
| 251 |
+
{"current_steps": 2490, "total_steps": 4425, "loss": 0.5702, "learning_rate": 9.558332598148156e-05, "epoch": 2.8135593220338984, "percentage": 56.27, "elapsed_time": "0:40:12", "remaining_time": "0:31:14"}
|
| 252 |
+
{"current_steps": 2500, "total_steps": 4425, "loss": 0.5556, "learning_rate": 9.479529305846652e-05, "epoch": 2.824858757062147, "percentage": 56.5, "elapsed_time": "0:40:22", "remaining_time": "0:31:05"}
|
| 253 |
+
{"current_steps": 2510, "total_steps": 4425, "loss": 0.5417, "learning_rate": 9.400758409535597e-05, "epoch": 2.8361581920903953, "percentage": 56.72, "elapsed_time": "0:40:32", "remaining_time": "0:30:56"}
|
| 254 |
+
{"current_steps": 2520, "total_steps": 4425, "loss": 0.5531, "learning_rate": 9.322024812202295e-05, "epoch": 2.847457627118644, "percentage": 56.95, "elapsed_time": "0:40:41", "remaining_time": "0:30:45"}
|
| 255 |
+
{"current_steps": 2530, "total_steps": 4425, "loss": 0.5692, "learning_rate": 9.243333414512428e-05, "epoch": 2.8587570621468927, "percentage": 57.18, "elapsed_time": "0:40:52", "remaining_time": "0:30:37"}
|
| 256 |
+
{"current_steps": 2540, "total_steps": 4425, "loss": 0.556, "learning_rate": 9.164689114505007e-05, "epoch": 2.870056497175141, "percentage": 57.4, "elapsed_time": "0:41:02", "remaining_time": "0:30:27"}
|
| 257 |
+
{"current_steps": 2550, "total_steps": 4425, "loss": 0.547, "learning_rate": 9.086096807287525e-05, "epoch": 2.8813559322033897, "percentage": 57.63, "elapsed_time": "0:41:11", "remaining_time": "0:30:17"}
|
| 258 |
+
{"current_steps": 2560, "total_steps": 4425, "loss": 0.5843, "learning_rate": 9.007561384731249e-05, "epoch": 2.8926553672316384, "percentage": 57.85, "elapsed_time": "0:41:20", "remaining_time": "0:30:07"}
|
| 259 |
+
{"current_steps": 2570, "total_steps": 4425, "loss": 0.5642, "learning_rate": 8.929087735166738e-05, "epoch": 2.903954802259887, "percentage": 58.08, "elapsed_time": "0:41:29", "remaining_time": "0:29:57"}
|
| 260 |
+
{"current_steps": 2580, "total_steps": 4425, "loss": 0.5191, "learning_rate": 8.850680743079576e-05, "epoch": 2.915254237288136, "percentage": 58.31, "elapsed_time": "0:41:39", "remaining_time": "0:29:47"}
|
| 261 |
+
{"current_steps": 2590, "total_steps": 4425, "loss": 0.5823, "learning_rate": 8.772345288806338e-05, "epoch": 2.926553672316384, "percentage": 58.53, "elapsed_time": "0:41:47", "remaining_time": "0:29:36"}
|
| 262 |
+
{"current_steps": 2600, "total_steps": 4425, "loss": 0.5673, "learning_rate": 8.694086248230836e-05, "epoch": 2.937853107344633, "percentage": 58.76, "elapsed_time": "0:41:56", "remaining_time": "0:29:26"}
|
| 263 |
+
{"current_steps": 2610, "total_steps": 4425, "loss": 0.5555, "learning_rate": 8.615908492480598e-05, "epoch": 2.9491525423728815, "percentage": 58.98, "elapsed_time": "0:42:04", "remaining_time": "0:29:15"}
|
| 264 |
+
{"current_steps": 2620, "total_steps": 4425, "loss": 0.5883, "learning_rate": 8.537816887623706e-05, "epoch": 2.9604519774011298, "percentage": 59.21, "elapsed_time": "0:42:13", "remaining_time": "0:29:05"}
|
| 265 |
+
{"current_steps": 2630, "total_steps": 4425, "loss": 0.6002, "learning_rate": 8.459816294365892e-05, "epoch": 2.9717514124293785, "percentage": 59.44, "elapsed_time": "0:42:22", "remaining_time": "0:28:55"}
|
| 266 |
+
{"current_steps": 2640, "total_steps": 4425, "loss": 0.5751, "learning_rate": 8.381911567747986e-05, "epoch": 2.983050847457627, "percentage": 59.66, "elapsed_time": "0:42:32", "remaining_time": "0:28:45"}
|
| 267 |
+
{"current_steps": 2650, "total_steps": 4425, "loss": 0.5583, "learning_rate": 8.304107556843739e-05, "epoch": 2.994350282485876, "percentage": 59.89, "elapsed_time": "0:42:41", "remaining_time": "0:28:35"}
|
| 268 |
+
{"current_steps": 2660, "total_steps": 4425, "loss": 0.5075, "learning_rate": 8.22640910445799e-05, "epoch": 3.005649717514124, "percentage": 60.11, "elapsed_time": "0:42:52", "remaining_time": "0:28:26"}
|
| 269 |
+
{"current_steps": 2670, "total_steps": 4425, "loss": 0.4768, "learning_rate": 8.14882104682522e-05, "epoch": 3.016949152542373, "percentage": 60.34, "elapsed_time": "0:43:01", "remaining_time": "0:28:16"}
|
| 270 |
+
{"current_steps": 2680, "total_steps": 4425, "loss": 0.4959, "learning_rate": 8.07134821330855e-05, "epoch": 3.0282485875706215, "percentage": 60.56, "elapsed_time": "0:43:11", "remaining_time": "0:28:07"}
|
| 271 |
+
{"current_steps": 2690, "total_steps": 4425, "loss": 0.4765, "learning_rate": 7.993995426099132e-05, "epoch": 3.0395480225988702, "percentage": 60.79, "elapsed_time": "0:43:22", "remaining_time": "0:27:58"}
|
| 272 |
+
{"current_steps": 2700, "total_steps": 4425, "loss": 0.4615, "learning_rate": 7.916767499915998e-05, "epoch": 3.0508474576271185, "percentage": 61.02, "elapsed_time": "0:43:30", "remaining_time": "0:27:47"}
|
| 273 |
+
{"current_steps": 2710, "total_steps": 4425, "loss": 0.495, "learning_rate": 7.839669241706368e-05, "epoch": 3.062146892655367, "percentage": 61.24, "elapsed_time": "0:43:39", "remaining_time": "0:27:37"}
|
| 274 |
+
{"current_steps": 2720, "total_steps": 4425, "loss": 0.486, "learning_rate": 7.762705450346462e-05, "epoch": 3.073446327683616, "percentage": 61.47, "elapsed_time": "0:43:47", "remaining_time": "0:27:27"}
|
| 275 |
+
{"current_steps": 2730, "total_steps": 4425, "loss": 0.4816, "learning_rate": 7.685880916342795e-05, "epoch": 3.084745762711864, "percentage": 61.69, "elapsed_time": "0:43:56", "remaining_time": "0:27:17"}
|
| 276 |
+
{"current_steps": 2740, "total_steps": 4425, "loss": 0.4706, "learning_rate": 7.609200421533991e-05, "epoch": 3.096045197740113, "percentage": 61.92, "elapsed_time": "0:44:05", "remaining_time": "0:27:07"}
|
| 277 |
+
{"current_steps": 2750, "total_steps": 4425, "loss": 0.479, "learning_rate": 7.532668738793159e-05, "epoch": 3.1073446327683616, "percentage": 62.15, "elapsed_time": "0:44:16", "remaining_time": "0:26:57"}
|
| 278 |
+
{"current_steps": 2760, "total_steps": 4425, "loss": 0.5023, "learning_rate": 7.456290631730795e-05, "epoch": 3.1186440677966103, "percentage": 62.37, "elapsed_time": "0:44:26", "remaining_time": "0:26:48"}
|
| 279 |
+
{"current_steps": 2770, "total_steps": 4425, "loss": 0.477, "learning_rate": 7.380070854398292e-05, "epoch": 3.1299435028248586, "percentage": 62.6, "elapsed_time": "0:44:34", "remaining_time": "0:26:38"}
|
| 280 |
+
{"current_steps": 2780, "total_steps": 4425, "loss": 0.511, "learning_rate": 7.304014150992016e-05, "epoch": 3.1412429378531073, "percentage": 62.82, "elapsed_time": "0:44:43", "remaining_time": "0:26:28"}
|
| 281 |
+
{"current_steps": 2790, "total_steps": 4425, "loss": 0.4797, "learning_rate": 7.228125255558026e-05, "epoch": 3.152542372881356, "percentage": 63.05, "elapsed_time": "0:44:52", "remaining_time": "0:26:17"}
|
| 282 |
+
{"current_steps": 2800, "total_steps": 4425, "loss": 0.4908, "learning_rate": 7.152408891697406e-05, "epoch": 3.1638418079096047, "percentage": 63.28, "elapsed_time": "0:45:01", "remaining_time": "0:26:08"}
|
| 283 |
+
{"current_steps": 2810, "total_steps": 4425, "loss": 0.4944, "learning_rate": 7.076869772272231e-05, "epoch": 3.175141242937853, "percentage": 63.5, "elapsed_time": "0:45:11", "remaining_time": "0:25:58"}
|
| 284 |
+
{"current_steps": 2820, "total_steps": 4425, "loss": 0.4764, "learning_rate": 7.001512599112254e-05, "epoch": 3.1864406779661016, "percentage": 63.73, "elapsed_time": "0:45:22", "remaining_time": "0:25:49"}
|
| 285 |
+
{"current_steps": 2830, "total_steps": 4425, "loss": 0.4917, "learning_rate": 6.926342062722223e-05, "epoch": 3.1977401129943503, "percentage": 63.95, "elapsed_time": "0:45:32", "remaining_time": "0:25:40"}
|
| 286 |
+
{"current_steps": 2840, "total_steps": 4425, "loss": 0.5105, "learning_rate": 6.851362841989926e-05, "epoch": 3.209039548022599, "percentage": 64.18, "elapsed_time": "0:45:42", "remaining_time": "0:25:30"}
|
| 287 |
+
{"current_steps": 2850, "total_steps": 4425, "loss": 0.4888, "learning_rate": 6.776579603894983e-05, "epoch": 3.2203389830508473, "percentage": 64.41, "elapsed_time": "0:45:51", "remaining_time": "0:25:20"}
|
| 288 |
+
{"current_steps": 2860, "total_steps": 4425, "loss": 0.4597, "learning_rate": 6.701997003218334e-05, "epoch": 3.231638418079096, "percentage": 64.63, "elapsed_time": "0:46:01", "remaining_time": "0:25:10"}
|
| 289 |
+
{"current_steps": 2870, "total_steps": 4425, "loss": 0.5198, "learning_rate": 6.627619682252514e-05, "epoch": 3.2429378531073447, "percentage": 64.86, "elapsed_time": "0:46:10", "remaining_time": "0:25:01"}
|
| 290 |
+
{"current_steps": 2880, "total_steps": 4425, "loss": 0.4881, "learning_rate": 6.553452270512708e-05, "epoch": 3.2542372881355934, "percentage": 65.08, "elapsed_time": "0:46:19", "remaining_time": "0:24:51"}
|
| 291 |
+
{"current_steps": 2890, "total_steps": 4425, "loss": 0.4839, "learning_rate": 6.47949938444858e-05, "epoch": 3.2655367231638417, "percentage": 65.31, "elapsed_time": "0:46:29", "remaining_time": "0:24:41"}
|
| 292 |
+
{"current_steps": 2900, "total_steps": 4425, "loss": 0.4953, "learning_rate": 6.405765627156934e-05, "epoch": 3.2768361581920904, "percentage": 65.54, "elapsed_time": "0:46:37", "remaining_time": "0:24:31"}
|
| 293 |
+
{"current_steps": 2910, "total_steps": 4425, "loss": 0.4936, "learning_rate": 6.332255588095211e-05, "epoch": 3.288135593220339, "percentage": 65.76, "elapsed_time": "0:46:45", "remaining_time": "0:24:20"}
|
| 294 |
+
{"current_steps": 2920, "total_steps": 4425, "loss": 0.4927, "learning_rate": 6.258973842795803e-05, "epoch": 3.2994350282485874, "percentage": 65.99, "elapsed_time": "0:46:56", "remaining_time": "0:24:11"}
|
| 295 |
+
{"current_steps": 2930, "total_steps": 4425, "loss": 0.4908, "learning_rate": 6.185924952581286e-05, "epoch": 3.310734463276836, "percentage": 66.21, "elapsed_time": "0:47:06", "remaining_time": "0:24:02"}
|
| 296 |
+
{"current_steps": 2940, "total_steps": 4425, "loss": 0.4938, "learning_rate": 6.11311346428046e-05, "epoch": 3.3220338983050848, "percentage": 66.44, "elapsed_time": "0:47:15", "remaining_time": "0:23:51"}
|
| 297 |
+
{"current_steps": 2950, "total_steps": 4425, "loss": 0.4795, "learning_rate": 6.040543909945393e-05, "epoch": 3.3333333333333335, "percentage": 66.67, "elapsed_time": "0:47:24", "remaining_time": "0:23:42"}
|
| 298 |
+
{"current_steps": 2960, "total_steps": 4425, "loss": 0.4821, "learning_rate": 5.968220806569289e-05, "epoch": 3.3446327683615817, "percentage": 66.89, "elapsed_time": "0:47:34", "remaining_time": "0:23:32"}
|
| 299 |
+
{"current_steps": 2970, "total_steps": 4425, "loss": 0.4765, "learning_rate": 5.89614865580534e-05, "epoch": 3.3559322033898304, "percentage": 67.12, "elapsed_time": "0:47:43", "remaining_time": "0:23:22"}
|
| 300 |
+
{"current_steps": 2980, "total_steps": 4425, "loss": 0.4622, "learning_rate": 5.8243319436865554e-05, "epoch": 3.367231638418079, "percentage": 67.34, "elapsed_time": "0:47:53", "remaining_time": "0:23:13"}
|
| 301 |
+
{"current_steps": 2990, "total_steps": 4425, "loss": 0.4966, "learning_rate": 5.7527751403464935e-05, "epoch": 3.378531073446328, "percentage": 67.57, "elapsed_time": "0:48:02", "remaining_time": "0:23:03"}
|
| 302 |
+
{"current_steps": 3000, "total_steps": 4425, "loss": 0.4847, "learning_rate": 5.681482699741052e-05, "epoch": 3.389830508474576, "percentage": 67.8, "elapsed_time": "0:48:11", "remaining_time": "0:22:53"}
|
| 303 |
+
{"current_steps": 3000, "total_steps": 4425, "eval_loss": 0.7709711194038391, "epoch": 3.389830508474576, "percentage": 67.8, "elapsed_time": "0:48:28", "remaining_time": "0:23:01"}
|
| 304 |
+
{"current_steps": 3010, "total_steps": 4425, "loss": 0.4904, "learning_rate": 5.610459059371229e-05, "epoch": 3.401129943502825, "percentage": 68.02, "elapsed_time": "0:48:38", "remaining_time": "0:22:51"}
|
| 305 |
+
{"current_steps": 3020, "total_steps": 4425, "loss": 0.486, "learning_rate": 5.53970864000693e-05, "epoch": 3.4124293785310735, "percentage": 68.25, "elapsed_time": "0:48:48", "remaining_time": "0:22:42"}
|
| 306 |
+
{"current_steps": 3030, "total_steps": 4425, "loss": 0.485, "learning_rate": 5.4692358454117596e-05, "epoch": 3.423728813559322, "percentage": 68.47, "elapsed_time": "0:48:58", "remaining_time": "0:22:32"}
|
| 307 |
+
{"current_steps": 3040, "total_steps": 4425, "loss": 0.5055, "learning_rate": 5.399045062068977e-05, "epoch": 3.4350282485875705, "percentage": 68.7, "elapsed_time": "0:49:08", "remaining_time": "0:22:23"}
|
| 308 |
+
{"current_steps": 3050, "total_steps": 4425, "loss": 0.5047, "learning_rate": 5.329140658908423e-05, "epoch": 3.446327683615819, "percentage": 68.93, "elapsed_time": "0:49:18", "remaining_time": "0:22:13"}
|
| 309 |
+
{"current_steps": 3060, "total_steps": 4425, "loss": 0.5181, "learning_rate": 5.259526987034593e-05, "epoch": 3.457627118644068, "percentage": 69.15, "elapsed_time": "0:49:28", "remaining_time": "0:22:03"}
|
| 310 |
+
{"current_steps": 3070, "total_steps": 4425, "loss": 0.4901, "learning_rate": 5.190208379455802e-05, "epoch": 3.4689265536723166, "percentage": 69.38, "elapsed_time": "0:49:38", "remaining_time": "0:21:54"}
|
| 311 |
+
{"current_steps": 3080, "total_steps": 4425, "loss": 0.4919, "learning_rate": 5.121189150814507e-05, "epoch": 3.480225988700565, "percentage": 69.6, "elapsed_time": "0:49:48", "remaining_time": "0:21:44"}
|
| 312 |
+
{"current_steps": 3090, "total_steps": 4425, "loss": 0.4954, "learning_rate": 5.052473597118715e-05, "epoch": 3.4915254237288136, "percentage": 69.83, "elapsed_time": "0:49:57", "remaining_time": "0:21:35"}
|
| 313 |
+
{"current_steps": 3100, "total_steps": 4425, "loss": 0.4966, "learning_rate": 4.984065995474601e-05, "epoch": 3.5028248587570623, "percentage": 70.06, "elapsed_time": "0:50:06", "remaining_time": "0:21:24"}
|
| 314 |
+
{"current_steps": 3110, "total_steps": 4425, "loss": 0.4907, "learning_rate": 4.915970603820293e-05, "epoch": 3.5141242937853105, "percentage": 70.28, "elapsed_time": "0:50:14", "remaining_time": "0:21:14"}
|
| 315 |
+
{"current_steps": 3120, "total_steps": 4425, "loss": 0.4957, "learning_rate": 4.84819166066082e-05, "epoch": 3.5254237288135593, "percentage": 70.51, "elapsed_time": "0:50:24", "remaining_time": "0:21:04"}
|
| 316 |
+
{"current_steps": 3130, "total_steps": 4425, "loss": 0.5131, "learning_rate": 4.780733384804312e-05, "epoch": 3.536723163841808, "percentage": 70.73, "elapsed_time": "0:50:32", "remaining_time": "0:20:54"}
|
| 317 |
+
{"current_steps": 3140, "total_steps": 4425, "loss": 0.5214, "learning_rate": 4.713599975099399e-05, "epoch": 3.548022598870056, "percentage": 70.96, "elapsed_time": "0:50:41", "remaining_time": "0:20:44"}
|
| 318 |
+
{"current_steps": 3150, "total_steps": 4425, "loss": 0.498, "learning_rate": 4.646795610173864e-05, "epoch": 3.559322033898305, "percentage": 71.19, "elapsed_time": "0:50:50", "remaining_time": "0:20:34"}
|
| 319 |
+
{"current_steps": 3160, "total_steps": 4425, "loss": 0.4889, "learning_rate": 4.5803244481745275e-05, "epoch": 3.5706214689265536, "percentage": 71.41, "elapsed_time": "0:50:59", "remaining_time": "0:20:24"}
|
| 320 |
+
{"current_steps": 3170, "total_steps": 4425, "loss": 0.4889, "learning_rate": 4.514190626508465e-05, "epoch": 3.5819209039548023, "percentage": 71.64, "elapsed_time": "0:51:09", "remaining_time": "0:20:15"}
|
| 321 |
+
{"current_steps": 3180, "total_steps": 4425, "loss": 0.4688, "learning_rate": 4.448398261585459e-05, "epoch": 3.593220338983051, "percentage": 71.86, "elapsed_time": "0:51:19", "remaining_time": "0:20:05"}
|
| 322 |
+
{"current_steps": 3190, "total_steps": 4425, "loss": 0.4719, "learning_rate": 4.3829514485617754e-05, "epoch": 3.6045197740112993, "percentage": 72.09, "elapsed_time": "0:51:28", "remaining_time": "0:19:55"}
|
| 323 |
+
{"current_steps": 3200, "total_steps": 4425, "loss": 0.4816, "learning_rate": 4.31785426108527e-05, "epoch": 3.615819209039548, "percentage": 72.32, "elapsed_time": "0:51:38", "remaining_time": "0:19:46"}
|
| 324 |
+
{"current_steps": 3210, "total_steps": 4425, "loss": 0.4894, "learning_rate": 4.253110751041846e-05, "epoch": 3.6271186440677967, "percentage": 72.54, "elapsed_time": "0:51:48", "remaining_time": "0:19:36"}
|
| 325 |
+
{"current_steps": 3220, "total_steps": 4425, "loss": 0.4978, "learning_rate": 4.1887249483032195e-05, "epoch": 3.638418079096045, "percentage": 72.77, "elapsed_time": "0:51:57", "remaining_time": "0:19:26"}
|
| 326 |
+
{"current_steps": 3230, "total_steps": 4425, "loss": 0.4834, "learning_rate": 4.1247008604761096e-05, "epoch": 3.6497175141242937, "percentage": 72.99, "elapsed_time": "0:52:07", "remaining_time": "0:19:17"}
|
| 327 |
+
{"current_steps": 3240, "total_steps": 4425, "loss": 0.5177, "learning_rate": 4.061042472652786e-05, "epoch": 3.6610169491525424, "percentage": 73.22, "elapsed_time": "0:52:15", "remaining_time": "0:19:06"}
|
| 328 |
+
{"current_steps": 3250, "total_steps": 4425, "loss": 0.5206, "learning_rate": 3.997753747163014e-05, "epoch": 3.672316384180791, "percentage": 73.45, "elapsed_time": "0:52:25", "remaining_time": "0:18:57"}
|
| 329 |
+
{"current_steps": 3260, "total_steps": 4425, "loss": 0.4996, "learning_rate": 3.934838623327427e-05, "epoch": 3.68361581920904, "percentage": 73.67, "elapsed_time": "0:52:35", "remaining_time": "0:18:47"}
|
| 330 |
+
{"current_steps": 3270, "total_steps": 4425, "loss": 0.4741, "learning_rate": 3.872301017212337e-05, "epoch": 3.694915254237288, "percentage": 73.9, "elapsed_time": "0:52:45", "remaining_time": "0:18:38"}
|
| 331 |
+
{"current_steps": 3280, "total_steps": 4425, "loss": 0.4757, "learning_rate": 3.8101448213859846e-05, "epoch": 3.7062146892655368, "percentage": 74.12, "elapsed_time": "0:52:55", "remaining_time": "0:18:28"}
|
| 332 |
+
{"current_steps": 3290, "total_steps": 4425, "loss": 0.4887, "learning_rate": 3.7483739046762326e-05, "epoch": 3.7175141242937855, "percentage": 74.35, "elapsed_time": "0:53:05", "remaining_time": "0:18:18"}
