Upload 15 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 lima/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+code_alpaca/tokenizer.json filter=lfs diff=lfs merge=lfs -text

code_alpaca/README.md

@@ -0,0 +1,67 @@
+---
+base_model: /cpfs01/user/zhangyiqun/models/gemma-2-2b-it
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: code_alpaca
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# code_alpaca
+
+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 code_alpaca dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7001
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4081        | 1.6807 | 1000 | 0.4699          |
+| 0.2383        | 3.3613 | 2000 | 0.5870          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.44.2
+- Pytorch 2.3.0+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

code_alpaca/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/cpfs01/user/zhangyiqun/models/gemma-2-2b-it",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

code_alpaca/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8919e9a024617099b0381bad684b2207602642baa90a9b8c71592d2f7030cb2
+size 41581360

code_alpaca/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.700109601020813,
+    "eval_runtime": 9.0559,
+    "eval_samples_per_second": 110.536,
+    "eval_steps_per_second": 13.914,
+    "total_flos": 2.1667263896407245e+17,
+    "train_loss": 0.34065224741687294,
+    "train_runtime": 1015.5372,
+    "train_samples_per_second": 93.62,
+    "train_steps_per_second": 2.929
+}

code_alpaca/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 0.700109601020813,
+    "eval_runtime": 9.0559,
+    "eval_samples_per_second": 110.536,
+    "eval_steps_per_second": 13.914
+}

code_alpaca/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

code_alpaca/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
+size 17525357

code_alpaca/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

code_alpaca/tokenizer_config.json

@@ -0,0 +1,2015 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255968": {
+      "content": "[toxicity=0]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255969": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255970": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255971": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255972": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255973": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255974": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255975": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255976": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255977": {
+      "content": "\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255978": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255979": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255980": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255981": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255982": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255983": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255984": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255985": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255986": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255987": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255988": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255989": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255990": {
+      "content": "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255991": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255992": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255993": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255994": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255995": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255996": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255997": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255998": {
+      "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",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255999": {
+      "content": "<unused99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "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 %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

code_alpaca/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.1667263896407245e+17,
+    "train_loss": 0.34065224741687294,
+    "train_runtime": 1015.5372,
+    "train_samples_per_second": 93.62,
+    "train_steps_per_second": 2.929
+}