|
| 333 |
+
{"current_steps": 3300, "total_steps": 4425, "loss": 0.4603, "learning_rate": 3.6869921119297714e-05, "epoch": 3.7288135593220337, "percentage": 74.58, "elapsed_time": "0:53:14", "remaining_time": "0:18:09"}
|
| 334 |
+
{"current_steps": 3310, "total_steps": 4425, "loss": 0.5009, "learning_rate": 3.626003263772813e-05, "epoch": 3.7401129943502824, "percentage": 74.8, "elapsed_time": "0:53:25", "remaining_time": "0:17:59"}
|
| 335 |
+
{"current_steps": 3320, "total_steps": 4425, "loss": 0.4982, "learning_rate": 3.565411156373252e-05, "epoch": 3.751412429378531, "percentage": 75.03, "elapsed_time": "0:53:35", "remaining_time": "0:17:50"}
|
| 336 |
+
{"current_steps": 3330, "total_steps": 4425, "loss": 0.4716, "learning_rate": 3.505219561204398e-05, "epoch": 3.7627118644067794, "percentage": 75.25, "elapsed_time": "0:53:44", "remaining_time": "0:17:40"}
|
| 337 |
+
{"current_steps": 3340, "total_steps": 4425, "loss": 0.4992, "learning_rate": 3.445432224810232e-05, "epoch": 3.774011299435028, "percentage": 75.48, "elapsed_time": "0:53:55", "remaining_time": "0:17:30"}
|
| 338 |
+
{"current_steps": 3350, "total_steps": 4425, "loss": 0.5063, "learning_rate": 3.386052868572186e-05, "epoch": 3.785310734463277, "percentage": 75.71, "elapsed_time": "0:54:03", "remaining_time": "0:17:20"}
|
| 339 |
+
{"current_steps": 3360, "total_steps": 4425, "loss": 0.5045, "learning_rate": 3.3270851884775203e-05, "epoch": 3.7966101694915255, "percentage": 75.93, "elapsed_time": "0:54:14", "remaining_time": "0:17:11"}
|
| 340 |
+
{"current_steps": 3370, "total_steps": 4425, "loss": 0.4818, "learning_rate": 3.268532854889287e-05, "epoch": 3.8079096045197742, "percentage": 76.16, "elapsed_time": "0:54:23", "remaining_time": "0:17:01"}
|
| 341 |
+
{"current_steps": 3380, "total_steps": 4425, "loss": 0.5064, "learning_rate": 3.210399512317849e-05, "epoch": 3.8192090395480225, "percentage": 76.38, "elapsed_time": "0:54:33", "remaining_time": "0:16:51"}
|
| 342 |
+
{"current_steps": 3390, "total_steps": 4425, "loss": 0.4761, "learning_rate": 3.1526887791940395e-05, "epoch": 3.830508474576271, "percentage": 76.61, "elapsed_time": "0:54:42", "remaining_time": "0:16:42"}
|
| 343 |
+
{"current_steps": 3400, "total_steps": 4425, "loss": 0.4874, "learning_rate": 3.095404247643955e-05, "epoch": 3.84180790960452, "percentage": 76.84, "elapsed_time": "0:54:53", "remaining_time": "0:16:32"}
|
| 344 |
+
{"current_steps": 3410, "total_steps": 4425, "loss": 0.4748, "learning_rate": 3.038549483265348e-05, "epoch": 3.853107344632768, "percentage": 77.06, "elapsed_time": "0:55:02", "remaining_time": "0:16:23"}
|
| 345 |
+
{"current_steps": 3420, "total_steps": 4425, "loss": 0.4841, "learning_rate": 2.982128024905697e-05, "epoch": 3.864406779661017, "percentage": 77.29, "elapsed_time": "0:55:12", "remaining_time": "0:16:13"}
|
| 346 |
+
{"current_steps": 3430, "total_steps": 4425, "loss": 0.4687, "learning_rate": 2.9261433844419306e-05, "epoch": 3.8757062146892656, "percentage": 77.51, "elapsed_time": "0:55:22", "remaining_time": "0:16:03"}
|
| 347 |
+
{"current_steps": 3440, "total_steps": 4425, "loss": 0.489, "learning_rate": 2.870599046561858e-05, "epoch": 3.8870056497175143, "percentage": 77.74, "elapsed_time": "0:55:31", "remaining_time": "0:15:53"}
|
| 348 |
+
{"current_steps": 3450, "total_steps": 4425, "loss": 0.4886, "learning_rate": 2.8154984685472373e-05, "epoch": 3.898305084745763, "percentage": 77.97, "elapsed_time": "0:55:42", "remaining_time": "0:15:44"}
|
| 349 |
+
{"current_steps": 3460, "total_steps": 4425, "loss": 0.5028, "learning_rate": 2.7608450800586016e-05, "epoch": 3.9096045197740112, "percentage": 78.19, "elapsed_time": "0:55:51", "remaining_time": "0:15:34"}
|
| 350 |
+
{"current_steps": 3470, "total_steps": 4425, "loss": 0.5216, "learning_rate": 2.7066422829217875e-05, "epoch": 3.92090395480226, "percentage": 78.42, "elapsed_time": "0:56:00", "remaining_time": "0:15:24"}
|
| 351 |
+
{"current_steps": 3480, "total_steps": 4425, "loss": 0.4596, "learning_rate": 2.6528934509161763e-05, "epoch": 3.9322033898305087, "percentage": 78.64, "elapsed_time": "0:56:09", "remaining_time": "0:15:15"}
|
| 352 |
+
{"current_steps": 3490, "total_steps": 4425, "loss": 0.4944, "learning_rate": 2.599601929564709e-05, "epoch": 3.943502824858757, "percentage": 78.87, "elapsed_time": "0:56:19", "remaining_time": "0:15:05"}
|
| 353 |
+
{"current_steps": 3500, "total_steps": 4425, "loss": 0.4779, "learning_rate": 2.5467710359256557e-05, "epoch": 3.9548022598870056, "percentage": 79.1, "elapsed_time": "0:56:28", "remaining_time": "0:14:55"}
|
| 354 |
+
{"current_steps": 3510, "total_steps": 4425, "loss": 0.4878, "learning_rate": 2.4944040583861284e-05, "epoch": 3.9661016949152543, "percentage": 79.32, "elapsed_time": "0:56:38", "remaining_time": "0:14:45"}
|
| 355 |
+
{"current_steps": 3520, "total_steps": 4425, "loss": 0.4719, "learning_rate": 2.4425042564574184e-05, "epoch": 3.9774011299435026, "percentage": 79.55, "elapsed_time": "0:56:48", "remaining_time": "0:14:36"}
|
| 356 |
+
{"current_steps": 3530, "total_steps": 4425, "loss": 0.4983, "learning_rate": 2.3910748605721066e-05, "epoch": 3.9887005649717513, "percentage": 79.77, "elapsed_time": "0:56:57", "remaining_time": "0:14:26"}
|
| 357 |
+
{"current_steps": 3540, "total_steps": 4425, "loss": 0.4916, "learning_rate": 2.3401190718829945e-05, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:57:06", "remaining_time": "0:14:16"}
|
| 358 |
+
{"current_steps": 3550, "total_steps": 4425, "loss": 0.4653, "learning_rate": 2.289640062063839e-05, "epoch": 4.011299435028248, "percentage": 80.23, "elapsed_time": "0:57:17", "remaining_time": "0:14:07"}
|
| 359 |
+
{"current_steps": 3560, "total_steps": 4425, "loss": 0.4595, "learning_rate": 2.239640973111945e-05, "epoch": 4.022598870056497, "percentage": 80.45, "elapsed_time": "0:57:26", "remaining_time": "0:13:57"}
|
| 360 |
+
{"current_steps": 3570, "total_steps": 4425, "loss": 0.4471, "learning_rate": 2.1901249171526063e-05, "epoch": 4.033898305084746, "percentage": 80.68, "elapsed_time": "0:57:36", "remaining_time": "0:13:47"}
|
| 361 |
+
{"current_steps": 3580, "total_steps": 4425, "loss": 0.437, "learning_rate": 2.1410949762453735e-05, "epoch": 4.045197740112994, "percentage": 80.9, "elapsed_time": "0:57:46", "remaining_time": "0:13:38"}
|
| 362 |
+
{"current_steps": 3590, "total_steps": 4425, "loss": 0.4194, "learning_rate": 2.0925542021922283e-05, "epoch": 4.056497175141243, "percentage": 81.13, "elapsed_time": "0:57:54", "remaining_time": "0:13:28"}
|
| 363 |
+
{"current_steps": 3600, "total_steps": 4425, "loss": 0.4568, "learning_rate": 2.0445056163476374e-05, "epoch": 4.067796610169491, "percentage": 81.36, "elapsed_time": "0:58:03", "remaining_time": "0:13:18"}
|
| 364 |
+
{"current_steps": 3610, "total_steps": 4425, "loss": 0.4673, "learning_rate": 1.9969522094304704e-05, "epoch": 4.0790960451977405, "percentage": 81.58, "elapsed_time": "0:58:13", "remaining_time": "0:13:08"}
|
| 365 |
+
{"current_steps": 3620, "total_steps": 4425, "loss": 0.4507, "learning_rate": 1.949896941337861e-05, "epoch": 4.090395480225989, "percentage": 81.81, "elapsed_time": "0:58:22", "remaining_time": "0:12:58"}
|
| 366 |
+
{"current_steps": 3630, "total_steps": 4425, "loss": 0.4271, "learning_rate": 1.9033427409609738e-05, "epoch": 4.101694915254237, "percentage": 82.03, "elapsed_time": "0:58:32", "remaining_time": "0:12:49"}
|
| 367 |
+
{"current_steps": 3640, "total_steps": 4425, "loss": 0.4331, "learning_rate": 1.8572925060026868e-05, "epoch": 4.112994350282486, "percentage": 82.26, "elapsed_time": "0:58:41", "remaining_time": "0:12:39"}
|
| 368 |
+
{"current_steps": 3650, "total_steps": 4425, "loss": 0.4388, "learning_rate": 1.8117491027972476e-05, "epoch": 4.124293785310734, "percentage": 82.49, "elapsed_time": "0:58:50", "remaining_time": "0:12:29"}
|
| 369 |
+
{"current_steps": 3660, "total_steps": 4425, "loss": 0.4432, "learning_rate": 1.766715366131837e-05, "epoch": 4.135593220338983, "percentage": 82.71, "elapsed_time": "0:59:00", "remaining_time": "0:12:20"}
|
| 370 |
+
{"current_steps": 3670, "total_steps": 4425, "loss": 0.4445, "learning_rate": 1.722194099070148e-05, "epoch": 4.146892655367232, "percentage": 82.94, "elapsed_time": "0:59:10", "remaining_time": "0:12:10"}
|
| 371 |
+
{"current_steps": 3680, "total_steps": 4425, "loss": 0.4348, "learning_rate": 1.678188072777891e-05, "epoch": 4.15819209039548, "percentage": 83.16, "elapsed_time": "0:59:20", "remaining_time": "0:12:00"}
|
| 372 |
+
{"current_steps": 3690, "total_steps": 4425, "loss": 0.4293, "learning_rate": 1.6347000263503176e-05, "epoch": 4.169491525423728, "percentage": 83.39, "elapsed_time": "0:59:30", "remaining_time": "0:11:51"}
|
| 373 |
+
{"current_steps": 3700, "total_steps": 4425, "loss": 0.4469, "learning_rate": 1.591732666641732e-05, "epoch": 4.1807909604519775, "percentage": 83.62, "elapsed_time": "0:59:41", "remaining_time": "0:11:41"}
|
| 374 |
+
{"current_steps": 3710, "total_steps": 4425, "loss": 0.4415, "learning_rate": 1.5492886680969963e-05, "epoch": 4.192090395480226, "percentage": 83.84, "elapsed_time": "0:59:50", "remaining_time": "0:11:31"}
|
| 375 |
+
{"current_steps": 3720, "total_steps": 4425, "loss": 0.4365, "learning_rate": 1.5073706725850679e-05, "epoch": 4.203389830508475, "percentage": 84.07, "elapsed_time": "1:00:00", "remaining_time": "0:11:22"}
|
| 376 |
+
{"current_steps": 3730, "total_steps": 4425, "loss": 0.4717, "learning_rate": 1.4659812892345692e-05, "epoch": 4.214689265536723, "percentage": 84.29, "elapsed_time": "1:00:09", "remaining_time": "0:11:12"}
|
| 377 |
+
{"current_steps": 3740, "total_steps": 4425, "loss": 0.4484, "learning_rate": 1.425123094271369e-05, "epoch": 4.2259887005649714, "percentage": 84.52, "elapsed_time": "1:00:18", "remaining_time": "0:11:02"}
|
| 378 |
+
{"current_steps": 3750, "total_steps": 4425, "loss": 0.4566, "learning_rate": 1.3847986308582384e-05, "epoch": 4.237288135593221, "percentage": 84.75, "elapsed_time": "1:00:28", "remaining_time": "0:10:53"}
|
| 379 |
+
{"current_steps": 3760, "total_steps": 4425, "loss": 0.4768, "learning_rate": 1.3450104089365611e-05, "epoch": 4.248587570621469, "percentage": 84.97, "elapsed_time": "1:00:37", "remaining_time": "0:10:43"}
|
| 380 |
+
{"current_steps": 3770, "total_steps": 4425, "loss": 0.4657, "learning_rate": 1.3057609050700881e-05, "epoch": 4.259887005649717, "percentage": 85.2, "elapsed_time": "1:00:47", "remaining_time": "0:10:33"}
|
| 381 |
+
{"current_steps": 3780, "total_steps": 4425, "loss": 0.4412, "learning_rate": 1.267052562290808e-05, "epoch": 4.271186440677966, "percentage": 85.42, "elapsed_time": "1:00:56", "remaining_time": "0:10:23"}
|
| 382 |
+
{"current_steps": 3790, "total_steps": 4425, "loss": 0.4528, "learning_rate": 1.2288877899468653e-05, "epoch": 4.2824858757062145, "percentage": 85.65, "elapsed_time": "1:01:06", "remaining_time": "0:10:14"}
|
| 383 |
+
{"current_steps": 3800, "total_steps": 4425, "loss": 0.4466, "learning_rate": 1.1912689635526086e-05, "epoch": 4.293785310734464, "percentage": 85.88, "elapsed_time": "1:01:16", "remaining_time": "0:10:04"}
|
| 384 |
+
{"current_steps": 3810, "total_steps": 4425, "loss": 0.4332, "learning_rate": 1.1541984246407189e-05, "epoch": 4.305084745762712, "percentage": 86.1, "elapsed_time": "1:01:25", "remaining_time": "0:09:54"}
|
| 385 |
+
{"current_steps": 3820, "total_steps": 4425, "loss": 0.4223, "learning_rate": 1.1176784806164676e-05, "epoch": 4.31638418079096, "percentage": 86.33, "elapsed_time": "1:01:34", "remaining_time": "0:09:45"}
|
| 386 |
+
{"current_steps": 3830, "total_steps": 4425, "loss": 0.4335, "learning_rate": 1.081711404614104e-05, "epoch": 4.327683615819209, "percentage": 86.55, "elapsed_time": "1:01:44", "remaining_time": "0:09:35"}
|
| 387 |
+
{"current_steps": 3840, "total_steps": 4425, "loss": 0.4221, "learning_rate": 1.0462994353553512e-05, "epoch": 4.338983050847458, "percentage": 86.78, "elapsed_time": "1:01:52", "remaining_time": "0:09:25"}
|
| 388 |
+
{"current_steps": 3850, "total_steps": 4425, "loss": 0.43, "learning_rate": 1.0114447770100688e-05, "epoch": 4.350282485875706, "percentage": 87.01, "elapsed_time": "1:02:01", "remaining_time": "0:09:15"}
|
| 389 |
+
{"current_steps": 3860, "total_steps": 4425, "loss": 0.4407, "learning_rate": 9.77149599059063e-06, "epoch": 4.361581920903955, "percentage": 87.23, "elapsed_time": "1:02:10", "remaining_time": "0:09:06"}
|
| 390 |
+
{"current_steps": 3870, "total_steps": 4425, "loss": 0.4434, "learning_rate": 9.434160361590372e-06, "epoch": 4.372881355932203, "percentage": 87.46, "elapsed_time": "1:02:19", "remaining_time": "0:08:56"}
|
| 391 |
+
{"current_steps": 3880, "total_steps": 4425, "loss": 0.4411, "learning_rate": 9.102461880097302e-06, "epoch": 4.3841807909604515, "percentage": 87.68, "elapsed_time": "1:02:29", "remaining_time": "0:08:46"}
|
| 392 |
+
{"current_steps": 3890, "total_steps": 4425, "loss": 0.431, "learning_rate": 8.776421192232298e-06, "epoch": 4.395480225988701, "percentage": 87.91, "elapsed_time": "1:02:40", "remaining_time": "0:08:37"}
|
| 393 |
+
{"current_steps": 3900, "total_steps": 4425, "loss": 0.4422, "learning_rate": 8.456058591954463e-06, "epoch": 4.406779661016949, "percentage": 88.14, "elapsed_time": "1:02:50", "remaining_time": "0:08:27"}
|
| 394 |
+
{"current_steps": 3910, "total_steps": 4425, "loss": 0.4413, "learning_rate": 8.141394019798177e-06, "epoch": 4.418079096045198, "percentage": 88.36, "elapsed_time": "1:03:00", "remaining_time": "0:08:17"}
|
| 395 |
+
{"current_steps": 3920, "total_steps": 4425, "loss": 0.4191, "learning_rate": 7.832447061631688e-06, "epoch": 4.429378531073446, "percentage": 88.59, "elapsed_time": "1:03:09", "remaining_time": "0:08:08"}
|
| 396 |
+
{"current_steps": 3930, "total_steps": 4425, "loss": 0.4428, "learning_rate": 7.529236947438256e-06, "epoch": 4.440677966101695, "percentage": 88.81, "elapsed_time": "1:03:18", "remaining_time": "0:07:58"}
|
| 397 |
+
{"current_steps": 3940, "total_steps": 4425, "loss": 0.4363, "learning_rate": 7.231782550119015e-06, "epoch": 4.451977401129944, "percentage": 89.04, "elapsed_time": "1:03:27", "remaining_time": "0:07:48"}
|
| 398 |
+
{"current_steps": 3950, "total_steps": 4425, "loss": 0.4462, "learning_rate": 6.940102384318314e-06, "epoch": 4.463276836158192, "percentage": 89.27, "elapsed_time": "1:03:36", "remaining_time": "0:07:38"}
|
| 399 |
+
{"current_steps": 3960, "total_steps": 4425, "loss": 0.4463, "learning_rate": 6.654214605271414e-06, "epoch": 4.47457627118644, "percentage": 89.49, "elapsed_time": "1:03:45", "remaining_time": "0:07:29"}
|
| 400 |
+
{"current_steps": 3970, "total_steps": 4425, "loss": 0.4388, "learning_rate": 6.37413700767423e-06, "epoch": 4.4858757062146895, "percentage": 89.72, "elapsed_time": "1:03:54", "remaining_time": "0:07:19"}
|
| 401 |
+
{"current_steps": 3980, "total_steps": 4425, "loss": 0.4466, "learning_rate": 6.099887024575901e-06, "epoch": 4.497175141242938, "percentage": 89.94, "elapsed_time": "1:04:02", "remaining_time": "0:07:09"}
|
| 402 |
+
{"current_steps": 3990, "total_steps": 4425, "loss": 0.4628, "learning_rate": 5.831481726293609e-06, "epoch": 4.508474576271187, "percentage": 90.17, "elapsed_time": "1:04:12", "remaining_time": "0:07:00"}
|
| 403 |
+
{"current_steps": 4000, "total_steps": 4425, "loss": 0.4261, "learning_rate": 5.568937819350084e-06, "epoch": 4.519774011299435, "percentage": 90.4, "elapsed_time": "1:04:22", "remaining_time": "0:06:50"}
|
| 404 |
+
{"current_steps": 4000, "total_steps": 4425, "eval_loss": 0.8213748335838318, "epoch": 4.519774011299435, "percentage": 90.4, "elapsed_time": "1:04:39", "remaining_time": "0:06:52"}
|
| 405 |
+
{"current_steps": 4010, "total_steps": 4425, "loss": 0.4298, "learning_rate": 5.312271645433697e-06, "epoch": 4.531073446327683, "percentage": 90.62, "elapsed_time": "1:04:49", "remaining_time": "0:06:42"}
|
| 406 |
+
{"current_steps": 4020, "total_steps": 4425, "loss": 0.4547, "learning_rate": 5.061499180381391e-06, "epoch": 4.5423728813559325, "percentage": 90.85, "elapsed_time": "1:04:59", "remaining_time": "0:06:32"}
|
| 407 |
+
{"current_steps": 4030, "total_steps": 4425, "loss": 0.4172, "learning_rate": 4.816636033184119e-06, "epoch": 4.553672316384181, "percentage": 91.07, "elapsed_time": "1:05:10", "remaining_time": "0:06:23"}
|
| 408 |
+
{"current_steps": 4040, "total_steps": 4425, "loss": 0.4664, "learning_rate": 4.577697445015472e-06, "epoch": 4.564971751412429, "percentage": 91.3, "elapsed_time": "1:05:20", "remaining_time": "0:06:13"}
|
| 409 |
+
{"current_steps": 4050, "total_steps": 4425, "loss": 0.4401, "learning_rate": 4.3446982882828555e-06, "epoch": 4.576271186440678, "percentage": 91.53, "elapsed_time": "1:05:29", "remaining_time": "0:06:03"}
|
| 410 |
+
{"current_steps": 4060, "total_steps": 4425, "loss": 0.4297, "learning_rate": 4.117653065701899e-06, "epoch": 4.5875706214689265, "percentage": 91.75, "elapsed_time": "1:05:39", "remaining_time": "0:05:54"}
|
| 411 |
+
{"current_steps": 4070, "total_steps": 4425, "loss": 0.453, "learning_rate": 3.896575909393663e-06, "epoch": 4.598870056497175, "percentage": 91.98, "elapsed_time": "1:05:48", "remaining_time": "0:05:44"}
|
| 412 |
+
{"current_steps": 4080, "total_steps": 4425, "loss": 0.445, "learning_rate": 3.6814805800050255e-06, "epoch": 4.610169491525424, "percentage": 92.2, "elapsed_time": "1:05:58", "remaining_time": "0:05:34"}
|
| 413 |
+
{"current_steps": 4090, "total_steps": 4425, "loss": 0.4332, "learning_rate": 3.4723804658522318e-06, "epoch": 4.621468926553672, "percentage": 92.43, "elapsed_time": "1:06:07", "remaining_time": "0:05:25"}
|
| 414 |
+
{"current_steps": 4100, "total_steps": 4425, "loss": 0.4667, "learning_rate": 3.269288582087493e-06, "epoch": 4.632768361581921, "percentage": 92.66, "elapsed_time": "1:06:15", "remaining_time": "0:05:15"}
|
| 415 |
+
{"current_steps": 4110, "total_steps": 4425, "loss": 0.4484, "learning_rate": 3.072217569888847e-06, "epoch": 4.6440677966101696, "percentage": 92.88, "elapsed_time": "1:06:26", "remaining_time": "0:05:05"}
|
| 416 |
+
{"current_steps": 4120, "total_steps": 4425, "loss": 0.4476, "learning_rate": 2.8811796956734418e-06, "epoch": 4.655367231638418, "percentage": 93.11, "elapsed_time": "1:06:35", "remaining_time": "0:04:55"}
|
| 417 |
+
{"current_steps": 4130, "total_steps": 4425, "loss": 0.4556, "learning_rate": 2.696186850333893e-06, "epoch": 4.666666666666667, "percentage": 93.33, "elapsed_time": "1:06:44", "remaining_time": "0:04:46"}
|
| 418 |
+
{"current_steps": 4140, "total_steps": 4425, "loss": 0.4361, "learning_rate": 2.5172505484982733e-06, "epoch": 4.677966101694915, "percentage": 93.56, "elapsed_time": "1:06:53", "remaining_time": "0:04:36"}
|
| 419 |
+
{"current_steps": 4150, "total_steps": 4425, "loss": 0.454, "learning_rate": 2.3443819278132996e-06, "epoch": 4.6892655367231635, "percentage": 93.79, "elapsed_time": "1:07:03", "remaining_time": "0:04:26"}
|
| 420 |
+
{"current_steps": 4160, "total_steps": 4425, "loss": 0.4438, "learning_rate": 2.17759174825114e-06, "epoch": 4.700564971751413, "percentage": 94.01, "elapsed_time": "1:07:12", "remaining_time": "0:04:16"}
|
| 421 |
+
{"current_steps": 4170, "total_steps": 4425, "loss": 0.4665, "learning_rate": 2.016890391439674e-06, "epoch": 4.711864406779661, "percentage": 94.24, "elapsed_time": "1:07:21", "remaining_time": "0:04:07"}
|
| 422 |
+
{"current_steps": 4180, "total_steps": 4425, "loss": 0.4477, "learning_rate": 1.8622878600162763e-06, "epoch": 4.72316384180791, "percentage": 94.46, "elapsed_time": "1:07:31", "remaining_time": "0:03:57"}
|
| 423 |
+
{"current_steps": 4190, "total_steps": 4425, "loss": 0.4605, "learning_rate": 1.7137937770052349e-06, "epoch": 4.734463276836158, "percentage": 94.69, "elapsed_time": "1:07:40", "remaining_time": "0:03:47"}
|
| 424 |
+
{"current_steps": 4200, "total_steps": 4425, "loss": 0.4458, "learning_rate": 1.5714173852187875e-06, "epoch": 4.745762711864407, "percentage": 94.92, "elapsed_time": "1:07:50", "remaining_time": "0:03:38"}
|
| 425 |
+
{"current_steps": 4210, "total_steps": 4425, "loss": 0.4311, "learning_rate": 1.4351675466817705e-06, "epoch": 4.757062146892656, "percentage": 95.14, "elapsed_time": "1:08:00", "remaining_time": "0:03:28"}
|
| 426 |
+
{"current_steps": 4220, "total_steps": 4425, "loss": 0.4526, "learning_rate": 1.3050527420800928e-06, "epoch": 4.768361581920904, "percentage": 95.37, "elapsed_time": "1:08:08", "remaining_time": "0:03:18"}
|
| 427 |
+
{"current_steps": 4230, "total_steps": 4425, "loss": 0.4407, "learning_rate": 1.1810810702327701e-06, "epoch": 4.779661016949152, "percentage": 95.59, "elapsed_time": "1:08:19", "remaining_time": "0:03:08"}
|
| 428 |
+
{"current_steps": 4240, "total_steps": 4425, "loss": 0.4367, "learning_rate": 1.063260247587905e-06, "epoch": 4.790960451977401, "percentage": 95.82, "elapsed_time": "1:08:29", "remaining_time": "0:02:59"}
|
| 429 |
+
{"current_steps": 4250, "total_steps": 4425, "loss": 0.4438, "learning_rate": 9.515976077423716e-07, "epoch": 4.80225988700565, "percentage": 96.05, "elapsed_time": "1:08:39", "remaining_time": "0:02:49"}
|
| 430 |
+
{"current_steps": 4260, "total_steps": 4425, "loss": 0.4326, "learning_rate": 8.461001009852809e-07, "epoch": 4.813559322033898, "percentage": 96.27, "elapsed_time": "1:08:49", "remaining_time": "0:02:39"}
|
| 431 |
+
{"current_steps": 4270, "total_steps": 4425, "loss": 0.4258, "learning_rate": 7.46774293865471e-07, "epoch": 4.824858757062147, "percentage": 96.5, "elapsed_time": "1:08:59", "remaining_time": "0:02:30"}
|
| 432 |
+
{"current_steps": 4280, "total_steps": 4425, "loss": 0.4377, "learning_rate": 6.536263687827005e-07, "epoch": 4.836158192090395, "percentage": 96.72, "elapsed_time": "1:09:09", "remaining_time": "0:02:20"}
|
| 433 |
+
{"current_steps": 4290, "total_steps": 4425, "loss": 0.447, "learning_rate": 5.66662123602879e-07, "epoch": 4.847457627118644, "percentage": 96.95, "elapsed_time": "1:09:18", "remaining_time": "0:02:10"}
|
| 434 |
+
{"current_steps": 4300, "total_steps": 4425, "loss": 0.4536, "learning_rate": 4.858869712971669e-07, "epoch": 4.858757062146893, "percentage": 97.18, "elapsed_time": "1:09:27", "remaining_time": "0:02:01"}
|
| 435 |
+
{"current_steps": 4310, "total_steps": 4425, "loss": 0.4328, "learning_rate": 4.113059396050445e-07, "epoch": 4.870056497175141, "percentage": 97.4, "elapsed_time": "1:09:36", "remaining_time": "0:01:51"}
|
| 436 |
+
{"current_steps": 4320, "total_steps": 4425, "loss": 0.4629, "learning_rate": 3.4292367072140677e-07, "epoch": 4.88135593220339, "percentage": 97.63, "elapsed_time": "1:09:45", "remaining_time": "0:01:41"}
|
| 437 |
+
{"current_steps": 4330, "total_steps": 4425, "loss": 0.4347, "learning_rate": 2.807444210075616e-07, "epoch": 4.892655367231638, "percentage": 97.85, "elapsed_time": "1:09:54", "remaining_time": "0:01:32"}
|
| 438 |
+
{"current_steps": 4340, "total_steps": 4425, "loss": 0.4536, "learning_rate": 2.2477206072633038e-07, "epoch": 4.903954802259887, "percentage": 98.08, "elapsed_time": "1:10:03", "remaining_time": "0:01:22"}
|
| 439 |
+
{"current_steps": 4350, "total_steps": 4425, "loss": 0.4453, "learning_rate": 1.7501007380115174e-07, "epoch": 4.915254237288136, "percentage": 98.31, "elapsed_time": "1:10:13", "remaining_time": "0:01:12"}
|
| 440 |
+
{"current_steps": 4360, "total_steps": 4425, "loss": 0.4454, "learning_rate": 1.3146155759923285e-07, "epoch": 4.926553672316384, "percentage": 98.53, "elapsed_time": "1:10:23", "remaining_time": "0:01:02"}
|
| 441 |
+
{"current_steps": 4370, "total_steps": 4425, "loss": 0.4107, "learning_rate": 9.412922273871471e-08, "epoch": 4.937853107344633, "percentage": 98.76, "elapsed_time": "1:10:34", "remaining_time": "0:00:53"}
|
| 442 |
+
{"current_steps": 4380, "total_steps": 4425, "loss": 0.4355, "learning_rate": 6.301539292001834e-08, "epoch": 4.9491525423728815, "percentage": 98.98, "elapsed_time": "1:10:44", "remaining_time": "0:00:43"}
|
| 443 |
+
{"current_steps": 4390, "total_steps": 4425, "loss": 0.4502, "learning_rate": 3.8122004781149246e-08, "epoch": 4.96045197740113, "percentage": 99.21, "elapsed_time": "1:10:53", "remaining_time": "0:00:33"}
|
| 444 |
+
{"current_steps": 4400, "total_steps": 4425, "loss": 0.4426, "learning_rate": 1.9450607777204978e-08, "epoch": 4.971751412429379, "percentage": 99.44, "elapsed_time": "1:11:03", "remaining_time": "0:00:24"}
|
| 445 |
+
{"current_steps": 4410, "total_steps": 4425, "loss": 0.449, "learning_rate": 7.00236408388566e-09, "epoch": 4.983050847457627, "percentage": 99.66, "elapsed_time": "1:11:13", "remaining_time": "0:00:14"}
|
| 446 |
+
{"current_steps": 4420, "total_steps": 4425, "loss": 0.4552, "learning_rate": 7.780485252073533e-10, "epoch": 4.994350282485875, "percentage": 99.89, "elapsed_time": "1:11:22", "remaining_time": "0:00:04"}
|
| 447 |
+
{"current_steps": 4425, "total_steps": 4425, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:11:27", "remaining_time": "0:00:00"}
|
wizardlm/trainer_state.json
ADDED
|
@@ -0,0 +1,3168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 1000,
|
| 6 |
+
"global_step": 4425,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.011299435028248588,
|
| 13 |
+
"grad_norm": 0.7552605867385864,
|
| 14 |
+
"learning_rate": 4.5146726862302485e-06,
|
| 15 |
+
"loss": 1.0465,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.022598870056497175,
|
| 20 |
+
"grad_norm": 0.8854597210884094,
|
| 21 |
+
"learning_rate": 9.029345372460497e-06,
|
| 22 |
+
"loss": 1.0939,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03389830508474576,
|
| 27 |
+
"grad_norm": 0.7813611030578613,
|
| 28 |
+
"learning_rate": 1.3544018058690747e-05,
|
| 29 |
+
"loss": 1.0292,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04519774011299435,
|
| 34 |
+
"grad_norm": 0.6397517919540405,
|
| 35 |
+
"learning_rate": 1.8058690744920994e-05,
|
| 36 |
+
"loss": 0.995,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05649717514124294,
|
| 41 |
+
"grad_norm": 0.4727611839771271,
|
| 42 |
+
"learning_rate": 2.2573363431151244e-05,
|
| 43 |
+
"loss": 0.896,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06779661016949153,
|
| 48 |
+
"grad_norm": 0.37453365325927734,
|
| 49 |
+
"learning_rate": 2.7088036117381494e-05,
|
| 50 |
+
"loss": 0.8037,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07909604519774012,
|
| 55 |
+
"grad_norm": 0.5303831696510315,
|
| 56 |
+
"learning_rate": 3.1602708803611745e-05,
|
| 57 |
+
"loss": 0.7872,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0903954802259887,
|
| 62 |
+
"grad_norm": 0.3839394152164459,
|
| 63 |
+
"learning_rate": 3.611738148984199e-05,
|
| 64 |
+
"loss": 0.7697,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1016949152542373,
|
| 69 |
+
"grad_norm": 0.39426788687705994,
|
| 70 |
+
"learning_rate": 4.063205417607224e-05,
|
| 71 |
+
"loss": 0.7481,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11299435028248588,
|
| 76 |
+
"grad_norm": 0.29685771465301514,
|
| 77 |
+
"learning_rate": 4.514672686230249e-05,
|
| 78 |
+
"loss": 0.7166,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12429378531073447,
|
| 83 |
+
"grad_norm": 0.3550776243209839,
|
| 84 |
+
"learning_rate": 4.966139954853273e-05,
|
| 85 |
+
"loss": 0.7455,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.13559322033898305,
|
| 90 |
+
"grad_norm": 0.49571502208709717,
|
| 91 |
+
"learning_rate": 5.417607223476299e-05,
|
| 92 |
+
"loss": 0.7451,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.14689265536723164,
|
| 97 |
+
"grad_norm": 0.3369849622249603,
|
| 98 |
+
"learning_rate": 5.869074492099323e-05,
|
| 99 |
+
"loss": 0.7235,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.15819209039548024,
|
| 104 |
+
"grad_norm": 0.37830305099487305,
|
| 105 |
+
"learning_rate": 6.320541760722349e-05,
|
| 106 |
+
"loss": 0.7201,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1694915254237288,
|
| 111 |
+
"grad_norm": 0.42834165692329407,
|
| 112 |
+
"learning_rate": 6.772009029345373e-05,
|
| 113 |
+
"loss": 0.7199,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1807909604519774,
|
| 118 |
+
"grad_norm": 0.3480307459831238,
|
| 119 |
+
"learning_rate": 7.223476297968398e-05,
|
| 120 |
+
"loss": 0.7134,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.192090395480226,
|
| 125 |
+
"grad_norm": 0.47217118740081787,
|
| 126 |
+
"learning_rate": 7.674943566591423e-05,
|
| 127 |
+
"loss": 0.7193,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2033898305084746,
|
| 132 |
+
"grad_norm": 0.43827682733535767,
|
| 133 |
+
"learning_rate": 8.126410835214448e-05,
|
| 134 |
+
"loss": 0.7049,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.21468926553672316,
|
| 139 |
+
"grad_norm": 0.38405266404151917,
|
| 140 |
+
"learning_rate": 8.577878103837473e-05,
|
| 141 |
+
"loss": 0.719,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.22598870056497175,
|
| 146 |
+
"grad_norm": 0.48938581347465515,
|
| 147 |
+
"learning_rate": 9.029345372460498e-05,
|
| 148 |
+
"loss": 0.7077,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.23728813559322035,
|
| 153 |
+
"grad_norm": 0.4330425560474396,
|
| 154 |
+
"learning_rate": 9.480812641083521e-05,
|
| 155 |
+
"loss": 0.7301,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24858757062146894,
|
| 160 |
+
"grad_norm": 0.3442066013813019,
|
| 161 |
+
"learning_rate": 9.932279909706546e-05,
|
| 162 |
+
"loss": 0.7174,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.2598870056497175,
|
| 167 |
+
"grad_norm": 0.41479647159576416,
|
| 168 |
+
"learning_rate": 0.00010383747178329573,
|
| 169 |
+
"loss": 0.7163,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2711864406779661,
|
| 174 |
+
"grad_norm": 0.4269746243953705,
|
| 175 |
+
"learning_rate": 0.00010835214446952598,
|
| 176 |
+
"loss": 0.7206,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2824858757062147,
|
| 181 |
+
"grad_norm": 0.4595146179199219,
|
| 182 |
+
"learning_rate": 0.00011286681715575623,
|
| 183 |
+
"loss": 0.7198,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2937853107344633,
|
| 188 |
+
"grad_norm": 0.459258496761322,
|
| 189 |
+
"learning_rate": 0.00011738148984198646,
|
| 190 |
+
"loss": 0.6791,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3050847457627119,
|
| 195 |
+
"grad_norm": 0.40073147416114807,
|
| 196 |
+
"learning_rate": 0.00012189616252821671,
|
| 197 |
+
"loss": 0.7379,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3163841807909605,
|
| 202 |
+
"grad_norm": 0.4646053910255432,
|
| 203 |
+
"learning_rate": 0.00012641083521444698,
|
| 204 |
+
"loss": 0.7146,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.327683615819209,
|
| 209 |
+
"grad_norm": 0.5096935629844666,
|
| 210 |
+
"learning_rate": 0.00013092550790067722,
|
| 211 |
+
"loss": 0.6855,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3389830508474576,
|
| 216 |
+
"grad_norm": 0.37696900963783264,
|
| 217 |
+
"learning_rate": 0.00013544018058690745,
|
| 218 |
+
"loss": 0.7169,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3502824858757062,
|
| 223 |
+
"grad_norm": 0.344178169965744,
|
| 224 |
+
"learning_rate": 0.00013995485327313772,
|
| 225 |
+
"loss": 0.7079,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3615819209039548,
|
| 230 |
+
"grad_norm": 0.33671554923057556,
|
| 231 |
+
"learning_rate": 0.00014446952595936795,
|
| 232 |
+
"loss": 0.68,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.3728813559322034,
|
| 237 |
+
"grad_norm": 0.365024596452713,
|
| 238 |
+
"learning_rate": 0.00014898419864559822,
|
| 239 |
+
"loss": 0.7247,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.384180790960452,
|
| 244 |
+
"grad_norm": 0.36559364199638367,
|
| 245 |
+
"learning_rate": 0.00015349887133182845,
|
| 246 |
+
"loss": 0.6753,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.3954802259887006,
|
| 251 |
+
"grad_norm": 0.3757419288158417,
|
| 252 |
+
"learning_rate": 0.0001580135440180587,
|
| 253 |
+
"loss": 0.6616,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4067796610169492,
|
| 258 |
+
"grad_norm": 0.5549542307853699,
|
| 259 |
+
"learning_rate": 0.00016252821670428895,
|
| 260 |
+
"loss": 0.686,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4180790960451977,
|
| 265 |
+
"grad_norm": 0.3681774139404297,
|
| 266 |
+
"learning_rate": 0.0001670428893905192,
|
| 267 |
+
"loss": 0.7086,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4293785310734463,
|
| 272 |
+
"grad_norm": 0.3036465346813202,
|
| 273 |
+
"learning_rate": 0.00017155756207674945,
|
| 274 |
+
"loss": 0.6966,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.4406779661016949,
|
| 279 |
+
"grad_norm": 0.32314741611480713,
|
| 280 |
+
"learning_rate": 0.0001760722347629797,
|
| 281 |
+
"loss": 0.7406,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4519774011299435,
|
| 286 |
+
"grad_norm": 0.41190987825393677,
|
| 287 |
+
"learning_rate": 0.00018058690744920995,
|
| 288 |
+
"loss": 0.6772,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.4632768361581921,
|
| 293 |
+
"grad_norm": 0.28181225061416626,
|
| 294 |
+
"learning_rate": 0.0001851015801354402,
|
| 295 |
+
"loss": 0.6843,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4745762711864407,
|
| 300 |
+
"grad_norm": 0.2925048768520355,
|
| 301 |
+
"learning_rate": 0.00018961625282167043,
|
| 302 |
+
"loss": 0.7206,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4858757062146893,
|
| 307 |
+
"grad_norm": 0.33646613359451294,
|
| 308 |
+
"learning_rate": 0.0001941309255079007,
|
| 309 |
+
"loss": 0.6879,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.4971751412429379,
|
| 314 |
+
"grad_norm": 0.40007829666137695,
|
| 315 |
+
"learning_rate": 0.00019864559819413093,
|
| 316 |
+
"loss": 0.7032,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5084745762711864,
|
| 321 |
+
"grad_norm": 0.29928356409072876,
|
| 322 |
+
"learning_rate": 0.00019999847502678901,
|
| 323 |
+
"loss": 0.7086,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.519774011299435,
|
| 328 |
+
"grad_norm": 0.285306453704834,
|
| 329 |
+
"learning_rate": 0.00019999100588221217,
|
| 330 |
+
"loss": 0.6709,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5310734463276836,
|
| 335 |
+
"grad_norm": 0.5055399537086487,
|
| 336 |
+
"learning_rate": 0.00019997731293347473,
|
| 337 |
+
"loss": 0.6901,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5423728813559322,
|
| 342 |
+
"grad_norm": 0.3232295513153076,
|
| 343 |
+
"learning_rate": 0.00019995739703287558,
|
| 344 |
+
"loss": 0.6748,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5536723163841808,
|
| 349 |
+
"grad_norm": 0.40595105290412903,
|
| 350 |
+
"learning_rate": 0.00019993125942005297,
|
| 351 |
+
"loss": 0.6908,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5649717514124294,
|
| 356 |
+
"grad_norm": 0.29886409640312195,
|
| 357 |
+
"learning_rate": 0.00019989890172190697,
|
| 358 |
+
"loss": 0.6961,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.576271186440678,
|
| 363 |
+
"grad_norm": 0.3396940231323242,
|
| 364 |
+
"learning_rate": 0.00019986032595249855,
|
| 365 |
+
"loss": 0.6741,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5875706214689266,
|
| 370 |
+
"grad_norm": 0.3772926926612854,
|
| 371 |
+
"learning_rate": 0.00019981553451292396,
|
| 372 |
+
"loss": 0.6681,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5988700564971752,
|
| 377 |
+
"grad_norm": 0.3138965964317322,
|
| 378 |
+
"learning_rate": 0.00019976453019116547,
|
| 379 |
+