code_alpaca/trainer_log.jsonl

@@ -0,0 +1,300 @@
+{"current_steps": 10, "total_steps": 2975, "loss": 1.2952, "learning_rate": 6.7114093959731546e-06, "epoch": 0.01680672268907563, "percentage": 0.34, "elapsed_time": "0:00:03", "remaining_time": "0:19:27"}
+{"current_steps": 20, "total_steps": 2975, "loss": 1.4041, "learning_rate": 1.3422818791946309e-05, "epoch": 0.03361344537815126, "percentage": 0.67, "elapsed_time": "0:00:07", "remaining_time": "0:17:46"}
+{"current_steps": 30, "total_steps": 2975, "loss": 1.2144, "learning_rate": 2.013422818791946e-05, "epoch": 0.05042016806722689, "percentage": 1.01, "elapsed_time": "0:00:10", "remaining_time": "0:16:51"}
+{"current_steps": 40, "total_steps": 2975, "loss": 0.8496, "learning_rate": 2.6845637583892618e-05, "epoch": 0.06722689075630252, "percentage": 1.34, "elapsed_time": "0:00:13", "remaining_time": "0:16:43"}
+{"current_steps": 50, "total_steps": 2975, "loss": 0.642, "learning_rate": 3.3557046979865775e-05, "epoch": 0.08403361344537816, "percentage": 1.68, "elapsed_time": "0:00:17", "remaining_time": "0:16:39"}
+{"current_steps": 60, "total_steps": 2975, "loss": 0.5978, "learning_rate": 4.026845637583892e-05, "epoch": 0.10084033613445378, "percentage": 2.02, "elapsed_time": "0:00:20", "remaining_time": "0:16:28"}
+{"current_steps": 70, "total_steps": 2975, "loss": 0.5342, "learning_rate": 4.697986577181208e-05, "epoch": 0.11764705882352941, "percentage": 2.35, "elapsed_time": "0:00:24", "remaining_time": "0:16:36"}
+{"current_steps": 80, "total_steps": 2975, "loss": 0.536, "learning_rate": 5.3691275167785237e-05, "epoch": 0.13445378151260504, "percentage": 2.69, "elapsed_time": "0:00:27", "remaining_time": "0:16:28"}
+{"current_steps": 90, "total_steps": 2975, "loss": 0.5294, "learning_rate": 6.04026845637584e-05, "epoch": 0.15126050420168066, "percentage": 3.03, "elapsed_time": "0:00:30", "remaining_time": "0:16:18"}
+{"current_steps": 100, "total_steps": 2975, "loss": 0.5288, "learning_rate": 6.711409395973155e-05, "epoch": 0.16806722689075632, "percentage": 3.36, "elapsed_time": "0:00:34", "remaining_time": "0:16:21"}
+{"current_steps": 110, "total_steps": 2975, "loss": 0.5467, "learning_rate": 7.382550335570471e-05, "epoch": 0.18487394957983194, "percentage": 3.7, "elapsed_time": "0:00:37", "remaining_time": "0:16:24"}
+{"current_steps": 120, "total_steps": 2975, "loss": 0.5057, "learning_rate": 8.053691275167784e-05, "epoch": 0.20168067226890757, "percentage": 4.03, "elapsed_time": "0:00:40", "remaining_time": "0:16:10"}
+{"current_steps": 130, "total_steps": 2975, "loss": 0.5094, "learning_rate": 8.7248322147651e-05, "epoch": 0.2184873949579832, "percentage": 4.37, "elapsed_time": "0:00:43", "remaining_time": "0:15:58"}
+{"current_steps": 140, "total_steps": 2975, "loss": 0.5195, "learning_rate": 9.395973154362417e-05, "epoch": 0.23529411764705882, "percentage": 4.71, "elapsed_time": "0:00:47", "remaining_time": "0:15:52"}
+{"current_steps": 150, "total_steps": 2975, "loss": 0.4653, "learning_rate": 0.00010067114093959733, "epoch": 0.25210084033613445, "percentage": 5.04, "elapsed_time": "0:00:50", "remaining_time": "0:15:44"}
+{"current_steps": 160, "total_steps": 2975, "loss": 0.4979, "learning_rate": 0.00010738255033557047, "epoch": 0.2689075630252101, "percentage": 5.38, "elapsed_time": "0:00:53", "remaining_time": "0:15:40"}