"loss": 0.7027,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6101694915254238,
|
| 384 |
+
"grad_norm": 0.31275707483291626,
|
| 385 |
+
"learning_rate": 0.00019970731616191772,
|
| 386 |
+
"loss": 0.6955,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6214689265536724,
|
| 391 |
+
"grad_norm": 0.28057295083999634,
|
| 392 |
+
"learning_rate": 0.00019964389598639012,
|
| 393 |
+
"loss": 0.6617,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.632768361581921,
|
| 398 |
+
"grad_norm": 0.5602757930755615,
|
| 399 |
+
"learning_rate": 0.00019957427361208522,
|
| 400 |
+
"loss": 0.6896,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6440677966101694,
|
| 405 |
+
"grad_norm": 0.43884241580963135,
|
| 406 |
+
"learning_rate": 0.00019949845337255306,
|
| 407 |
+
"loss": 0.6786,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.655367231638418,
|
| 412 |
+
"grad_norm": 0.3063630759716034,
|
| 413 |
+
"learning_rate": 0.00019941643998712128,
|
| 414 |
+
"loss": 0.685,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6666666666666666,
|
| 419 |
+
"grad_norm": 0.2912139594554901,
|
| 420 |
+
"learning_rate": 0.00019932823856060153,
|
| 421 |
+
"loss": 0.691,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6779661016949152,
|
| 426 |
+
"grad_norm": 0.5503478646278381,
|
| 427 |
+
"learning_rate": 0.00019923385458297168,
|
| 428 |
+
"loss": 0.7076,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6892655367231638,
|
| 433 |
+
"grad_norm": 0.30678126215934753,
|
| 434 |
+
"learning_rate": 0.00019913329392903396,
|
| 435 |
+
"loss": 0.6628,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7005649717514124,
|
| 440 |
+
"grad_norm": 0.341691792011261,
|
| 441 |
+
"learning_rate": 0.00019902656285804954,
|
| 442 |
+
"loss": 0.6973,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.711864406779661,
|
| 447 |
+
"grad_norm": 0.2795998454093933,
|
| 448 |
+
"learning_rate": 0.0001989136680133488,
|
| 449 |
+
"loss": 0.668,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7231638418079096,
|
| 454 |
+
"grad_norm": 0.3217742443084717,
|
| 455 |
+
"learning_rate": 0.00019879461642191774,
|
| 456 |
+
"loss": 0.6839,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7344632768361582,
|
| 461 |
+
"grad_norm": 0.2668191194534302,
|
| 462 |
+
"learning_rate": 0.00019866941549396075,
|
| 463 |
+
"loss": 0.6929,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7457627118644068,
|
| 468 |
+
"grad_norm": 0.8005201816558838,
|
| 469 |
+
"learning_rate": 0.0001985380730224393,
|
| 470 |
+
"loss": 0.701,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7570621468926554,
|
| 475 |
+
"grad_norm": 0.29280129075050354,
|
| 476 |
+
"learning_rate": 0.00019840059718258693,
|
| 477 |
+
"loss": 0.7222,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.768361581920904,
|
| 482 |
+
"grad_norm": 0.3449852764606476,
|
| 483 |
+
"learning_rate": 0.00019825699653140032,
|
| 484 |
+
"loss": 0.6919,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7796610169491526,
|
| 489 |
+
"grad_norm": 0.2684054970741272,
|
| 490 |
+
"learning_rate": 0.0001981072800071066,
|
| 491 |
+
"loss": 0.6859,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7909604519774012,
|
| 496 |
+
"grad_norm": 0.3716861307621002,
|
| 497 |
+
"learning_rate": 0.00019795145692860726,
|
| 498 |
+
"loss": 0.666,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8022598870056498,
|
| 503 |
+
"grad_norm": 0.3001028597354889,
|
| 504 |
+
"learning_rate": 0.00019778953699489785,
|
| 505 |
+
"loss": 0.6587,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.8135593220338984,
|
| 510 |
+
"grad_norm": 0.476034551858902,
|
| 511 |
+
"learning_rate": 0.0001976215302844644,
|
| 512 |
+
"loss": 0.6766,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8248587570621468,
|
| 517 |
+
"grad_norm": 0.3516661524772644,
|
| 518 |
+
"learning_rate": 0.00019744744725465617,
|
| 519 |
+
"loss": 0.6836,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8361581920903954,
|
| 524 |
+
"grad_norm": 0.275155246257782,
|
| 525 |
+
"learning_rate": 0.00019726729874103448,
|
| 526 |
+
"loss": 0.6729,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.847457627118644,
|
| 531 |
+
"grad_norm": 0.31217560172080994,
|
| 532 |
+
"learning_rate": 0.00019708109595669858,
|
| 533 |
+
"loss": 0.6811,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8587570621468926,
|
| 538 |
+
"grad_norm": 0.3042563199996948,
|
| 539 |
+
"learning_rate": 0.00019688885049158752,
|
| 540 |
+
"loss": 0.7353,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8700564971751412,
|
| 545 |
+
"grad_norm": 0.3564906120300293,
|
| 546 |
+
"learning_rate": 0.0001966905743117588,
|
| 547 |
+
"loss": 0.6938,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.8813559322033898,
|
| 552 |
+
"grad_norm": 0.3310820162296295,
|
| 553 |
+
"learning_rate": 0.00019648627975864355,
|
| 554 |
+
"loss": 0.6724,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8926553672316384,
|
| 559 |
+
"grad_norm": 0.4258658289909363,
|
| 560 |
+
"learning_rate": 0.00019627597954827833,
|
| 561 |
+
"loss": 0.6901,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.903954802259887,
|
| 566 |
+
"grad_norm": 0.3146076202392578,
|
| 567 |
+
"learning_rate": 0.00019605968677051378,
|
| 568 |
+
"loss": 0.7008,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9152542372881356,
|
| 573 |
+
"grad_norm": 0.3338530957698822,
|
| 574 |
+
"learning_rate": 0.0001958374148881996,
|
| 575 |
+
"loss": 0.6567,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9265536723163842,
|
| 580 |
+
"grad_norm": 0.3822636008262634,
|
| 581 |
+
"learning_rate": 0.00019560917773634676,
|
| 582 |
+
"loss": 0.6756,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.9378531073446328,
|
| 587 |
+
"grad_norm": 0.3074444830417633,
|
| 588 |
+
"learning_rate": 0.00019537498952126642,
|
| 589 |
+
"loss": 0.6958,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9491525423728814,
|
| 594 |
+
"grad_norm": 0.31832125782966614,
|
| 595 |
+
"learning_rate": 0.00019513486481968545,
|
| 596 |
+
"loss": 0.6871,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.96045197740113,
|
| 601 |
+
"grad_norm": 0.3670668303966522,
|
| 602 |
+
"learning_rate": 0.00019488881857783935,
|
| 603 |
+
"loss": 0.6956,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9717514124293786,
|
| 608 |
+
"grad_norm": 0.2784234881401062,
|
| 609 |
+
"learning_rate": 0.00019463686611054172,
|
| 610 |
+
"loss": 0.6865,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9830508474576272,
|
| 615 |
+
"grad_norm": 0.3210557997226715,
|
| 616 |
+
"learning_rate": 0.00019437902310023126,
|
| 617 |
+
"loss": 0.6845,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9943502824858758,
|
| 622 |
+
"grad_norm": 0.3313763737678528,
|
| 623 |
+
"learning_rate": 0.0001941153055959954,
|
| 624 |
+
"loss": 0.6589,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 1.0056497175141244,
|
| 629 |
+
"grad_norm": 0.35079240798950195,
|
| 630 |
+
"learning_rate": 0.00019384573001257155,
|
| 631 |
+
"loss": 0.671,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 1.0169491525423728,
|
| 636 |
+
"grad_norm": 0.3715152442455292,
|
| 637 |
+
"learning_rate": 0.0001935703131293252,
|
| 638 |
+
"loss": 0.608,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.0282485875706215,
|
| 643 |
+
"grad_norm": 0.3646804988384247,
|
| 644 |
+
"learning_rate": 0.00019328907208920567,
|
| 645 |
+
"loss": 0.6457,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.03954802259887,
|
| 650 |
+
"grad_norm": 0.3106479048728943,
|
| 651 |
+
"learning_rate": 0.00019300202439767898,
|
| 652 |
+
"loss": 0.6105,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.0508474576271187,
|
| 657 |
+
"grad_norm": 0.29659685492515564,
|
| 658 |
+
"learning_rate": 0.00019270918792163827,
|
| 659 |
+
"loss": 0.6221,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.0621468926553672,
|
| 664 |
+
"grad_norm": 0.4973548948764801,
|
| 665 |
+
"learning_rate": 0.00019241058088829166,
|
| 666 |
+
"loss": 0.6465,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 1.073446327683616,
|
| 671 |
+
"grad_norm": 0.4067288637161255,
|
| 672 |
+
"learning_rate": 0.00019210622188402788,
|
| 673 |
+
"loss": 0.6374,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.0847457627118644,
|
| 678 |
+
"grad_norm": 0.4106499254703522,
|
| 679 |
+
"learning_rate": 0.00019179612985325908,
|
| 680 |
+
"loss": 0.6226,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 1.0960451977401129,
|
| 685 |
+
"grad_norm": 0.31531280279159546,
|
| 686 |
+
"learning_rate": 0.000191480324097242,
|
| 687 |
+
"loss": 0.6604,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.1073446327683616,
|
| 692 |
+
"grad_norm": 0.3855787515640259,
|
| 693 |
+
"learning_rate": 0.00019115882427287638,
|
| 694 |
+
"loss": 0.6466,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 1.11864406779661,
|
| 699 |
+
"grad_norm": 0.36246171593666077,
|
| 700 |
+
"learning_rate": 0.00019083165039148153,
|
| 701 |
+
"loss": 0.6315,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.1299435028248588,
|
| 706 |
+
"grad_norm": 0.4511447846889496,
|
| 707 |
+
"learning_rate": 0.00019049882281755066,
|
| 708 |
+
"loss": 0.6341,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.1299435028248588,
|
| 713 |
+
"eval_loss": 0.7100452184677124,
|
| 714 |
+
"eval_runtime": 16.7354,
|
| 715 |
+
"eval_samples_per_second": 89.093,
|
| 716 |
+
"eval_steps_per_second": 11.174,
|
| 717 |
+
"step": 1000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.1412429378531073,
|
| 721 |
+
"grad_norm": 0.39097025990486145,
|
| 722 |
+
"learning_rate": 0.00019016036226748346,
|
| 723 |
+
"loss": 0.6144,
|
| 724 |
+
"step": 1010
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.152542372881356,
|
| 728 |
+
"grad_norm": 0.40734922885894775,
|
| 729 |
+
"learning_rate": 0.00018981628980829652,
|
| 730 |
+
"loss": 0.6458,
|
| 731 |
+
"step": 1020
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.1638418079096045,
|
| 735 |
+
"grad_norm": 0.3473665118217468,
|
| 736 |
+
"learning_rate": 0.00018946662685631203,
|
| 737 |
+
"loss": 0.6417,
|
| 738 |
+
"step": 1030
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.1751412429378532,
|
| 742 |
+
"grad_norm": 0.41758203506469727,
|
| 743 |
+
"learning_rate": 0.0001891113951758249,
|
| 744 |
+
"loss": 0.6355,
|
| 745 |
+
"step": 1040
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.1864406779661016,
|
| 749 |
+
"grad_norm": 0.6268119215965271,
|
| 750 |
+
"learning_rate": 0.0001887506168777479,
|
| 751 |
+
"loss": 0.6332,
|
| 752 |
+
"step": 1050
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.1977401129943503,
|
| 756 |
+
"grad_norm": 0.3336067795753479,
|
| 757 |
+
"learning_rate": 0.00018838431441823547,
|
| 758 |
+
"loss": 0.6445,
|
| 759 |
+
"step": 1060
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.2090395480225988,
|
| 763 |
+
"grad_norm": 0.3316787779331207,
|
| 764 |
+
"learning_rate": 0.00018801251059728604,
|
| 765 |
+
"loss": 0.6314,
|
| 766 |
+
"step": 1070
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.2203389830508475,
|
| 770 |
+
"grad_norm": 0.304683119058609,
|
| 771 |
+
"learning_rate": 0.00018763522855732266,
|
| 772 |
+
"loss": 0.6232,
|
| 773 |
+
"step": 1080
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.231638418079096,
|
| 777 |
+
"grad_norm": 0.34174299240112305,
|
| 778 |
+
"learning_rate": 0.00018725249178175286,
|
| 779 |
+
"loss": 0.6561,
|
| 780 |
+
"step": 1090
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.2429378531073447,
|
| 784 |
+
"grad_norm": 0.3202422559261322,
|
| 785 |
+
"learning_rate": 0.0001868643240935066,
|
| 786 |
+
"loss": 0.6066,
|
| 787 |
+
"step": 1100
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.2542372881355932,
|
| 791 |
+
"grad_norm": 0.3420744836330414,
|
| 792 |
+
"learning_rate": 0.0001864707496535537,
|
| 793 |
+
"loss": 0.6367,
|
| 794 |
+
"step": 1110
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.2655367231638417,
|
| 798 |
+
"grad_norm": 0.38407158851623535,
|
| 799 |
+
"learning_rate": 0.00018607179295939983,
|
| 800 |
+
"loss": 0.6278,
|
| 801 |
+
"step": 1120
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.2768361581920904,
|
| 805 |
+
"grad_norm": 0.37982526421546936,
|
| 806 |
+
"learning_rate": 0.00018566747884356182,
|
| 807 |
+
"loss": 0.6209,
|
| 808 |
+
"step": 1130
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.288135593220339,
|
| 812 |
+
"grad_norm": 0.33808642625808716,
|
| 813 |
+
"learning_rate": 0.00018525783247202188,
|
| 814 |
+
"loss": 0.6525,
|
| 815 |
+
"step": 1140
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.2994350282485876,
|
| 819 |
+
"grad_norm": 0.45425844192504883,
|
| 820 |
+
"learning_rate": 0.00018484287934266122,
|
| 821 |
+
"loss": 0.6367,
|
| 822 |
+
"step": 1150
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.310734463276836,
|
| 826 |
+
"grad_norm": 0.422880083322525,
|
| 827 |
+
"learning_rate": 0.00018442264528367304,
|
| 828 |
+
"loss": 0.6499,
|
| 829 |
+
"step": 1160
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.3220338983050848,
|
| 833 |
+
"grad_norm": 0.3406778573989868,
|
| 834 |
+
"learning_rate": 0.0001839971564519547,
|
| 835 |
+
"loss": 0.6478,
|
| 836 |
+
"step": 1170
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.3333333333333333,
|
| 840 |
+
"grad_norm": 0.37413087487220764,
|
| 841 |
+
"learning_rate": 0.00018356643933147986,
|
| 842 |
+
"loss": 0.6382,
|
| 843 |
+
"step": 1180
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.344632768361582,
|
| 847 |
+
"grad_norm": 0.3171542286872864,
|
| 848 |
+
"learning_rate": 0.00018313052073164982,
|
| 849 |
+
"loss": 0.6373,
|
| 850 |
+
"step": 1190
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.3559322033898304,
|
| 854 |
+
"grad_norm": 0.3208696246147156,
|
| 855 |
+
"learning_rate": 0.00018268942778562494,
|
| 856 |
+
"loss": 0.6231,
|
| 857 |
+
"step": 1200
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.3672316384180792,
|
| 861 |
+
"grad_norm": 0.37951213121414185,
|
| 862 |
+
"learning_rate": 0.0001822431879486357,
|
| 863 |
+
"loss": 0.6659,
|
| 864 |
+
"step": 1210
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.3785310734463276,
|
| 868 |
+
"grad_norm": 0.3654930591583252,
|
| 869 |
+
"learning_rate": 0.00018179182899627386,
|
| 870 |
+
"loss": 0.6467,
|
| 871 |
+
"step": 1220
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.3898305084745763,
|
| 875 |
+
"grad_norm": 0.5204548239707947,
|
| 876 |
+
"learning_rate": 0.00018133537902276342,
|
| 877 |
+
"loss": 0.6479,
|
| 878 |
+
"step": 1230
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.4011299435028248,
|
| 882 |
+
"grad_norm": 0.33258357644081116,
|
| 883 |
+
"learning_rate": 0.0001808738664392122,
|
| 884 |
+
"loss": 0.613,
|
| 885 |
+
"step": 1240
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.4124293785310735,
|
| 889 |
+
"grad_norm": 0.3374476134777069,
|
| 890 |
+
"learning_rate": 0.0001804073199718432,
|
| 891 |
+
"loss": 0.6308,
|
| 892 |
+
"step": 1250
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.423728813559322,
|
| 896 |
+
"grad_norm": 0.3677334189414978,
|
| 897 |
+
"learning_rate": 0.0001799357686602068,
|
| 898 |
+
"loss": 0.6412,
|
| 899 |
+
"step": 1260
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.4350282485875705,
|
| 903 |
+
"grad_norm": 0.503189742565155,
|
| 904 |
+
"learning_rate": 0.00017945924185537295,
|
| 905 |
+
"loss": 0.6242,
|
| 906 |
+
"step": 1270
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.4463276836158192,
|
| 910 |
+
"grad_norm": 0.44822338223457336,
|
| 911 |
+
"learning_rate": 0.00017897776921810453,
|
| 912 |
+
"loss": 0.6269,
|
| 913 |
+
"step": 1280
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.457627118644068,
|
| 917 |
+
"grad_norm": 0.38298189640045166,
|
| 918 |
+
"learning_rate": 0.00017849138071701092,
|
| 919 |
+
"loss": 0.6206,
|
| 920 |
+
"step": 1290
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.4689265536723164,
|
| 924 |
+
"grad_norm": 0.40119263529777527,
|
| 925 |
+
"learning_rate": 0.0001780001066266829,
|
| 926 |
+
"loss": 0.6398,
|
| 927 |
+
"step": 1300
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.4802259887005649,
|
| 931 |
+
"grad_norm": 0.5280100703239441,
|
| 932 |
+
"learning_rate": 0.00017750397752580796,
|
| 933 |
+
"loss": 0.6299,
|
| 934 |
+
"step": 1310
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.4915254237288136,
|
| 938 |
+
"grad_norm": 0.35528528690338135,
|
| 939 |
+
"learning_rate": 0.00017700302429526723,
|
| 940 |
+
"loss": 0.6511,
|
| 941 |
+
"step": 1320
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.5028248587570623,
|
| 945 |
+
"grad_norm": 0.3741821348667145,
|
| 946 |
+
"learning_rate": 0.00017649727811621315,
|
| 947 |
+
"loss": 0.6564,
|
| 948 |
+
"step": 1330
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.5141242937853108,
|
| 952 |
+
"grad_norm": 0.5371260046958923,
|
| 953 |
+
"learning_rate": 0.0001759867704681288,
|
| 954 |
+
"loss": 0.6186,
|
| 955 |
+
"step": 1340
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.5254237288135593,
|
| 959 |
+
"grad_norm": 0.3590337336063385,
|
| 960 |
+
"learning_rate": 0.00017547153312686832,
|
| 961 |
+
"loss": 0.6372,
|
| 962 |
+
"step": 1350
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.536723163841808,
|
| 966 |
+
"grad_norm": 0.34499940276145935,
|
| 967 |
+
"learning_rate": 0.00017495159816267929,
|
| 968 |
+
"loss": 0.6442,
|
| 969 |
+
"step": 1360
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.5480225988700564,
|
| 973 |
+
"grad_norm": 0.45834365487098694,
|
| 974 |
+
"learning_rate": 0.00017442699793820631,
|
| 975 |
+
"loss": 0.6363,
|
| 976 |
+
"step": 1370
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.559322033898305,
|
| 980 |
+
"grad_norm": 0.3389630615711212,
|
| 981 |
+
"learning_rate": 0.00017389776510647688,
|
| 982 |
+
"loss": 0.6399,
|
| 983 |
+
"step": 1380
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.5706214689265536,
|
| 987 |
+
"grad_norm": 1.0764904022216797,
|
| 988 |
+
"learning_rate": 0.0001733639326088688,
|
| 989 |
+
"loss": 0.6073,
|
| 990 |
+
"step": 1390
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.5819209039548023,
|
| 994 |
+
"grad_norm": 0.32130682468414307,
|
| 995 |
+
"learning_rate": 0.00017282553367305975,
|
| 996 |
+
"loss": 0.65,
|
| 997 |
+
"step": 1400
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.5932203389830508,
|
| 1001 |
+
"grad_norm": 0.5010311603546143,
|
| 1002 |
+
"learning_rate": 0.00017228260181095925,
|
| 1003 |
+
"loss": 0.626,
|
| 1004 |
+
"step": 1410
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.6045197740112993,
|
| 1008 |
+
"grad_norm": 0.3811778128147125,
|
| 1009 |
+
"learning_rate": 0.00017173517081662255,
|
| 1010 |
+
"loss": 0.6565,
|
| 1011 |
+
"step": 1420
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.615819209039548,
|
| 1015 |
+
"grad_norm": 0.793699324131012,
|
| 1016 |
+
"learning_rate": 0.00017118327476414735,
|
| 1017 |
+
"loss": 0.6555,
|
| 1018 |
+
"step": 1430
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.6271186440677967,
|
| 1022 |
+
"grad_norm": 0.33635199069976807,
|
| 1023 |
+
"learning_rate": 0.0001706269480055528,
|
| 1024 |
+
"loss": 0.6431,
|
| 1025 |
+
"step": 1440
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.6384180790960452,
|
| 1029 |
+
"grad_norm": 0.46125972270965576,
|
| 1030 |
+
"learning_rate": 0.00017006622516864127,
|
| 1031 |
+
"loss": 0.6383,
|
| 1032 |
+
"step": 1450
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.6497175141242937,
|
| 1036 |
+
"grad_norm": 0.37351667881011963,
|
| 1037 |
+
"learning_rate": 0.00016950114115484315,
|
| 1038 |
+
"loss": 0.6304,
|
| 1039 |
+
"step": 1460
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.6610169491525424,
|
| 1043 |
+
"grad_norm": 0.35749056935310364,
|
| 1044 |
+
"learning_rate": 0.0001689317311370442,
|
| 1045 |
+
"loss": 0.6647,
|
| 1046 |
+
"step": 1470
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.672316384180791,
|
| 1050 |
+
"grad_norm": 0.3775118887424469,
|
| 1051 |
+
"learning_rate": 0.0001683580305573966,
|
| 1052 |
+
"loss": 0.6288,
|
| 1053 |
+
"step": 1480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.6836158192090396,
|
| 1057 |
+
"grad_norm": 0.3228208124637604,
|
| 1058 |
+
"learning_rate": 0.0001677800751251126,
|
| 1059 |
+
"loss": 0.6067,
|
| 1060 |
+
"step": 1490
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.694915254237288,
|
| 1064 |
+
"grad_norm": 0.38675859570503235,
|
| 1065 |
+
"learning_rate": 0.00016719790081424192,
|
| 1066 |
+
"loss": 0.6438,
|
| 1067 |
+
"step": 1500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.7062146892655368,
|
| 1071 |
+
"grad_norm": 0.3832201063632965,
|
| 1072 |
+
"learning_rate": 0.0001666115438614328,
|
| 1073 |
+
"loss": 0.6269,
|
| 1074 |
+
"step": 1510
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.7175141242937855,
|
| 1078 |
+
"grad_norm": 0.5429854989051819,
|
| 1079 |
+
"learning_rate": 0.00016602104076367624,
|
| 1080 |
+
"loss": 0.6397,
|
| 1081 |
+
"step": 1520
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.7288135593220337,
|
| 1085 |
+
"grad_norm": 0.4048645496368408,
|
| 1086 |
+
"learning_rate": 0.0001654264282760343,
|
| 1087 |
+
"loss": 0.6402,
|
| 1088 |
+
"step": 1530
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.7401129943502824,
|
| 1092 |
+
"grad_norm": 0.3748385012149811,
|
| 1093 |
+
"learning_rate": 0.00016482774340935267,
|
| 1094 |
+
"loss": 0.626,
|
| 1095 |
+
"step": 1540
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.7514124293785311,
|
| 1099 |
+
"grad_norm": 0.44016194343566895,
|
| 1100 |
+
"learning_rate": 0.00016422502342795648,
|
| 1101 |
+
"loss": 0.6542,
|
| 1102 |
+
"step": 1550
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.7627118644067796,
|
| 1106 |
+
"grad_norm": 0.34061527252197266,
|
| 1107 |
+
"learning_rate": 0.00016361830584733124,
|
| 1108 |
+
"loss": 0.6472,
|
| 1109 |
+
"step": 1560
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.774011299435028,
|
| 1113 |
+
"grad_norm": 0.3848430812358856,
|
| 1114 |
+
"learning_rate": 0.00016300762843178754,
|
| 1115 |
+
"loss": 0.6304,
|
| 1116 |
+
"step": 1570
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.7853107344632768,
|
| 1120 |
+
"grad_norm": 0.3756044805049896,
|
| 1121 |
+
"learning_rate": 0.00016239302919211052,
|
| 1122 |
+
"loss": 0.6161,
|
| 1123 |
+
"step": 1580
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.7966101694915255,
|
| 1127 |
+
"grad_norm": 0.40179935097694397,
|
| 1128 |
+
"learning_rate": 0.0001617745463831939,
|
| 1129 |
+
"loss": 0.6428,
|
| 1130 |
+
"step": 1590
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.807909604519774,
|
| 1134 |
+
"grad_norm": 0.4611279368400574,
|
| 1135 |
+
"learning_rate": 0.00016115221850165892,
|
| 1136 |
+
"loss": 0.6661,
|
| 1137 |
+
"step": 1600
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.8192090395480225,
|
| 1141 |
+
"grad_norm": 0.5279085636138916,
|
| 1142 |
+
"learning_rate": 0.0001605260842834581,
|
| 1143 |
+
"loss": 0.6293,
|
| 1144 |
+
"step": 1610
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.8305084745762712,
|
| 1148 |
+
"grad_norm": 0.5711485743522644,
|
| 1149 |
+
"learning_rate": 0.00015989618270146423,
|
| 1150 |
+
"loss": 0.6368,
|
| 1151 |
+
"step": 1620
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.84180790960452,
|
| 1155 |
+
"grad_norm": 0.37090200185775757,
|
| 1156 |
+
"learning_rate": 0.00015926255296304454,
|
| 1157 |
+
"loss": 0.6297,
|
| 1158 |
+
"step": 1630
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.8531073446327684,
|
| 1162 |
+
"grad_norm": 0.3836909830570221,
|
| 1163 |
+
"learning_rate": 0.00015862523450762032,
|
| 1164 |
+
"loss": 0.6817,
|
| 1165 |
+
"step": 1640
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.8644067796610169,
|
| 1169 |
+
"grad_norm": 0.4297361969947815,
|
| 1170 |
+
"learning_rate": 0.00015798426700421196,
|
| 1171 |
+
"loss": 0.6586,
|
| 1172 |
+
"step": 1650
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.8757062146892656,
|
| 1176 |
+
"grad_norm": 0.3696504235267639,
|
| 1177 |
+
"learning_rate": 0.0001573396903489699,
|
| 1178 |
+
"loss": 0.6466,
|
| 1179 |
+
"step": 1660
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.8870056497175143,
|
| 1183 |
+
"grad_norm": 0.39131200313568115,
|
| 1184 |
+
"learning_rate": 0.00015669154466269137,
|
| 1185 |
+
"loss": 0.6448,
|
| 1186 |
+
"step": 1670
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.8983050847457628,
|
| 1190 |
+
"grad_norm": 0.3583720624446869,
|
| 1191 |
+
"learning_rate": 0.00015603987028832303,
|
| 1192 |
+
"loss": 0.6385,
|
| 1193 |
+
"step": 1680
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.9096045197740112,
|
| 1197 |
+
"grad_norm": 0.40514451265335083,
|
| 1198 |
+
"learning_rate": 0.00015538470778844995,
|
| 1199 |
+
"loss": 0.6368,
|
| 1200 |
+
"step": 1690
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.92090395480226,
|
| 1204 |
+
"grad_norm": 0.4644288122653961,
|
| 1205 |
+
"learning_rate": 0.00015472609794277083,
|
| 1206 |
+
"loss": 0.6341,
|
| 1207 |
+
"step": 1700
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.9322033898305084,
|
| 1211 |
+
"grad_norm": 0.6364967823028564,
|
| 1212 |
+
"learning_rate": 0.00015406408174555976,
|
| 1213 |
+
"loss": 0.619,
|
| 1214 |
+
"step": 1710
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.943502824858757,
|
| 1218 |
+
"grad_norm": 0.3623166084289551,
|
| 1219 |
+
"learning_rate": 0.00015339870040311448,
|
| 1220 |
+
"loss": 0.6591,
|
| 1221 |
+
"step": 1720
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.9548022598870056,
|
| 1225 |
+
"grad_norm": 0.39671990275382996,
|
| 1226 |
+
"learning_rate": 0.00015272999533119162,
|
| 1227 |
+
"loss": 0.645,
|
| 1228 |
+
"step": 1730
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.9661016949152543,
|
| 1232 |
+
"grad_norm": 0.45107388496398926,
|
| 1233 |
+
"learning_rate": 0.0001520580081524289,
|
| 1234 |
+
"loss": 0.625,
|
| 1235 |
+
"step": 1740
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.9774011299435028,
|
| 1239 |
+
"grad_norm": 0.4473719596862793,
|
| 1240 |
+
"learning_rate": 0.00015138278069375423,
|
| 1241 |
+
"loss": 0.6481,
|
| 1242 |
+
"step": 1750
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.9887005649717513,
|
| 1246 |
+
"grad_norm": 0.390774130821228,
|
| 1247 |
+
"learning_rate": 0.00015070435498378243,
|
| 1248 |
+
"loss": 0.6482,
|
| 1249 |
+
"step": 1760
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.0,
|
| 1253 |
+
"grad_norm": 0.41401803493499756,
|
| 1254 |
+
"learning_rate": 0.00015002277325019904,
|
| 1255 |
+
"loss": 0.623,
|
| 1256 |
+
"step": 1770
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.0112994350282487,
|
| 1260 |
+
"grad_norm": 0.7757445573806763,
|
| 1261 |
+
"learning_rate": 0.00014933807791713203,
|
| 1262 |
+
"loss": 0.573,
|
| 1263 |
+
"step": 1780
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.022598870056497,
|
| 1267 |
+
"grad_norm": 0.44817861914634705,
|
| 1268 |
+
"learning_rate": 0.00014865031160251116,
|
| 1269 |
+
"loss": 0.6054,
|
| 1270 |
+
"step": 1790
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.0338983050847457,
|
| 1274 |
+
"grad_norm": 0.4326503574848175,
|
| 1275 |
+
"learning_rate": 0.0001479595171154152,
|
| 1276 |
+
"loss": 0.5724,
|
| 1277 |
+
"step": 1800
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.0451977401129944,
|
| 1281 |
+
"grad_norm": 0.4020352065563202,
|
| 1282 |
+
"learning_rate": 0.00014726573745340747,
|
| 1283 |
+
"loss": 0.5536,
|
| 1284 |
+
"step": 1810
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.056497175141243,
|
| 1288 |
+
"grad_norm": 0.3883920907974243,
|
| 1289 |
+
"learning_rate": 0.00014656901579985934,
|
| 1290 |
+
"loss": 0.5591,
|
| 1291 |
+
"step": 1820
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.0677966101694913,
|
| 1295 |
+
"grad_norm": 0.4672842025756836,
|
| 1296 |
+
"learning_rate": 0.00014586939552126255,
|
| 1297 |
+
"loss": 0.5467,
|
| 1298 |
+
"step": 1830
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.07909604519774,
|
| 1302 |
+
"grad_norm": 0.5037193894386292,
|
| 1303 |
+
"learning_rate": 0.0001451669201645298,
|
| 1304 |
+
"loss": 0.5548,
|
| 1305 |
+
"step": 1840
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.0903954802259888,
|
| 1309 |
+
"grad_norm": 0.46837809681892395,
|
| 1310 |
+
"learning_rate": 0.00014446163345428411,
|
| 1311 |
+
"loss": 0.5464,
|
| 1312 |
+
"step": 1850
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.1016949152542375,
|
| 1316 |
+
"grad_norm": 0.4075257480144501,
|
| 1317 |
+
"learning_rate": 0.00014375357929013763,
|
| 1318 |
+
"loss": 0.5658,
|
| 1319 |
+
"step": 1860
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.1129943502824857,
|
| 1323 |
+
"grad_norm": 0.5770477652549744,
|
| 1324 |
+
"learning_rate": 0.00014304280174395862,
|
| 1325 |
+
"loss": 0.5657,
|
| 1326 |
+
"step": 1870
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.1242937853107344,
|
| 1330 |
+
"grad_norm": 0.38950198888778687,
|
| 1331 |
+
"learning_rate": 0.00014232934505712877,
|
| 1332 |
+
"loss": 0.5488,
|
| 1333 |
+
"step": 1880
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.135593220338983,
|
| 1337 |
+
"grad_norm": 0.45963385701179504,
|
| 1338 |
+
"learning_rate": 0.00014161325363778914,
|
| 1339 |
+
"loss": 0.5536,
|
| 1340 |
+
"step": 1890
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.146892655367232,
|
| 1344 |
+
"grad_norm": 0.5212920904159546,
|
| 1345 |
+
"learning_rate": 0.00014089457205807614,
|
| 1346 |
+
"loss": 0.5518,
|
| 1347 |
+
"step": 1900
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.15819209039548,
|
| 1351 |
+
"grad_norm": 0.7819460034370422,
|
| 1352 |
+
"learning_rate": 0.00014017334505134722,
|
| 1353 |
+
"loss": 0.5493,
|
| 1354 |
+
"step": 1910
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.169491525423729,
|
| 1358 |
+
"grad_norm": 0.41791173815727234,
|
| 1359 |
+
"learning_rate": 0.00013944961750939644,
|
| 1360 |
+
"loss": 0.5685,
|
| 1361 |
+
"step": 1920
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.1807909604519775,
|
| 1365 |
+
"grad_norm": 0.40155965089797974,
|
| 1366 |
+
"learning_rate": 0.00013872343447966033,
|
| 1367 |
+
"loss": 0.5385,
|
| 1368 |
+
"step": 1930
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.1920903954802258,
|
| 1372 |
+
"grad_norm": 0.3540368974208832,
|
| 1373 |
+
"learning_rate": 0.00013799484116241382,
|
| 1374 |
+
"loss": 0.5601,
|
| 1375 |
+
"step": 1940
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.2033898305084745,
|
| 1379 |
+
"grad_norm": 0.45144760608673096,
|
| 1380 |
+
"learning_rate": 0.00013726388290795697,
|
| 1381 |
+
"loss": 0.5547,
|
| 1382 |
+
"step": 1950
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.214689265536723,
|
| 1386 |
+
"grad_norm": 0.4121219515800476,
|
| 1387 |
+
"learning_rate": 0.00013653060521379216,
|
| 1388 |
+
"loss": 0.5627,
|
| 1389 |
+
"step": 1960
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.225988700564972,
|
| 1393 |
+
"grad_norm": 0.5211389660835266,
|
| 1394 |
+
"learning_rate": 0.0001357950537217921,
|
| 1395 |
+
"loss": 0.5797,
|
| 1396 |
+
"step": 1970
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.23728813559322,
|
| 1400 |
+
"grad_norm": 0.5209491848945618,
|
| 1401 |
+
"learning_rate": 0.00013505727421535892,
|
| 1402 |
+
"loss": 0.5644,
|
| 1403 |
+
"step": 1980
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.248587570621469,
|
| 1407 |
+
"grad_norm": 0.40179020166397095,
|
| 1408 |
+
"learning_rate": 0.00013431731261657462,
|
| 1409 |
+
"loss": 0.5446,
|
| 1410 |
+
"step": 1990
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.2598870056497176,
|
| 1414 |
+
"grad_norm": 0.45757922530174255,
|
| 1415 |
+
"learning_rate": 0.0001335752149833424,
|
| 1416 |
+
"loss": 0.5528,
|
| 1417 |
+
"step": 2000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.2598870056497176,
|
| 1421 |
+
"eval_loss": 0.731483519077301,
|
| 1422 |
+
"eval_runtime": 16.8378,
|
| 1423 |
+
"eval_samples_per_second": 88.551,
|
| 1424 |
+
"eval_steps_per_second": 11.106,
|
| 1425 |
+
"step": 2000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.2711864406779663,
|
| 1429 |
+
"grad_norm": 0.5437088012695312,
|
| 1430 |
+
"learning_rate": 0.00013283102750652007,
|
| 1431 |
+
"loss": 0.5476,
|
| 1432 |
+
"step": 2010
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.2824858757062145,
|
| 1436 |
+
"grad_norm": 0.5207261443138123,
|
| 1437 |
+
"learning_rate": 0.00013208479650704503,
|
| 1438 |
+
"loss": 0.5839,
|
| 1439 |
+
"step": 2020
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.2937853107344632,
|
| 1443 |
+
"grad_norm": 0.47627148032188416,
|
| 1444 |
+
"learning_rate": 0.00013133656843305078,
|
| 1445 |
+
"loss": 0.5791,
|
| 1446 |
+
"step": 2030
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.305084745762712,
|
| 1450 |
+
"grad_norm": 0.4785435199737549,
|
| 1451 |
+
"learning_rate": 0.00013058638985697618,
|
| 1452 |
+
"loss": 0.5389,
|
| 1453 |
+
"step": 2040
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.3163841807909606,
|
| 1457 |
+
"grad_norm": 0.40203753113746643,
|
| 1458 |
+
"learning_rate": 0.0001298343074726663,
|
| 1459 |
+
"loss": 0.5417,
|
| 1460 |
+
"step": 2050
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.327683615819209,
|
| 1464 |
+
"grad_norm": 0.6017877459526062,
|
| 1465 |
+
"learning_rate": 0.00012908036809246623,
|
| 1466 |
+
"loss": 0.544,
|
| 1467 |
+
"step": 2060
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.3389830508474576,
|
| 1471 |
+
"grad_norm": 0.5637748837471008,
|
| 1472 |
+
"learning_rate": 0.0001283246186443073,
|
| 1473 |
+
"loss": 0.5429,
|
| 1474 |
+
"step": 2070
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.3502824858757063,
|
| 1478 |
+
"grad_norm": 0.4815099835395813,
|
| 1479 |
+
"learning_rate": 0.00012756710616878593,
|
| 1480 |
+
"loss": 0.5466,
|
| 1481 |
+
"step": 2080
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.361581920903955,
|
| 1485 |
+
"grad_norm": 0.4496362805366516,
|
| 1486 |
+
"learning_rate": 0.00012680787781623582,
|
| 1487 |
+
"loss": 0.5894,
|
| 1488 |
+
"step": 2090
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.3728813559322033,
|
| 1492 |
+
"grad_norm": 0.4290124475955963,
|
| 1493 |
+
"learning_rate": 0.00012604698084379322,
|
| 1494 |
+
"loss": 0.5504,
|
| 1495 |
+
"step": 2100
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.384180790960452,
|
| 1499 |
+
"grad_norm": 0.5070333480834961,
|
| 1500 |
+
"learning_rate": 0.00012528446261245515,
|
| 1501 |
+
"loss": 0.5522,
|
| 1502 |
+
"step": 2110
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.3954802259887007,
|
| 1506 |
+
"grad_norm": 0.5735118985176086,
|
| 1507 |
+
"learning_rate": 0.00012452037058413194,
|
| 1508 |
+
"loss": 0.5674,
|
| 1509 |
+
"step": 2120
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.406779661016949,
|
| 1513 |
+
"grad_norm": 0.40572336316108704,
|
| 1514 |
+
"learning_rate": 0.00012375475231869249,
|
| 1515 |
+
"loss": 0.5814,
|
| 1516 |
+
"step": 2130
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.4180790960451977,
|
| 1520 |
+
"grad_norm": 0.5074964165687561,
|
| 1521 |
+
"learning_rate": 0.00012298765547100445,
|
| 1522 |
+
"loss": 0.5663,
|
| 1523 |
+
"step": 2140
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.4293785310734464,
|
| 1527 |
+
"grad_norm": 0.445563942193985,
|
| 1528 |
+
"learning_rate": 0.0001222191277879678,
|
| 1529 |