+{"current_steps": 170, "total_steps": 2975, "loss": 0.5004, "learning_rate": 0.00011409395973154362, "epoch": 0.2857142857142857, "percentage": 5.71, "elapsed_time": "0:00:57", "remaining_time": "0:15:40"}
+{"current_steps": 180, "total_steps": 2975, "loss": 0.4975, "learning_rate": 0.0001208053691275168, "epoch": 0.3025210084033613, "percentage": 6.05, "elapsed_time": "0:01:01", "remaining_time": "0:15:49"}
+{"current_steps": 190, "total_steps": 2975, "loss": 0.4779, "learning_rate": 0.00012751677852348994, "epoch": 0.31932773109243695, "percentage": 6.39, "elapsed_time": "0:01:04", "remaining_time": "0:15:43"}
+{"current_steps": 200, "total_steps": 2975, "loss": 0.5172, "learning_rate": 0.0001342281879194631, "epoch": 0.33613445378151263, "percentage": 6.72, "elapsed_time": "0:01:07", "remaining_time": "0:15:41"}
+{"current_steps": 210, "total_steps": 2975, "loss": 0.4858, "learning_rate": 0.00014093959731543624, "epoch": 0.35294117647058826, "percentage": 7.06, "elapsed_time": "0:01:10", "remaining_time": "0:15:34"}
+{"current_steps": 220, "total_steps": 2975, "loss": 0.5518, "learning_rate": 0.00014765100671140942, "epoch": 0.3697478991596639, "percentage": 7.39, "elapsed_time": "0:01:14", "remaining_time": "0:15:32"}
+{"current_steps": 230, "total_steps": 2975, "loss": 0.4668, "learning_rate": 0.00015436241610738256, "epoch": 0.3865546218487395, "percentage": 7.73, "elapsed_time": "0:01:17", "remaining_time": "0:15:28"}
+{"current_steps": 240, "total_steps": 2975, "loss": 0.5524, "learning_rate": 0.0001610738255033557, "epoch": 0.40336134453781514, "percentage": 8.07, "elapsed_time": "0:01:21", "remaining_time": "0:15:24"}
+{"current_steps": 250, "total_steps": 2975, "loss": 0.4681, "learning_rate": 0.00016778523489932888, "epoch": 0.42016806722689076, "percentage": 8.4, "elapsed_time": "0:01:24", "remaining_time": "0:15:20"}
+{"current_steps": 260, "total_steps": 2975, "loss": 0.4922, "learning_rate": 0.000174496644295302, "epoch": 0.4369747899159664, "percentage": 8.74, "elapsed_time": "0:01:27", "remaining_time": "0:15:15"}
+{"current_steps": 270, "total_steps": 2975, "loss": 0.4656, "learning_rate": 0.00018120805369127517, "epoch": 0.453781512605042, "percentage": 9.08, "elapsed_time": "0:01:30", "remaining_time": "0:15:10"}
+{"current_steps": 280, "total_steps": 2975, "loss": 0.4973, "learning_rate": 0.00018791946308724833, "epoch": 0.47058823529411764, "percentage": 9.41, "elapsed_time": "0:01:34", "remaining_time": "0:15:06"}
+{"current_steps": 290, "total_steps": 2975, "loss": 0.4703, "learning_rate": 0.0001946308724832215, "epoch": 0.48739495798319327, "percentage": 9.75, "elapsed_time": "0:01:37", "remaining_time": "0:15:04"}
+{"current_steps": 300, "total_steps": 2975, "loss": 0.4574, "learning_rate": 0.00019999972455632807, "epoch": 0.5042016806722689, "percentage": 10.08, "elapsed_time": "0:01:41", "remaining_time": "0:15:02"}
+{"current_steps": 310, "total_steps": 2975, "loss": 0.4596, "learning_rate": 0.00019999008418713482, "epoch": 0.5210084033613446, "percentage": 10.42, "elapsed_time": "0:01:44", "remaining_time": "0:14:56"}
+{"current_steps": 320, "total_steps": 2975, "loss": 0.4853, "learning_rate": 0.00019996667315169163, "epoch": 0.5378151260504201, "percentage": 10.76, "elapsed_time": "0:01:47", "remaining_time": "0:14:51"}
+{"current_steps": 330, "total_steps": 2975, "loss": 0.4407, "learning_rate": 0.00019992949467417378, "epoch": 0.5546218487394958, "percentage": 11.09, "elapsed_time": "0:01:51", "remaining_time": "0:14:53"}
+{"current_steps": 340, "total_steps": 2975, "loss": 0.4614, "learning_rate": 0.00019987855387481305, "epoch": 0.5714285714285714, "percentage": 11.43, "elapsed_time": "0:01:54", "remaining_time": "0:14:47"}
+{"current_steps": 350, "total_steps": 2975, "loss": 0.4619, "learning_rate": 0.0001998138577691925, "epoch": 0.5882352941176471, "percentage": 11.76, "elapsed_time": "0:01:57", "remaining_time": "0:14:42"}
+{"current_steps": 360, "total_steps": 2975, "loss": 0.4828, "learning_rate": 0.00019973541526728048, "epoch": 0.6050420168067226, "percentage": 12.1, "elapsed_time": "0:02:00", "remaining_time": "0:14:37"}
+{"current_steps": 370, "total_steps": 2975, "loss": 0.4406, "learning_rate": 0.0001996432371722033, "epoch": 0.6218487394957983, "percentage": 12.44, "elapsed_time": "0:02:03", "remaining_time": "0:14:32"}
+{"current_steps": 380, "total_steps": 2975, "loss": 0.4854, "learning_rate": 0.00019953733617875759, "epoch": 0.6386554621848739, "percentage": 12.77, "elapsed_time": "0:02:07", "remaining_time": "0:14:31"}
+{"current_steps": 390, "total_steps": 2975, "loss": 0.4921, "learning_rate": 0.00019941772687166192, "epoch": 0.6554621848739496, "percentage": 13.11, "elapsed_time": "0:02:10", "remaining_time": "0:14:27"}
+{"current_steps": 400, "total_steps": 2975, "loss": 0.4802, "learning_rate": 0.00019928442572354814, "epoch": 0.6722689075630253, "percentage": 13.45, "elapsed_time": "0:02:14", "remaining_time": "0:14:24"}
+{"current_steps": 410, "total_steps": 2975, "loss": 0.5042, "learning_rate": 0.00019913745109269288, "epoch": 0.6890756302521008, "percentage": 13.78, "elapsed_time": "0:02:17", "remaining_time": "0:14:21"}
+{"current_steps": 420, "total_steps": 2975, "loss": 0.4865, "learning_rate": 0.00019897682322048908, "epoch": 0.7058823529411765, "percentage": 14.12, "elapsed_time": "0:02:20", "remaining_time": "0:14:17"}
+{"current_steps": 430, "total_steps": 2975, "loss": 0.4781, "learning_rate": 0.0001988025642286585, "epoch": 0.7226890756302521, "percentage": 14.45, "elapsed_time": "0:02:24", "remaining_time": "0:14:12"}
+{"current_steps": 440, "total_steps": 2975, "loss": 0.5091, "learning_rate": 0.000198614698116205, "epoch": 0.7394957983193278, "percentage": 14.79, "elapsed_time": "0:02:27", "remaining_time": "0:14:07"}
+{"current_steps": 450, "total_steps": 2975, "loss": 0.5004, "learning_rate": 0.00019841325075610944, "epoch": 0.7563025210084033, "percentage": 15.13, "elapsed_time": "0:02:30", "remaining_time": "0:14:04"}
+{"current_steps": 460, "total_steps": 2975, "loss": 0.4652, "learning_rate": 0.00019819824989176645, "epoch": 0.773109243697479, "percentage": 15.46, "elapsed_time": "0:02:33", "remaining_time": "0:13:59"}
+{"current_steps": 470, "total_steps": 2975, "loss": 0.4739, "learning_rate": 0.00019796972513316355, "epoch": 0.7899159663865546, "percentage": 15.8, "elapsed_time": "0:02:36", "remaining_time": "0:13:55"}
+{"current_steps": 480, "total_steps": 2975, "loss": 0.5072, "learning_rate": 0.00019772770795280329, "epoch": 0.8067226890756303, "percentage": 16.13, "elapsed_time": "0:02:40", "remaining_time": "0:13:54"}
+{"current_steps": 490, "total_steps": 2975, "loss": 0.5094, "learning_rate": 0.00019747223168136886, "epoch": 0.8235294117647058, "percentage": 16.47, "elapsed_time": "0:02:43", "remaining_time": "0:13:50"}