+
"loss": 0.5476,
|
| 1530 |
+
"step": 2150
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.440677966101695,
|
| 1534 |
+
"grad_norm": 0.5029497742652893,
|
| 1535 |
+
"learning_rate": 0.00012144921710554278,
|
| 1536 |
+
"loss": 0.5818,
|
| 1537 |
+
"step": 2160
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.4519774011299433,
|
| 1541 |
+
"grad_norm": 0.4790378212928772,
|
| 1542 |
+
"learning_rate": 0.00012067797134577275,
|
| 1543 |
+
"loss": 0.5878,
|
| 1544 |
+
"step": 2170
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.463276836158192,
|
| 1548 |
+
"grad_norm": 0.43805941939353943,
|
| 1549 |
+
"learning_rate": 0.00011990543851380094,
|
| 1550 |
+
"loss": 0.5602,
|
| 1551 |
+
"step": 2180
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.4745762711864407,
|
| 1555 |
+
"grad_norm": 0.49226316809654236,
|
| 1556 |
+
"learning_rate": 0.00011913166669488278,
|
| 1557 |
+
"loss": 0.5692,
|
| 1558 |
+
"step": 2190
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.4858757062146895,
|
| 1562 |
+
"grad_norm": 0.44978803396224976,
|
| 1563 |
+
"learning_rate": 0.00011835670405139272,
|
| 1564 |
+
"loss": 0.5698,
|
| 1565 |
+
"step": 2200
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.4971751412429377,
|
| 1569 |
+
"grad_norm": 0.4665353000164032,
|
| 1570 |
+
"learning_rate": 0.00011758059881982639,
|
| 1571 |
+
"loss": 0.567,
|
| 1572 |
+
"step": 2210
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.5084745762711864,
|
| 1576 |
+
"grad_norm": 0.3619357943534851,
|
| 1577 |
+
"learning_rate": 0.00011680339930779843,
|
| 1578 |
+
"loss": 0.5528,
|
| 1579 |
+
"step": 2220
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.519774011299435,
|
| 1583 |
+
"grad_norm": 0.5655903220176697,
|
| 1584 |
+
"learning_rate": 0.00011602515389103529,
|
| 1585 |
+
"loss": 0.57,
|
| 1586 |
+
"step": 2230
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.5310734463276834,
|
| 1590 |
+
"grad_norm": 0.5191211700439453,
|
| 1591 |
+
"learning_rate": 0.00011524591101036446,
|
| 1592 |
+
"loss": 0.5731,
|
| 1593 |
+
"step": 2240
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.542372881355932,
|
| 1597 |
+
"grad_norm": 0.4011457562446594,
|
| 1598 |
+
"learning_rate": 0.00011446571916869917,
|
| 1599 |
+
"loss": 0.5603,
|
| 1600 |
+
"step": 2250
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.553672316384181,
|
| 1604 |
+
"grad_norm": 0.4324322044849396,
|
| 1605 |
+
"learning_rate": 0.00011368462692801944,
|
| 1606 |
+
"loss": 0.5508,
|
| 1607 |
+
"step": 2260
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.5649717514124295,
|
| 1611 |
+
"grad_norm": 0.44678226113319397,
|
| 1612 |
+
"learning_rate": 0.00011290268290634943,
|
| 1613 |
+
"loss": 0.5695,
|
| 1614 |
+
"step": 2270
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.576271186440678,
|
| 1618 |
+
"grad_norm": 0.7076367139816284,
|
| 1619 |
+
"learning_rate": 0.00011211993577473121,
|
| 1620 |
+
"loss": 0.5812,
|
| 1621 |
+
"step": 2280
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.5875706214689265,
|
| 1625 |
+
"grad_norm": 0.36905479431152344,
|
| 1626 |
+
"learning_rate": 0.00011133643425419531,
|
| 1627 |
+
"loss": 0.5775,
|
| 1628 |
+
"step": 2290
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 2.598870056497175,
|
| 1632 |
+
"grad_norm": 0.4640151560306549,
|
| 1633 |
+
"learning_rate": 0.0001105522271127283,
|
| 1634 |
+
"loss": 0.5932,
|
| 1635 |
+
"step": 2300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 2.610169491525424,
|
| 1639 |
+
"grad_norm": 0.541059672832489,
|
| 1640 |
+
"learning_rate": 0.00010976736316223698,
|
| 1641 |
+
"loss": 0.5803,
|
| 1642 |
+
"step": 2310
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.621468926553672,
|
| 1646 |
+
"grad_norm": 0.46233227849006653,
|
| 1647 |
+
"learning_rate": 0.00010898189125551052,
|
| 1648 |
+
"loss": 0.5939,
|
| 1649 |
+
"step": 2320
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.632768361581921,
|
| 1653 |
+
"grad_norm": 0.49569135904312134,
|
| 1654 |
+
"learning_rate": 0.0001081958602831794,
|
| 1655 |
+
"loss": 0.5762,
|
| 1656 |
+
"step": 2330
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.6440677966101696,
|
| 1660 |
+
"grad_norm": 0.46241089701652527,
|
| 1661 |
+
"learning_rate": 0.00010740931917067231,
|
| 1662 |
+
"loss": 0.5455,
|
| 1663 |
+
"step": 2340
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 2.655367231638418,
|
| 1667 |
+
"grad_norm": 0.4825233221054077,
|
| 1668 |
+
"learning_rate": 0.00010662231687517112,
|
| 1669 |
+
"loss": 0.5697,
|
| 1670 |
+
"step": 2350
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 2.6666666666666665,
|
| 1674 |
+
"grad_norm": 0.3972626328468323,
|
| 1675 |
+
"learning_rate": 0.00010583490238256322,
|
| 1676 |
+
"loss": 0.5544,
|
| 1677 |
+
"step": 2360
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 2.6779661016949152,
|
| 1681 |
+
"grad_norm": 0.458835244178772,
|
| 1682 |
+
"learning_rate": 0.00010504712470439266,
|
| 1683 |
+
"loss": 0.5603,
|
| 1684 |
+
"step": 2370
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 2.689265536723164,
|
| 1688 |
+
"grad_norm": 0.5480552911758423,
|
| 1689 |
+
"learning_rate": 0.00010425903287480969,
|
| 1690 |
+
"loss": 0.5555,
|
| 1691 |
+
"step": 2380
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 2.7005649717514126,
|
| 1695 |
+
"grad_norm": 0.5089293122291565,
|
| 1696 |
+
"learning_rate": 0.0001034706759475182,
|
| 1697 |
+
"loss": 0.5374,
|
| 1698 |
+
"step": 2390
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 2.711864406779661,
|
| 1702 |
+
"grad_norm": 0.39211511611938477,
|
| 1703 |
+
"learning_rate": 0.00010268210299272294,
|
| 1704 |
+
"loss": 0.5499,
|
| 1705 |
+
"step": 2400
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 2.7231638418079096,
|
| 1709 |
+
"grad_norm": 0.4466584324836731,
|
| 1710 |
+
"learning_rate": 0.00010189336309407492,
|
| 1711 |
+
"loss": 0.5692,
|
| 1712 |
+
"step": 2410
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 2.7344632768361583,
|
| 1716 |
+
"grad_norm": 0.4684606194496155,
|
| 1717 |
+
"learning_rate": 0.00010110450534561629,
|
| 1718 |
+
"loss": 0.5858,
|
| 1719 |
+
"step": 2420
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 2.7457627118644066,
|
| 1723 |
+
"grad_norm": 0.4925701320171356,
|
| 1724 |
+
"learning_rate": 0.00010031557884872471,
|
| 1725 |
+
"loss": 0.5577,
|
| 1726 |
+
"step": 2430
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.7570621468926553,
|
| 1730 |
+
"grad_norm": 0.5621470212936401,
|
| 1731 |
+
"learning_rate": 9.952663270905691e-05,
|
| 1732 |
+
"loss": 0.543,
|
| 1733 |
+
"step": 2440
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 2.768361581920904,
|
| 1737 |
+
"grad_norm": 0.5334658622741699,
|
| 1738 |
+
"learning_rate": 9.873771603349229e-05,
|
| 1739 |
+
"loss": 0.5673,
|
| 1740 |
+
"step": 2450
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.7796610169491527,
|
| 1744 |
+
"grad_norm": 0.4116109311580658,
|
| 1745 |
+
"learning_rate": 9.79488779270763e-05,
|
| 1746 |
+
"loss": 0.5759,
|
| 1747 |
+
"step": 2460
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.7909604519774014,
|
| 1751 |
+
"grad_norm": 0.579428493976593,
|
| 1752 |
+
"learning_rate": 9.716016748996397e-05,
|
| 1753 |
+
"loss": 0.5804,
|
| 1754 |
+
"step": 2470
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.8022598870056497,
|
| 1758 |
+
"grad_norm": 0.6294684410095215,
|
| 1759 |
+
"learning_rate": 9.637163381436368e-05,
|
| 1760 |
+
"loss": 0.573,
|
| 1761 |
+
"step": 2480
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 2.8135593220338984,
|
| 1765 |
+
"grad_norm": 0.4215356409549713,
|
| 1766 |
+
"learning_rate": 9.558332598148156e-05,
|
| 1767 |
+
"loss": 0.5702,
|
| 1768 |
+
"step": 2490
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 2.824858757062147,
|
| 1772 |
+
"grad_norm": 0.6607437133789062,
|
| 1773 |
+
"learning_rate": 9.479529305846652e-05,
|
| 1774 |
+
"loss": 0.5556,
|
| 1775 |
+
"step": 2500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.8361581920903953,
|
| 1779 |
+
"grad_norm": 0.4144829213619232,
|
| 1780 |
+
"learning_rate": 9.400758409535597e-05,
|
| 1781 |
+
"loss": 0.5417,
|
| 1782 |
+
"step": 2510
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 2.847457627118644,
|
| 1786 |
+
"grad_norm": 0.47953999042510986,
|
| 1787 |
+
"learning_rate": 9.322024812202295e-05,
|
| 1788 |
+
"loss": 0.5531,
|
| 1789 |
+
"step": 2520
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 2.8587570621468927,
|
| 1793 |
+
"grad_norm": 0.4800129532814026,
|
| 1794 |
+
"learning_rate": 9.243333414512428e-05,
|
| 1795 |
+
"loss": 0.5692,
|
| 1796 |
+
"step": 2530
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 2.870056497175141,
|
| 1800 |
+
"grad_norm": 0.6145460605621338,
|
| 1801 |
+
"learning_rate": 9.164689114505007e-05,
|
| 1802 |
+
"loss": 0.556,
|
| 1803 |
+
"step": 2540
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 2.8813559322033897,
|
| 1807 |
+
"grad_norm": 0.45880794525146484,
|
| 1808 |
+
"learning_rate": 9.086096807287525e-05,
|
| 1809 |
+
"loss": 0.547,
|
| 1810 |
+
"step": 2550
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.8926553672316384,
|
| 1814 |
+
"grad_norm": 0.4852420389652252,
|
| 1815 |
+
"learning_rate": 9.007561384731249e-05,
|
| 1816 |
+
"loss": 0.5843,
|
| 1817 |
+
"step": 2560
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.903954802259887,
|
| 1821 |
+
"grad_norm": 0.4079766571521759,
|
| 1822 |
+
"learning_rate": 8.929087735166738e-05,
|
| 1823 |
+
"loss": 0.5642,
|
| 1824 |
+
"step": 2570
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 2.915254237288136,
|
| 1828 |
+
"grad_norm": 0.41701099276542664,
|
| 1829 |
+
"learning_rate": 8.850680743079576e-05,
|
| 1830 |
+
"loss": 0.5191,
|
| 1831 |
+
"step": 2580
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 2.926553672316384,
|
| 1835 |
+
"grad_norm": 0.51291823387146,
|
| 1836 |
+
"learning_rate": 8.772345288806338e-05,
|
| 1837 |
+
"loss": 0.5823,
|
| 1838 |
+
"step": 2590
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 2.937853107344633,
|
| 1842 |
+
"grad_norm": 0.3969896137714386,
|
| 1843 |
+
"learning_rate": 8.694086248230836e-05,
|
| 1844 |
+
"loss": 0.5673,
|
| 1845 |
+
"step": 2600
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 2.9491525423728815,
|
| 1849 |
+
"grad_norm": 0.5091503858566284,
|
| 1850 |
+
"learning_rate": 8.615908492480598e-05,
|
| 1851 |
+
"loss": 0.5555,
|
| 1852 |
+
"step": 2610
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 2.9604519774011298,
|
| 1856 |
+
"grad_norm": 0.5286157131195068,
|
| 1857 |
+
"learning_rate": 8.537816887623706e-05,
|
| 1858 |
+
"loss": 0.5883,
|
| 1859 |
+
"step": 2620
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.9717514124293785,
|
| 1863 |
+
"grad_norm": 0.42479345202445984,
|
| 1864 |
+
"learning_rate": 8.459816294365892e-05,
|
| 1865 |
+
"loss": 0.6002,
|
| 1866 |
+
"step": 2630
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 2.983050847457627,
|
| 1870 |
+
"grad_norm": 0.6383501291275024,
|
| 1871 |
+
"learning_rate": 8.381911567747986e-05,
|
| 1872 |
+
"loss": 0.5751,
|
| 1873 |
+
"step": 2640
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 2.994350282485876,
|
| 1877 |
+
"grad_norm": 0.4221038520336151,
|
| 1878 |
+
"learning_rate": 8.304107556843739e-05,
|
| 1879 |
+
"loss": 0.5583,
|
| 1880 |
+
"step": 2650
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 3.005649717514124,
|
| 1884 |
+
"grad_norm": 0.46783480048179626,
|
| 1885 |
+
"learning_rate": 8.22640910445799e-05,
|
| 1886 |
+
"loss": 0.5075,
|
| 1887 |
+
"step": 2660
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 3.016949152542373,
|
| 1891 |
+
"grad_norm": 0.48267218470573425,
|
| 1892 |
+
"learning_rate": 8.14882104682522e-05,
|
| 1893 |
+
"loss": 0.4768,
|
| 1894 |
+
"step": 2670
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 3.0282485875706215,
|
| 1898 |
+
"grad_norm": 0.3863345682621002,
|
| 1899 |
+
"learning_rate": 8.07134821330855e-05,
|
| 1900 |
+
"loss": 0.4959,
|
| 1901 |
+
"step": 2680
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 3.0395480225988702,
|
| 1905 |
+
"grad_norm": 0.5208786129951477,
|
| 1906 |
+
"learning_rate": 7.993995426099132e-05,
|
| 1907 |
+
"loss": 0.4765,
|
| 1908 |
+
"step": 2690
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 3.0508474576271185,
|
| 1912 |
+
"grad_norm": 0.4619675874710083,
|
| 1913 |
+
"learning_rate": 7.916767499915998e-05,
|
| 1914 |
+
"loss": 0.4615,
|
| 1915 |
+
"step": 2700
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 3.062146892655367,
|
| 1919 |
+
"grad_norm": 0.4720297157764435,
|
| 1920 |
+
"learning_rate": 7.839669241706368e-05,
|
| 1921 |
+
"loss": 0.495,
|
| 1922 |
+
"step": 2710
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 3.073446327683616,
|
| 1926 |
+
"grad_norm": 0.5332727432250977,
|
| 1927 |
+
"learning_rate": 7.762705450346462e-05,
|
| 1928 |
+
"loss": 0.486,
|
| 1929 |
+
"step": 2720
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 3.084745762711864,
|
| 1933 |
+
"grad_norm": 0.5170637965202332,
|
| 1934 |
+
"learning_rate": 7.685880916342795e-05,
|
| 1935 |
+
"loss": 0.4816,
|
| 1936 |
+
"step": 2730
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 3.096045197740113,
|
| 1940 |
+
"grad_norm": 0.47557196021080017,
|
| 1941 |
+
"learning_rate": 7.609200421533991e-05,
|
| 1942 |
+
"loss": 0.4706,
|
| 1943 |
+
"step": 2740
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 3.1073446327683616,
|
| 1947 |
+
"grad_norm": 0.7031615376472473,
|
| 1948 |
+
"learning_rate": 7.532668738793159e-05,
|
| 1949 |
+
"loss": 0.479,
|
| 1950 |
+
"step": 2750
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 3.1186440677966103,
|
| 1954 |
+
"grad_norm": 0.4733956456184387,
|
| 1955 |
+
"learning_rate": 7.456290631730795e-05,
|
| 1956 |
+
"loss": 0.5023,
|
| 1957 |
+
"step": 2760
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 3.1299435028248586,
|
| 1961 |
+
"grad_norm": 0.5425024032592773,
|
| 1962 |
+
"learning_rate": 7.380070854398292e-05,
|
| 1963 |
+
"loss": 0.477,
|
| 1964 |
+
"step": 2770
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 3.1412429378531073,
|
| 1968 |
+
"grad_norm": 0.4106122851371765,
|
| 1969 |
+
"learning_rate": 7.304014150992016e-05,
|
| 1970 |
+
"loss": 0.511,
|
| 1971 |
+
"step": 2780
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 3.152542372881356,
|
| 1975 |
+
"grad_norm": 0.580517053604126,
|
| 1976 |
+
"learning_rate": 7.228125255558026e-05,
|
| 1977 |
+
"loss": 0.4797,
|
| 1978 |
+
"step": 2790
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 3.1638418079096047,
|
| 1982 |
+
"grad_norm": 0.6407458186149597,
|
| 1983 |
+
"learning_rate": 7.152408891697406e-05,
|
| 1984 |
+
"loss": 0.4908,
|
| 1985 |
+
"step": 2800
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 3.175141242937853,
|
| 1989 |
+
"grad_norm": 0.6218848824501038,
|
| 1990 |
+
"learning_rate": 7.076869772272231e-05,
|
| 1991 |
+
"loss": 0.4944,
|
| 1992 |
+
"step": 2810
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 3.1864406779661016,
|
| 1996 |
+
"grad_norm": 0.49968206882476807,
|
| 1997 |
+
"learning_rate": 7.001512599112254e-05,
|
| 1998 |
+
"loss": 0.4764,
|
| 1999 |
+
"step": 2820
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 3.1977401129943503,
|
| 2003 |
+
"grad_norm": 0.465017706155777,
|
| 2004 |
+
"learning_rate": 6.926342062722223e-05,
|
| 2005 |
+
"loss": 0.4917,
|
| 2006 |
+
"step": 2830
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 3.209039548022599,
|
| 2010 |
+
"grad_norm": 0.49751996994018555,
|
| 2011 |
+
"learning_rate": 6.851362841989926e-05,
|
| 2012 |
+
"loss": 0.5105,
|
| 2013 |
+
"step": 2840
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 3.2203389830508473,
|
| 2017 |
+
"grad_norm": 0.5394355654716492,
|
| 2018 |
+
"learning_rate": 6.776579603894983e-05,
|
| 2019 |
+
"loss": 0.4888,
|
| 2020 |
+
"step": 2850
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 3.231638418079096,
|
| 2024 |
+
"grad_norm": 0.628495454788208,
|
| 2025 |
+
"learning_rate": 6.701997003218334e-05,
|
| 2026 |
+
"loss": 0.4597,
|
| 2027 |
+
"step": 2860
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 3.2429378531073447,
|
| 2031 |
+
"grad_norm": 0.544737696647644,
|
| 2032 |
+
"learning_rate": 6.627619682252514e-05,
|
| 2033 |
+
"loss": 0.5198,
|
| 2034 |
+
"step": 2870
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 3.2542372881355934,
|
| 2038 |
+
"grad_norm": 0.3959389626979828,
|
| 2039 |
+
"learning_rate": 6.553452270512708e-05,
|
| 2040 |
+
"loss": 0.4881,
|
| 2041 |
+
"step": 2880
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 3.2655367231638417,
|
| 2045 |
+
"grad_norm": 0.7966346740722656,
|
| 2046 |
+
"learning_rate": 6.47949938444858e-05,
|
| 2047 |
+
"loss": 0.4839,
|
| 2048 |
+
"step": 2890
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 3.2768361581920904,
|
| 2052 |
+
"grad_norm": 0.5471003651618958,
|
| 2053 |
+
"learning_rate": 6.405765627156934e-05,
|
| 2054 |
+
"loss": 0.4953,
|
| 2055 |
+
"step": 2900
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 3.288135593220339,
|
| 2059 |
+
"grad_norm": 0.6175327301025391,
|
| 2060 |
+
"learning_rate": 6.332255588095211e-05,
|
| 2061 |
+
"loss": 0.4936,
|
| 2062 |
+
"step": 2910
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 3.2994350282485874,
|
| 2066 |
+
"grad_norm": 0.5062096118927002,
|
| 2067 |
+
"learning_rate": 6.258973842795803e-05,
|
| 2068 |
+
"loss": 0.4927,
|
| 2069 |
+
"step": 2920
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 3.310734463276836,
|
| 2073 |
+
"grad_norm": 0.5980800986289978,
|
| 2074 |
+
"learning_rate": 6.185924952581286e-05,
|
| 2075 |
+
"loss": 0.4908,
|
| 2076 |
+
"step": 2930
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 3.3220338983050848,
|
| 2080 |
+
"grad_norm": 0.47181573510169983,
|
| 2081 |
+
"learning_rate": 6.11311346428046e-05,
|
| 2082 |
+
"loss": 0.4938,
|
| 2083 |
+
"step": 2940
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 3.3333333333333335,
|
| 2087 |
+
"grad_norm": 0.4729149341583252,
|
| 2088 |
+
"learning_rate": 6.040543909945393e-05,
|
| 2089 |
+
"loss": 0.4795,
|
| 2090 |
+
"step": 2950
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 3.3446327683615817,
|
| 2094 |
+
"grad_norm": 0.4721032977104187,
|
| 2095 |
+
"learning_rate": 5.968220806569289e-05,
|
| 2096 |
+
"loss": 0.4821,
|
| 2097 |
+
"step": 2960
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 3.3559322033898304,
|
| 2101 |
+
"grad_norm": 0.49077048897743225,
|
| 2102 |
+
"learning_rate": 5.89614865580534e-05,
|
| 2103 |
+
"loss": 0.4765,
|
| 2104 |
+
"step": 2970
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 3.367231638418079,
|
| 2108 |
+
"grad_norm": 0.4721141755580902,
|
| 2109 |
+
"learning_rate": 5.8243319436865554e-05,
|
| 2110 |
+
"loss": 0.4622,
|
| 2111 |
+
"step": 2980
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 3.378531073446328,
|
| 2115 |
+
"grad_norm": 0.5188248157501221,
|
| 2116 |
+
"learning_rate": 5.7527751403464935e-05,
|
| 2117 |
+
"loss": 0.4966,
|
| 2118 |
+
"step": 2990
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 3.389830508474576,
|
| 2122 |
+
"grad_norm": 0.5185617208480835,
|
| 2123 |
+
"learning_rate": 5.681482699741052e-05,
|
| 2124 |
+
"loss": 0.4847,
|
| 2125 |
+
"step": 3000
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 3.389830508474576,
|
| 2129 |
+
"eval_loss": 0.7709711194038391,
|
| 2130 |
+
"eval_runtime": 16.7631,
|
| 2131 |
+
"eval_samples_per_second": 88.945,
|
| 2132 |
+
"eval_steps_per_second": 11.155,
|
| 2133 |
+
"step": 3000
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 3.401129943502825,
|
| 2137 |
+
"grad_norm": 0.44520846009254456,
|
| 2138 |
+
"learning_rate": 5.610459059371229e-05,
|
| 2139 |
+
"loss": 0.4904,
|
| 2140 |
+
"step": 3010
|
| 2141 |
+
},
|
| 2142 |
+
{
|
| 2143 |
+
"epoch": 3.4124293785310735,
|
| 2144 |
+
"grad_norm": 0.4945251941680908,
|
| 2145 |
+
"learning_rate": 5.53970864000693e-05,
|
| 2146 |
+
"loss": 0.486,
|
| 2147 |
+
"step": 3020
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 3.423728813559322,
|
| 2151 |
+
"grad_norm": 0.45569783449172974,
|
| 2152 |
+
"learning_rate": 5.4692358454117596e-05,
|
| 2153 |
+
"loss": 0.485,
|
| 2154 |
+
"step": 3030
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 3.4350282485875705,
|
| 2158 |
+
"grad_norm": 0.6237002015113831,
|
| 2159 |
+
"learning_rate": 5.399045062068977e-05,
|
| 2160 |
+
"loss": 0.5055,
|
| 2161 |
+
"step": 3040
|
| 2162 |
+
},
|
| 2163 |
+
{
|
| 2164 |
+
"epoch": 3.446327683615819,
|
| 2165 |
+
"grad_norm": 0.4695291519165039,
|
| 2166 |
+
"learning_rate": 5.329140658908423e-05,
|
| 2167 |
+
"loss": 0.5047,
|
| 2168 |
+
"step": 3050
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 3.457627118644068,
|
| 2172 |
+
"grad_norm": 0.5210557579994202,
|
| 2173 |
+
"learning_rate": 5.259526987034593e-05,
|
| 2174 |
+
"loss": 0.5181,
|
| 2175 |
+
"step": 3060
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 3.4689265536723166,
|
| 2179 |
+
"grad_norm": 0.5110927224159241,
|
| 2180 |
+
"learning_rate": 5.190208379455802e-05,
|
| 2181 |
+
"loss": 0.4901,
|
| 2182 |
+
"step": 3070
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 3.480225988700565,
|
| 2186 |
+
"grad_norm": 0.5741479396820068,
|
| 2187 |
+
"learning_rate": 5.121189150814507e-05,
|
| 2188 |
+
"loss": 0.4919,
|
| 2189 |
+
"step": 3080
|
| 2190 |
+
},
|
| 2191 |
+
{
|
| 2192 |
+
"epoch": 3.4915254237288136,
|
| 2193 |
+
"grad_norm": 0.49151936173439026,
|
| 2194 |
+
"learning_rate": 5.052473597118715e-05,
|
| 2195 |
+
"loss": 0.4954,
|
| 2196 |
+
"step": 3090
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 3.5028248587570623,
|
| 2200 |
+
"grad_norm": 0.5301800966262817,
|
| 2201 |
+
"learning_rate": 4.984065995474601e-05,
|
| 2202 |
+
"loss": 0.4966,
|
| 2203 |
+
"step": 3100
|
| 2204 |
+
},
|
| 2205 |
+
{
|
| 2206 |
+
"epoch": 3.5141242937853105,
|
| 2207 |
+
"grad_norm": 0.5711139440536499,
|
| 2208 |
+
"learning_rate": 4.915970603820293e-05,
|
| 2209 |
+
"loss": 0.4907,
|
| 2210 |
+
"step": 3110
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 3.5254237288135593,
|
| 2214 |
+
"grad_norm": 0.6174890995025635,
|
| 2215 |
+
"learning_rate": 4.84819166066082e-05,
|
| 2216 |
+
"loss": 0.4957,
|
| 2217 |
+
"step": 3120
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 3.536723163841808,
|
| 2221 |
+
"grad_norm": 0.5370630621910095,
|
| 2222 |
+
"learning_rate": 4.780733384804312e-05,
|
| 2223 |
+
"loss": 0.5131,
|
| 2224 |
+
"step": 3130
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 3.548022598870056,
|
| 2228 |
+
"grad_norm": 0.4994024634361267,
|
| 2229 |
+
"learning_rate": 4.713599975099399e-05,
|
| 2230 |
+
"loss": 0.5214,
|
| 2231 |
+
"step": 3140
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 3.559322033898305,
|
| 2235 |
+
"grad_norm": 0.8335681557655334,
|
| 2236 |
+
"learning_rate": 4.646795610173864e-05,
|
| 2237 |
+
"loss": 0.498,
|
| 2238 |
+
"step": 3150
|
| 2239 |
+
},
|
| 2240 |
+
{
|
| 2241 |
+
"epoch": 3.5706214689265536,
|
| 2242 |
+
"grad_norm": 0.5772273540496826,
|
| 2243 |
+
"learning_rate": 4.5803244481745275e-05,
|
| 2244 |
+
"loss": 0.4889,
|
| 2245 |
+
"step": 3160
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 3.5819209039548023,
|
| 2249 |
+
"grad_norm": 0.725974977016449,
|
| 2250 |
+
"learning_rate": 4.514190626508465e-05,
|
| 2251 |
+
"loss": 0.4889,
|
| 2252 |
+
"step": 3170
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 3.593220338983051,
|
| 2256 |
+
"grad_norm": 0.4802244305610657,
|
| 2257 |
+
"learning_rate": 4.448398261585459e-05,
|
| 2258 |
+
"loss": 0.4688,
|
| 2259 |
+
"step": 3180
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 3.6045197740112993,
|
| 2263 |
+
"grad_norm": 1.078092098236084,
|
| 2264 |
+
"learning_rate": 4.3829514485617754e-05,
|
| 2265 |
+
"loss": 0.4719,
|
| 2266 |
+
"step": 3190
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 3.615819209039548,
|
| 2270 |
+
"grad_norm": 0.5553079843521118,
|
| 2271 |
+
"learning_rate": 4.31785426108527e-05,
|
| 2272 |
+
"loss": 0.4816,
|
| 2273 |
+
"step": 3200
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 3.6271186440677967,
|
| 2277 |
+
"grad_norm": 0.48087623715400696,
|
| 2278 |
+
"learning_rate": 4.253110751041846e-05,
|
| 2279 |
+
"loss": 0.4894,
|
| 2280 |
+
"step": 3210
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 3.638418079096045,
|
| 2284 |
+
"grad_norm": 0.6121565103530884,
|
| 2285 |
+
"learning_rate": 4.1887249483032195e-05,
|
| 2286 |
+
"loss": 0.4978,
|
| 2287 |
+
"step": 3220
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 3.6497175141242937,
|
| 2291 |
+
"grad_norm": 0.616296648979187,
|
| 2292 |
+
"learning_rate": 4.1247008604761096e-05,
|
| 2293 |
+
"loss": 0.4834,
|
| 2294 |
+
"step": 3230
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 3.6610169491525424,
|
| 2298 |
+
"grad_norm": 0.5769548416137695,
|
| 2299 |
+
"learning_rate": 4.061042472652786e-05,
|
| 2300 |
+
"loss": 0.5177,
|
| 2301 |
+
"step": 3240
|
| 2302 |
+
},
|
| 2303 |
+
{
|
| 2304 |
+
"epoch": 3.672316384180791,
|
| 2305 |
+
"grad_norm": 0.5508149862289429,
|
| 2306 |
+
"learning_rate": 3.997753747163014e-05,
|
| 2307 |
+
"loss": 0.5206,
|
| 2308 |
+
"step": 3250
|
| 2309 |
+
},
|
| 2310 |
+
{
|
| 2311 |
+
"epoch": 3.68361581920904,
|
| 2312 |
+
"grad_norm": 0.4783056080341339,
|
| 2313 |
+
"learning_rate": 3.934838623327427e-05,
|
| 2314 |
+
"loss": 0.4996,
|
| 2315 |
+
"step": 3260
|
| 2316 |
+
},
|
| 2317 |
+
{
|
| 2318 |
+
"epoch": 3.694915254237288,
|
| 2319 |
+
"grad_norm": 0.9651548266410828,
|
| 2320 |
+
"learning_rate": 3.872301017212337e-05,
|
| 2321 |
+
"loss": 0.4741,
|
| 2322 |
+
"step": 3270
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 3.7062146892655368,
|
| 2326 |
+
"grad_norm": 0.5215980410575867,
|
| 2327 |
+
"learning_rate": 3.8101448213859846e-05,
|
| 2328 |
+
"loss": 0.4757,
|
| 2329 |
+
"step": 3280
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 3.7175141242937855,
|
| 2333 |
+
"grad_norm": 0.4626060724258423,
|
| 2334 |
+
"learning_rate": 3.7483739046762326e-05,
|
| 2335 |
+
"loss": 0.4887,
|
| 2336 |
+
"step": 3290
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 3.7288135593220337,
|
| 2340 |
+
"grad_norm": 0.5218005180358887,
|
| 2341 |
+
"learning_rate": 3.6869921119297714e-05,
|
| 2342 |
+
"loss": 0.4603,
|
| 2343 |
+
"step": 3300
|
| 2344 |
+
},
|
| 2345 |
+
{
|
| 2346 |
+
"epoch": 3.7401129943502824,
|
| 2347 |
+
"grad_norm": 0.557963490486145,
|
| 2348 |
+
"learning_rate": 3.626003263772813e-05,
|
| 2349 |
+
"loss": 0.5009,
|
| 2350 |
+
"step": 3310
|
| 2351 |
+
},
|
| 2352 |
+
{
|
| 2353 |
+
"epoch": 3.751412429378531,
|
| 2354 |
+
"grad_norm": 0.7049193382263184,
|
| 2355 |
+
"learning_rate": 3.565411156373252e-05,
|
| 2356 |
+
"loss": 0.4982,
|
| 2357 |
+
"step": 3320
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 3.7627118644067794,
|
| 2361 |
+
"grad_norm": 0.5267760753631592,
|
| 2362 |
+
"learning_rate": 3.505219561204398e-05,
|
| 2363 |
+
"loss": 0.4716,
|
| 2364 |
+
"step": 3330
|
| 2365 |
+
},
|
| 2366 |
+
{
|
| 2367 |
+
"epoch": 3.774011299435028,
|
| 2368 |
+
"grad_norm": 0.5169788002967834,
|
| 2369 |
+
"learning_rate": 3.445432224810232e-05,
|
| 2370 |
+
"loss": 0.4992,
|
| 2371 |
+
"step": 3340
|
| 2372 |
+
},
|
| 2373 |
+
{
|
| 2374 |
+
"epoch": 3.785310734463277,
|
| 2375 |
+
"grad_norm": 0.5268625020980835,
|
| 2376 |
+
"learning_rate": 3.386052868572186e-05,
|
| 2377 |
+
"loss": 0.5063,
|
| 2378 |
+
"step": 3350
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 3.7966101694915255,
|
| 2382 |
+
"grad_norm": 0.5163342356681824,
|
| 2383 |
+
"learning_rate": 3.3270851884775203e-05,
|
| 2384 |
+
"loss": 0.5045,
|
| 2385 |
+
"step": 3360
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 3.8079096045197742,
|
| 2389 |
+
"grad_norm": 0.6581404805183411,
|
| 2390 |
+
"learning_rate": 3.268532854889287e-05,
|
| 2391 |
+
"loss": 0.4818,
|
| 2392 |
+
"step": 3370
|
| 2393 |
+
},
|
| 2394 |
+
{
|
| 2395 |
+
"epoch": 3.8192090395480225,
|
| 2396 |
+
"grad_norm": 0.5500733256340027,
|
| 2397 |
+
"learning_rate": 3.210399512317849e-05,
|
| 2398 |
+
"loss": 0.5064,
|
| 2399 |
+
"step": 3380
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 3.830508474576271,
|
| 2403 |
+
"grad_norm": 0.530192494392395,
|
| 2404 |
+
"learning_rate": 3.1526887791940395e-05,
|
| 2405 |
+
"loss": 0.4761,
|
| 2406 |
+
"step": 3390
|
| 2407 |
+
},
|
| 2408 |
+
{
|
| 2409 |
+
"epoch": 3.84180790960452,
|
| 2410 |
+
"grad_norm": 0.5225520133972168,
|
| 2411 |
+
"learning_rate": 3.095404247643955e-05,
|
| 2412 |
+
"loss": 0.4874,
|
| 2413 |
+
"step": 3400
|
| 2414 |
+
},
|
| 2415 |
+
{
|
| 2416 |
+
"epoch": 3.853107344632768,
|
| 2417 |
+
"grad_norm": 0.52415531873703,
|
| 2418 |
+
"learning_rate": 3.038549483265348e-05,
|
| 2419 |
+
"loss": 0.4748,
|
| 2420 |
+
"step": 3410
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 3.864406779661017,
|
| 2424 |
+
"grad_norm": 0.6530227661132812,
|
| 2425 |
+
"learning_rate": 2.982128024905697e-05,
|
| 2426 |
+
"loss": 0.4841,
|
| 2427 |
+
"step": 3420
|
| 2428 |
+
},
|
| 2429 |
+
{
|
| 2430 |
+
"epoch": 3.8757062146892656,
|
| 2431 |
+
"grad_norm": 0.5648587346076965,
|
| 2432 |
+
"learning_rate": 2.9261433844419306e-05,
|
| 2433 |
+
"loss": 0.4687,
|
| 2434 |
+
"step": 3430
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 3.8870056497175143,
|
| 2438 |
+
"grad_norm": 0.957992672920227,
|
| 2439 |
+
"learning_rate": 2.870599046561858e-05,
|
| 2440 |
+
"loss": 0.489,
|
| 2441 |
+
"step": 3440
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 3.898305084745763,
|
| 2445 |
+
"grad_norm": 0.5714943408966064,
|
| 2446 |
+
"learning_rate": 2.8154984685472373e-05,
|
| 2447 |
+
"loss": 0.4886,
|
| 2448 |
+
"step": 3450
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 3.9096045197740112,
|
| 2452 |
+
"grad_norm": 0.48912012577056885,
|
| 2453 |
+
"learning_rate": 2.7608450800586016e-05,
|
| 2454 |
+
"loss": 0.5028,
|
| 2455 |
+
"step": 3460
|
| 2456 |
+
},
|
| 2457 |
+
{
|
| 2458 |
+
"epoch": 3.92090395480226,
|
| 2459 |
+
"grad_norm": 0.5882663726806641,
|
| 2460 |
+
"learning_rate": 2.7066422829217875e-05,
|
| 2461 |
+
"loss": 0.5216,
|
| 2462 |
+
"step": 3470
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 3.9322033898305087,
|
| 2466 |
+
"grad_norm": 0.5730474591255188,
|
| 2467 |
+
"learning_rate": 2.6528934509161763e-05,
|
| 2468 |
+
"loss": 0.4596,
|
| 2469 |
+
"step": 3480
|
| 2470 |
+
},
|
| 2471 |
+
{
|
| 2472 |
+
"epoch": 3.943502824858757,
|
| 2473 |
+
"grad_norm": 0.6839239001274109,
|
| 2474 |
+
"learning_rate": 2.599601929564709e-05,
|
| 2475 |
+
"loss": 0.4944,
|
| 2476 |
+
"step": 3490
|
| 2477 |
+
},
|
| 2478 |
+
{
|
| 2479 |
+
"epoch": 3.9548022598870056,
|
| 2480 |
+
"grad_norm": 0.5317196249961853,
|
| 2481 |
+
"learning_rate": 2.5467710359256557e-05,
|
| 2482 |
+
"loss": 0.4779,
|
| 2483 |
+
"step": 3500
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 3.9661016949152543,
|
| 2487 |
+
"grad_norm": 0.5707146525382996,
|
| 2488 |
+
"learning_rate": 2.4944040583861284e-05,
|
| 2489 |
+
"loss": 0.4878,
|
| 2490 |
+
"step": 3510
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 3.9774011299435026,
|
| 2494 |
+
"grad_norm": 0.781765341758728,
|
| 2495 |
+
"learning_rate": 2.4425042564574184e-05,
|
| 2496 |
+
"loss": 0.4719,
|
| 2497 |
+
"step": 3520
|
| 2498 |
+
},
|
| 2499 |
+
{
|
| 2500 |
+
"epoch": 3.9887005649717513,
|
| 2501 |
+
"grad_norm": 0.6404000520706177,
|
| 2502 |
+
"learning_rate": 2.3910748605721066e-05,
|
| 2503 |
+
"loss": 0.4983,
|
| 2504 |
+
"step": 3530
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 4.0,
|
| 2508 |
+
"grad_norm": 0.6482042074203491,
|
| 2509 |
+
"learning_rate": 2.3401190718829945e-05,
|
| 2510 |
+
"loss": 0.4916,
|
| 2511 |
+
"step": 3540
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 4.011299435028248,
|
| 2515 |
+
"grad_norm": 0.4203549027442932,
|
| 2516 |
+
"learning_rate": 2.289640062063839e-05,
|
| 2517 |
+
"loss": 0.4653,
|
| 2518 |
+
"step": 3550
|
| 2519 |
+
},
|
| 2520 |
+
{
|
| 2521 |
+
"epoch": 4.022598870056497,
|
| 2522 |
+
"grad_norm": 0.48745134472846985,
|
| 2523 |
+
"learning_rate": 2.239640973111945e-05,
|
| 2524 |
+
"loss": 0.4595,
|
| 2525 |
+
"step": 3560
|
| 2526 |
+
},
|
| 2527 |
+
{
|
| 2528 |
+
"epoch": 4.033898305084746,
|
| 2529 |
+
"grad_norm": 0.5251093506813049,
|
| 2530 |
+
"learning_rate": 2.1901249171526063e-05,
|
| 2531 |
+
"loss": 0.4471,
|
| 2532 |
+
"step": 3570
|
| 2533 |
+
},
|
| 2534 |
+
{
|
| 2535 |
+
"epoch": 4.045197740112994,
|
| 2536 |
+
"grad_norm": 0.6273601651191711,
|
| 2537 |
+
"learning_rate": 2.1410949762453735e-05,
|
| 2538 |
+
"loss": 0.437,
|
| 2539 |
+
"step": 3580
|
| 2540 |
+
},
|
| 2541 |
+
{
|
| 2542 |
+
"epoch": 4.056497175141243,
|
| 2543 |
+
"grad_norm": 0.5651510953903198,
|
| 2544 |
+
"learning_rate": 2.0925542021922283e-05,
|
| 2545 |
+
"loss": 0.4194,
|
| 2546 |
+
"step": 3590
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 4.067796610169491,
|
| 2550 |
+
"grad_norm": 0.7425692081451416,
|
| 2551 |
+
"learning_rate": 2.0445056163476374e-05,
|
| 2552 |
+
"loss": 0.4568,
|
| 2553 |
+
"step": 3600
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 4.0790960451977405,
|
| 2557 |
+
"grad_norm": 0.49514123797416687,
|
| 2558 |
+
"learning_rate": 1.9969522094304704e-05,
|
| 2559 |
+
"loss": 0.4673,
|
| 2560 |
+
"step": 3610
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 4.090395480225989,
|
| 2564 |
+
"grad_norm": 0.7164167761802673,
|
| 2565 |
+
"learning_rate": 1.949896941337861e-05,
|
| 2566 |
+
"loss": 0.4507,
|
| 2567 |
+
"step": 3620
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 4.101694915254237,
|
| 2571 |
+
"grad_norm": 0.5990516543388367,
|
| 2572 |
+
"learning_rate": 1.9033427409609738e-05,
|
| 2573 |
+
"loss": 0.4271,
|
| 2574 |
+
"step": 3630
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 4.112994350282486,
|
| 2578 |
+
"grad_norm": 0.4122953414916992,
|
| 2579 |
+
"learning_rate": 1.8572925060026868e-05,
|
| 2580 |
+
"loss": 0.4331,
|
| 2581 |
+
"step": 3640
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 4.124293785310734,
|
| 2585 |
+
"grad_norm": 0.5930763483047485,
|
| 2586 |
+
"learning_rate": 1.8117491027972476e-05,
|
| 2587 |
+
"loss": 0.4388,
|
| 2588 |
+
"step": 3650
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 4.135593220338983,
|
| 2592 |
+
"grad_norm": 0.5768269300460815,
|
| 2593 |
+
"learning_rate": 1.766715366131837e-05,
|
| 2594 |
+
"loss": 0.4432,
|
| 2595 |
+
"step": 3660
|
| 2596 |
+
},
|
| 2597 |
+
{
|
| 2598 |
+
"epoch": 4.146892655367232,
|
| 2599 |
+
"grad_norm": 1.2128398418426514,
|
| 2600 |
+
"learning_rate": 1.722194099070148e-05,
|
| 2601 |
+
"loss": 0.4445,
|
| 2602 |
+
"step": 3670
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 4.15819209039548,
|
| 2606 |
+
"grad_norm": 0.5718667507171631,
|
| 2607 |
+
"learning_rate": 1.678188072777891e-05,
|
| 2608 |
+
"loss": 0.4348,
|
| 2609 |
+
"step": 3680
|
| 2610 |
+
},
|
| 2611 |
+
{
|
| 2612 |
+
"epoch": 4.169491525423728,
|
| 2613 |
+
"grad_norm": 0.6063762903213501,
|
| 2614 |
+
"learning_rate": 1.6347000263503176e-05,
|
| 2615 |
+
"loss": 0.4293,
|
| 2616 |
+
"step": 3690
|
| 2617 |
+
},
|
| 2618 |
+
{
|
| 2619 |
+
"epoch": 4.1807909604519775,
|
| 2620 |
+
"grad_norm": 0.5244751572608948,
|
| 2621 |
+
"learning_rate": 1.591732666641732e-05,
|
| 2622 |
+
"loss": 0.4469,
|
| 2623 |
+
"step": 3700
|
| 2624 |
+
},
|
| 2625 |
+
{
|
| 2626 |
+
"epoch": 4.192090395480226,
|
| 2627 |
+
"grad_norm": 0.6261086463928223,
|
| 2628 |
+
"learning_rate": 1.5492886680969963e-05,
|
| 2629 |
+
"loss": 0.4415,
|
| 2630 |
+
"step": 3710
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 4.203389830508475,
|
| 2634 |
+
"grad_norm": 1.0888699293136597,
|
| 2635 |
+
"learning_rate": 1.5073706725850679e-05,
|
| 2636 |
+
"loss": 0.4365,
|
| 2637 |
+
"step": 3720
|
| 2638 |
+
},
|
| 2639 |
+
{
|
| 2640 |
+
"epoch": 4.214689265536723,
|
| 2641 |
+
"grad_norm": 0.5183214545249939,
|
| 2642 |
+
"learning_rate": 1.4659812892345692e-05,
|
| 2643 |
+
"loss": 0.4717,
|
| 2644 |
+
"step": 3730
|
| 2645 |
+
},
|
| 2646 |
+
{
|
| 2647 |
+
"epoch": 4.2259887005649714,
|
| 2648 |
+
"grad_norm": 0.5120430588722229,
|
| 2649 |
+
"learning_rate": 1.425123094271369e-05,
|
| 2650 |
+
"loss": 0.4484,
|
| 2651 |
+
"step": 3740
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 4.237288135593221,
|
| 2655 |
+
"grad_norm": 0.4748518764972687,
|
| 2656 |
+
"learning_rate": 1.3847986308582384e-05,
|
| 2657 |
+
"loss": 0.4566,
|
| 2658 |
+
"step": 3750
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 4.248587570621469,
|
| 2662 |
+
"grad_norm": 0.5438849329948425,
|
| 2663 |
+
"learning_rate": 1.3450104089365611e-05,
|
| 2664 |
+
"loss": 0.4768,
|
| 2665 |
+
"step": 3760
|
| 2666 |
+
},
|
| 2667 |
+
{
|
| 2668 |
+
"epoch": 4.259887005649717,
|
| 2669 |
+
"grad_norm": 0.4719776213169098,
|
| 2670 |
+
"learning_rate": 1.3057609050700881e-05,
|
| 2671 |
+
"loss": 0.4657,
|
| 2672 |
+
"step": 3770
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 4.271186440677966,
|
| 2676 |
+
"grad_norm": 0.5300427675247192,
|
| 2677 |
+
"learning_rate": 1.267052562290808e-05,
|
| 2678 |
+
"loss": 0.4412,
|
| 2679 |
+
"step": 3780
|
| 2680 |
+
},
|
| 2681 |
+
{
|
| 2682 |
+
"epoch": 4.2824858757062145,
|
| 2683 |
+
"grad_norm": 0.6340104937553406,
|
| 2684 |
+
"learning_rate": 1.2288877899468653e-05,
|
| 2685 |
+
"loss": 0.4528,
|
| 2686 |
+
"step": 3790
|
| 2687 |
+
},
|
| 2688 |
+
{
|
| 2689 |
+
"epoch": 4.293785310734464,
|
| 2690 |
+
"grad_norm": 0.5274319648742676,
|
| 2691 |
+
"learning_rate": 1.1912689635526086e-05,
|
| 2692 |
+
"loss": 0.4466,
|
| 2693 |
+
"step": 3800
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 4.305084745762712,
|
| 2697 |
+
"grad_norm": 0.5659282803535461,
|
| 2698 |
+
"learning_rate": 1.1541984246407189e-05,
|
| 2699 |
+
"loss": 0.4332,
|
| 2700 |
+
"step": 3810
|
| 2701 |
+
},
|
| 2702 |
+
{
|
| 2703 |
+
"epoch": 4.31638418079096,
|
| 2704 |
+
"grad_norm": 0.5424573421478271,
|
| 2705 |
+
"learning_rate": 1.1176784806164676e-05,
|
| 2706 |
+
"loss": 0.4223,
|
| 2707 |
+
"step": 3820
|
| 2708 |
+
},
|
| 2709 |
+
{
|
| 2710 |
+
"epoch": 4.327683615819209,
|
| 2711 |
+
"grad_norm": 0.5446699261665344,
|
| 2712 |
+
"learning_rate": 1.081711404614104e-05,
|
| 2713 |
+
"loss": 0.4335,
|
| 2714 |
+
"step": 3830
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 4.338983050847458,
|
| 2718 |
+
"grad_norm": 0.4954063594341278,
|
| 2719 |
+
"learning_rate": 1.0462994353553512e-05,
|
| 2720 |
+
"loss": 0.4221,
|
| 2721 |
+
"step": 3840
|
| 2722 |
+
},
|
| 2723 |
+
{
|
| 2724 |
+
"epoch": 4.350282485875706,
|
| 2725 |
+
"grad_norm": 0.6320489048957825,
|
| 2726 |
+
"learning_rate": 1.0114447770100688e-05,
|
| 2727 |
+
"loss": 0.43,
|
| 2728 |
+
"step": 3850
|
| 2729 |
+
},
|
| 2730 |
+
{
|
| 2731 |
+
"epoch": 4.361581920903955,
|
| 2732 |
+
"grad_norm": 0.5482968688011169,
|
| 2733 |
+
"learning_rate": 9.77149599059063e-06,
|
| 2734 |
+
"loss": 0.4407,
|
| 2735 |
+
"step": 3860
|
| 2736 |
+
},
|
| 2737 |
+
{
|
| 2738 |
+
"epoch": 4.372881355932203,
|
| 2739 |
+
"grad_norm": 0.6075878739356995,
|
| 2740 |
+
"learning_rate": 9.434160361590372e-06,
|
| 2741 |
+
"loss": 0.4434,
|
| 2742 |
+
"step": 3870
|
| 2743 |
+
},
|
| 2744 |
+
{
|
| 2745 |
+
"epoch": 4.3841807909604515,
|
| 2746 |
+
"grad_norm": 0.6049032211303711,
|
| 2747 |
+
"learning_rate": 9.102461880097302e-06,
|
| 2748 |
+
"loss": 0.4411,
|
| 2749 |
+
"step": 3880
|
| 2750 |
+
},
|
| 2751 |
+
{
|
| 2752 |
+
"epoch": 4.395480225988701,
|
| 2753 |
+
"grad_norm": 0.5798004865646362,
|
| 2754 |
+
"learning_rate": 8.776421192232298e-06,
|
| 2755 |
+
"loss": 0.431,
|
| 2756 |
+
"step": 3890
|
| 2757 |
+
},
|
| 2758 |
+
{
|
| 2759 |
+
"epoch": 4.406779661016949,
|
| 2760 |
+
"grad_norm": 0.5278260707855225,
|
| 2761 |
+
"learning_rate": 8.456058591954463e-06,
|
| 2762 |
+
"loss": 0.4422,
|
| 2763 |
+
"step": 3900
|
| 2764 |
+
},
|
| 2765 |
+
{
|
| 2766 |
+
"epoch": 4.418079096045198,
|
| 2767 |
+
"grad_norm": 0.568495512008667,
|
| 2768 |
+
"learning_rate": 8.141394019798177e-06,
|
| 2769 |
+
"loss": 0.4413,
|
| 2770 |
+
"step": 3910
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 4.429378531073446,
|
| 2774 |
+
"grad_norm": 0.5533962845802307,
|
| 2775 |
+
"learning_rate": 7.832447061631688e-06,
|
| 2776 |
+
"loss": 0.4191,
|
| 2777 |
+
"step": 3920
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 4.440677966101695,
|
| 2781 |
+
"grad_norm": 0.5724579691886902,
|
| 2782 |
+
"learning_rate": 7.529236947438256e-06,
|
| 2783 |
+
"loss": 0.4428,
|
| 2784 |
+
"step": 3930
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 4.451977401129944,
|
| 2788 |
+
"grad_norm": 0.5295354723930359,
|
| 2789 |
+
"learning_rate": 7.231782550119015e-06,
|
| 2790 |
+
"loss": 0.4363,
|
| 2791 |
+
"step": 3940
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 4.463276836158192,
|
| 2795 |
+
"grad_norm": 0.6352728605270386,
|
| 2796 |
+
"learning_rate": 6.940102384318314e-06,
|
| 2797 |
+
"loss": 0.4462,
|
| 2798 |
+
"step": 3950
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 4.47457627118644,
|
| 2802 |
+
"grad_norm": 0.4653913080692291,
|
| 2803 |
+
"learning_rate": 6.654214605271414e-06,
|
| 2804 |
+
"loss": 0.4463,
|
| 2805 |
+
"step": 3960
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 4.4858757062146895,
|
| 2809 |
+
"grad_norm": 0.5769869685173035,
|
| 2810 |
+
"learning_rate": 6.37413700767423e-06,
|
| 2811 |
+
"loss": 0.4388,
|
| 2812 |
+
"step": 3970
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 4.497175141242938,
|
| 2816 |
+
"grad_norm": 0.4576704204082489,
|
| 2817 |
+
"learning_rate": 6.099887024575901e-06,
|
| 2818 |
+
"loss": 0.4466,
|
| 2819 |
+
"step": 3980
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 4.508474576271187,
|
| 2823 |
+
"grad_norm": 0.5665444135665894,
|
| 2824 |
+
"learning_rate": 5.831481726293609e-06,
|
| 2825 |
+
"loss": 0.4628,
|
| 2826 |
+
"step": 3990
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 4.519774011299435,
|
| 2830 |
+
"grad_norm": 0.527612566947937,
|
| 2831 |
+
"learning_rate": 5.568937819350084e-06,
|
| 2832 |
+
"loss": 0.4261,
|
| 2833 |
+
"step": 4000
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 4.519774011299435,
|
| 2837 |
+
"eval_loss": 0.8213748335838318,
|
| 2838 |
+
"eval_runtime": 16.8138,
|
| 2839 |
+
"eval_samples_per_second": 88.677,
|
| 2840 |
+
"eval_steps_per_second": 11.122,
|
| 2841 |
+
"step": 4000
|
| 2842 |
+
},
|
| 2843 |
+
{
|
| 2844 |
+
"epoch": 4.531073446327683,
|
| 2845 |
+
"grad_norm": 0.668229877948761,
|
| 2846 |
+
"learning_rate": 5.312271645433697e-06,
|
| 2847 |
+
"loss": 0.4298,
|
| 2848 |
+
"step": 4010
|
| 2849 |
+
},
|
| 2850 |
+
{
|
| 2851 |
+
"epoch": 4.5423728813559325,
|
| 2852 |
+
"grad_norm": 0.5199172496795654,
|
| 2853 |
+
"learning_rate": 5.061499180381391e-06,
|
| 2854 |
+
"loss": 0.4547,
|
| 2855 |
+
"step": 4020
|
| 2856 |
+
},
|
| 2857 |
+
{
|
| 2858 |
+
"epoch": 4.553672316384181,
|
| 2859 |
+
"grad_norm": 0.5515559911727905,
|
| 2860 |
+
"learning_rate": 4.816636033184119e-06,
|
| 2861 |
+
"loss": 0.4172,
|
| 2862 |
+
"step": 4030
|
| 2863 |
+
},
|
| 2864 |
+
{
|
| 2865 |
+
"epoch": 4.564971751412429,
|
| 2866 |
+
"grad_norm": 0.648692786693573,
|
| 2867 |
+
"learning_rate": 4.577697445015472e-06,
|
| 2868 |
+
"loss": 0.4664,
|
| 2869 |
+
"step": 4040
|
| 2870 |
+
},
|
| 2871 |
+
{
|
| 2872 |
+
"epoch": 4.576271186440678,
|
| 2873 |
+
"grad_norm": 0.5000047087669373,
|
| 2874 |
+
"learning_rate": 4.3446982882828555e-06,
|
| 2875 |
+
"loss": 0.4401,
|
| 2876 |
+
"step": 4050
|
| 2877 |
+
},
|
| 2878 |
+
{
|
| 2879 |
+
"epoch": 4.5875706214689265,
|
| 2880 |
+
"grad_norm": 0.51460862159729,
|
| 2881 |
+
"learning_rate": 4.117653065701899e-06,
|
| 2882 |
+
"loss": 0.4297,
|
| 2883 |
+
"step": 4060
|
| 2884 |
+
},
|
| 2885 |
+
{
|
| 2886 |
+
"epoch": 4.598870056497175,
|
| 2887 |
+
"grad_norm": 0.5801824331283569,
|
| 2888 |
+
"learning_rate": 3.896575909393663e-06,
|
| 2889 |
+
"loss": 0.453,
|
| 2890 |
+
"step": 4070
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 4.610169491525424,
|
| 2894 |
+
"grad_norm": 0.5613316297531128,
|
| 2895 |
+
"learning_rate": 3.6814805800050255e-06,
|
| 2896 |
+
"loss": 0.445,
|
| 2897 |
+
"step": 4080
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 4.621468926553672,
|
| 2901 |
+
"grad_norm": 0.556430459022522,
|
| 2902 |
+
"learning_rate": 3.4723804658522318e-06,
|
| 2903 |
+
"loss": 0.4332,
|
| 2904 |
+
"step": 4090
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 4.632768361581921,
|
| 2908 |
+
"grad_norm": 0.7290319204330444,
|
| 2909 |
+
"learning_rate": 3.269288582087493e-06,
|
| 2910 |
+
"loss": 0.4667,
|
| 2911 |
+
"step": 4100
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 4.6440677966101696,
|
| 2915 |
+
"grad_norm": 0.5109266638755798,
|
| 2916 |
+
"learning_rate": 3.072217569888847e-06,
|
| 2917 |
+
"loss": 0.4484,
|
| 2918 |
+
"step": 4110
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 4.655367231638418,
|
| 2922 |
+
"grad_norm": 0.5184862017631531,
|
| 2923 |
+
"learning_rate": 2.8811796956734418e-06,
|
| 2924 |
+
"loss": 0.4476,
|
| 2925 |
+
"step": 4120
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 4.666666666666667,
|
| 2929 |
+
"grad_norm": 0.45906636118888855,
|
| 2930 |
+
"learning_rate": 2.696186850333893e-06,
|
| 2931 |
+
"loss": 0.4556,
|
| 2932 |
+
"step": 4130
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 4.677966101694915,
|
| 2936 |
+
"grad_norm": 0.6825990080833435,
|
| 2937 |
+
"learning_rate": 2.5172505484982733e-06,
|
| 2938 |
+
"loss": 0.4361,
|
| 2939 |
+
"step": 4140
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 4.6892655367231635,
|
| 2943 |
+
"grad_norm": 0.6751702427864075,
|
| 2944 |
+
"learning_rate": 2.3443819278132996e-06,
|
| 2945 |
+
"loss": 0.454,
|
| 2946 |
+
"step": 4150
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 4.700564971751413,
|
| 2950 |
+
"grad_norm": 0.6289049983024597,
|
| 2951 |
+
"learning_rate": 2.17759174825114e-06,
|
| 2952 |
+
"loss": 0.4438,
|
| 2953 |
+
"step": 4160
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 4.711864406779661,
|
| 2957 |
+
"grad_norm": 0.6290619969367981,
|
| 2958 |
+
"learning_rate": 2.016890391439674e-06,
|
| 2959 |
+
"loss": 0.4665,
|
| 2960 |
+
"step": 4170
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 4.72316384180791,
|
| 2964 |
+
"grad_norm": 0.5864591002464294,
|
| 2965 |
+
"learning_rate": 1.8622878600162763e-06,
|
| 2966 |
+
"loss": 0.4477,
|
| 2967 |
+
"step": 4180
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 4.734463276836158,
|
| 2971 |
+
"grad_norm": 0.558210015296936,
|
| 2972 |
+
"learning_rate": 1.7137937770052349e-06,
|
| 2973 |
+
"loss": 0.4605,
|
| 2974 |
+
"step": 4190
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 4.745762711864407,
|
| 2978 |
+
"grad_norm": 0.6048043966293335,
|
| 2979 |
+
"learning_rate": 1.5714173852187875e-06,
|
| 2980 |
+
"loss": 0.4458,
|
| 2981 |
+
"step": 4200
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 4.757062146892656,
|
| 2985 |
+
"grad_norm": 0.6476958990097046,
|
| 2986 |
+
"learning_rate": 1.4351675466817705e-06,
|
| 2987 |
+
"loss": 0.4311,
|
| 2988 |
+
"step": 4210
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 4.768361581920904,
|
| 2992 |
+
"grad_norm": 0.6173336505889893,
|
| 2993 |
+
"learning_rate": 1.3050527420800928e-06,
|
| 2994 |
+
"loss": 0.4526,
|
| 2995 |
+
"step": 4220
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 4.779661016949152,
|
| 2999 |
+
"grad_norm": 0.5486857295036316,
|
| 3000 |
+
"learning_rate": 1.1810810702327701e-06,
|
| 3001 |
+
"loss": 0.4407,
|
| 3002 |
+
"step": 4230
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 4.790960451977401,
|
| 3006 |
+
"grad_norm": 0.4905402362346649,
|
| 3007 |
+
"learning_rate": 1.063260247587905e-06,
|
| 3008 |
+
"loss": 0.4367,
|
| 3009 |
+
"step": 4240
|
| 3010 |
+
},
|
| 3011 |
+
{
|
| 3012 |
+
"epoch": 4.80225988700565,
|
| 3013 |
+
"grad_norm": 0.6765434741973877,
|
| 3014 |
+
"learning_rate": 9.515976077423716e-07,
|
| 3015 |
+
"loss": 0.4438,
|
| 3016 |
+
"step": 4250
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 4.813559322033898,
|
| 3020 |
+
"grad_norm": 0.5942672491073608,
|
| 3021 |
+
"learning_rate": 8.461001009852809e-07,
|
| 3022 |
+
"loss": 0.4326,
|
| 3023 |
+
"step": 4260
|
| 3024 |
+
},
|
| 3025 |
+
{
|
| 3026 |
+
"epoch": 4.824858757062147,
|
| 3027 |
+
"grad_norm": 0.5058199167251587,
|
| 3028 |
+
"learning_rate": 7.46774293865471e-07,
|
| 3029 |
+
"loss": 0.4258,
|
| 3030 |
+
"step": 4270
|
| 3031 |
+
},
|
| 3032 |
+
{
|
| 3033 |
+
"epoch": 4.836158192090395,
|
| 3034 |
+
"grad_norm": 0.5257803797721863,
|
| 3035 |
+
"learning_rate": 6.536263687827005e-07,
|
| 3036 |
+
"loss": 0.4377,
|
| 3037 |
+
"step": 4280
|
| 3038 |
+
},
|
| 3039 |
+
{
|
| 3040 |
+
"epoch": 4.847457627118644,
|
| 3041 |
+
"grad_norm": 0.5546150207519531,
|
| 3042 |
+
"learning_rate": 5.66662123602879e-07,
|
| 3043 |
+
"loss": 0.447,
|
| 3044 |
+
"step": 4290
|
| 3045 |
+
},
|
| 3046 |
+
{
|
| 3047 |
+
"epoch": 4.858757062146893,
|
| 3048 |
+
"grad_norm": 0.5133059024810791,
|
| 3049 |
+
"learning_rate": 4.858869712971669e-07,
|
| 3050 |
+
"loss": 0.4536,
|
| 3051 |
+
"step": 4300
|
| 3052 |
+
},
|
| 3053 |
+
{
|
| 3054 |
+
"epoch": 4.870056497175141,
|
| 3055 |
+
"grad_norm": 0.6438310742378235,
|
| 3056 |
+
"learning_rate": 4.113059396050445e-07,
|
| 3057 |
+
"loss": 0.4328,
|
| 3058 |
+
"step": 4310
|
| 3059 |
+
},
|
| 3060 |
+
{
|
| 3061 |
+
"epoch": 4.88135593220339,
|
| 3062 |
+
"grad_norm": 0.5640572309494019,
|
| 3063 |
+
"learning_rate": 3.4292367072140677e-07,
|
| 3064 |
+
"loss": 0.4629,
|
| 3065 |
+
"step": 4320
|
| 3066 |
+
},
|
| 3067 |
+
{
|
| 3068 |
+
"epoch": 4.892655367231638,
|
| 3069 |
+
"grad_norm": 0.6676624417304993,
|
| 3070 |
+
"learning_rate": 2.807444210075616e-07,
|
| 3071 |
+
"loss": 0.4347,
|
| 3072 |
+
"step": 4330
|
| 3073 |
+
},
|
| 3074 |
+
{
|
| 3075 |
+
"epoch": 4.903954802259887,
|
| 3076 |
+
"grad_norm": 0.45671963691711426,
|
| 3077 |
+
"learning_rate": 2.2477206072633038e-07,
|
| 3078 |
+
"loss": 0.4536,
|
| 3079 |
+
"step": 4340
|
| 3080 |
+
},
|
| 3081 |
+
{
|
| 3082 |
+
"epoch": 4.915254237288136,
|
| 3083 |
+
"grad_norm": 0.6115604043006897,
|
| 3084 |
+
"learning_rate": 1.7501007380115174e-07,
|
| 3085 |
+
"loss": 0.4453,
|
| 3086 |
+
"step": 4350
|
| 3087 |
+
},
|
| 3088 |
+
{
|
| 3089 |
+
"epoch": 4.926553672316384,
|
| 3090 |
+
"grad_norm": 0.7250502109527588,
|
| 3091 |
+
"learning_rate": 1.3146155759923285e-07,
|
| 3092 |
+
"loss": 0.4454,
|
| 3093 |
+
"step": 4360
|
| 3094 |
+
},
|
| 3095 |
+
{
|
| 3096 |
+
"epoch": 4.937853107344633,
|
| 3097 |
+
"grad_norm": 0.5707434415817261,
|
| 3098 |
+
"learning_rate": 9.412922273871471e-08,
|
| 3099 |
+
"loss": 0.4107,
|
| 3100 |
+
"step": 4370
|
| 3101 |
+
},
|
| 3102 |
+
{
|
| 3103 |
+
"epoch": 4.9491525423728815,
|
| 3104 |
+
"grad_norm": 0.6125264763832092,
|
| 3105 |
+
"learning_rate": 6.301539292001834e-08,
|
| 3106 |
+
"loss": 0.4355,
|
| 3107 |
+
"step": 4380
|
| 3108 |
+
},
|
| 3109 |
+
{
|
| 3110 |
+
"epoch": 4.96045197740113,
|
| 3111 |
+
"grad_norm": 0.6177554130554199,
|
| 3112 |
+
"learning_rate": 3.8122004781149246e-08,
|
| 3113 |
+
"loss": 0.4502,
|
| 3114 |
+
"step": 4390
|
| 3115 |
+
},
|
| 3116 |
+
{
|
| 3117 |
+
"epoch": 4.971751412429379,
|
| 3118 |
+
"grad_norm": 0.7295418381690979,
|
| 3119 |
+
"learning_rate": 1.9450607777204978e-08,
|
| 3120 |
+
"loss": 0.4426,
|
| 3121 |
+
"step": 4400
|
| 3122 |
+
},
|
| 3123 |
+
{
|
| 3124 |
+
"epoch": 4.983050847457627,
|
| 3125 |
+
"grad_norm": 0.5891022682189941,
|
| 3126 |
+
"learning_rate": 7.00236408388566e-09,
|
| 3127 |
+
"loss": 0.449,
|
| 3128 |
+
"step": 4410
|
| 3129 |
+
},
|
| 3130 |
+
{
|
| 3131 |
+
"epoch": 4.994350282485875,
|
| 3132 |
+
"grad_norm": 0.5898358225822449,
|
| 3133 |
+
"learning_rate": 7.780485252073533e-10,
|
| 3134 |
+
"loss": 0.4552,
|
| 3135 |
+
"step": 4420
|
| 3136 |
+
},
|
| 3137 |
+
{
|
| 3138 |
+
"epoch": 5.0,
|
| 3139 |
+
"step": 4425,
|
| 3140 |
+
"total_flos": 1.2071933436588196e+18,
|
| 3141 |
+
"train_loss": 0.5702266787943867,
|
| 3142 |
+
"train_runtime": 4287.601,
|
| 3143 |
+
"train_samples_per_second": 33.024,
|
| 3144 |
+
"train_steps_per_second": 1.032
|
| 3145 |
+
}
|
| 3146 |
+
],
|
| 3147 |
+
"logging_steps": 10,
|
| 3148 |
+
"max_steps": 4425,
|
| 3149 |
+
"num_input_tokens_seen": 0,
|
| 3150 |
+
"num_train_epochs": 5,
|
| 3151 |
+
"save_steps": 1000,
|
| 3152 |
+
"stateful_callbacks": {
|
| 3153 |
+
"TrainerControl": {
|
| 3154 |
+
"args": {
|
| 3155 |
+
"should_epoch_stop": false,
|
| 3156 |
+
"should_evaluate": false,
|
| 3157 |
+
"should_log": false,
|
| 3158 |
+
"should_save": true,
|
| 3159 |
+
"should_training_stop": true
|
| 3160 |
+
},
|
| 3161 |
+
"attributes": {}
|
| 3162 |
+
}
|
| 3163 |
+
},
|
| 3164 |
+
"total_flos": 1.2071933436588196e+18,
|
| 3165 |
+
"train_batch_size": 2,
|
| 3166 |
+
"trial_name": null,
|
| 3167 |
+
"trial_params": null
|
| 3168 |
+
}
|
wizardlm/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:956f8a572e9f5b144638f75404234f104998213f6b8143dabf4cad1ef7e50182
|
| 3 |
+
size 5432
|
wizardlm/training_eval_loss.png
ADDED
|
wizardlm/training_loss.png
ADDED
|