+{"current_steps": 500, "total_steps": 2975, "loss": 0.4812, "learning_rate": 0.00019720333150313377, "epoch": 0.8403361344537815, "percentage": 16.81, "elapsed_time": "0:02:46", "remaining_time": "0:13:46"}
+{"current_steps": 510, "total_steps": 2975, "loss": 0.4823, "learning_rate": 0.0001969210444511162, "epoch": 0.8571428571428571, "percentage": 17.14, "elapsed_time": "0:02:50", "remaining_time": "0:13:42"}
+{"current_steps": 520, "total_steps": 2975, "loss": 0.4559, "learning_rate": 0.00019662540940197892, "epoch": 0.8739495798319328, "percentage": 17.48, "elapsed_time": "0:02:53", "remaining_time": "0:13:38"}
+{"current_steps": 530, "total_steps": 2975, "loss": 0.4803, "learning_rate": 0.00019631646707067511, "epoch": 0.8907563025210085, "percentage": 17.82, "elapsed_time": "0:02:56", "remaining_time": "0:13:34"}
+{"current_steps": 540, "total_steps": 2975, "loss": 0.4481, "learning_rate": 0.000195994260004841, "epoch": 0.907563025210084, "percentage": 18.15, "elapsed_time": "0:02:59", "remaining_time": "0:13:30"}
+{"current_steps": 550, "total_steps": 2975, "loss": 0.4606, "learning_rate": 0.00019565883257893635, "epoch": 0.9243697478991597, "percentage": 18.49, "elapsed_time": "0:03:03", "remaining_time": "0:13:27"}
+{"current_steps": 560, "total_steps": 2975, "loss": 0.4819, "learning_rate": 0.00019531023098813316, "epoch": 0.9411764705882353, "percentage": 18.82, "elapsed_time": "0:03:06", "remaining_time": "0:13:25"}
+{"current_steps": 570, "total_steps": 2975, "loss": 0.4742, "learning_rate": 0.00019494850324195353, "epoch": 0.957983193277311, "percentage": 19.16, "elapsed_time": "0:03:10", "remaining_time": "0:13:22"}
+{"current_steps": 580, "total_steps": 2975, "loss": 0.4514, "learning_rate": 0.00019457369915765798, "epoch": 0.9747899159663865, "percentage": 19.5, "elapsed_time": "0:03:13", "remaining_time": "0:13:19"}
+{"current_steps": 590, "total_steps": 2975, "loss": 0.4849, "learning_rate": 0.00019418587035338432, "epoch": 0.9915966386554622, "percentage": 19.83, "elapsed_time": "0:03:17", "remaining_time": "0:13:18"}
+{"current_steps": 600, "total_steps": 2975, "loss": 0.4626, "learning_rate": 0.0001937850702410391, "epoch": 1.0084033613445378, "percentage": 20.17, "elapsed_time": "0:03:21", "remaining_time": "0:13:15"}
+{"current_steps": 610, "total_steps": 2975, "loss": 0.4441, "learning_rate": 0.00019337135401894146, "epoch": 1.0252100840336134, "percentage": 20.5, "elapsed_time": "0:03:24", "remaining_time": "0:13:12"}
+{"current_steps": 620, "total_steps": 2975, "loss": 0.4287, "learning_rate": 0.0001929447786642213, "epoch": 1.0420168067226891, "percentage": 20.84, "elapsed_time": "0:03:27", "remaining_time": "0:13:08"}
+{"current_steps": 630, "total_steps": 2975, "loss": 0.4369, "learning_rate": 0.00019250540292497235, "epoch": 1.0588235294117647, "percentage": 21.18, "elapsed_time": "0:03:30", "remaining_time": "0:13:04"}
+{"current_steps": 640, "total_steps": 2975, "loss": 0.4119, "learning_rate": 0.00019205328731216147, "epoch": 1.0756302521008403, "percentage": 21.51, "elapsed_time": "0:03:34", "remaining_time": "0:13:01"}
+{"current_steps": 650, "total_steps": 2975, "loss": 0.4172, "learning_rate": 0.00019158849409129484, "epoch": 1.092436974789916, "percentage": 21.85, "elapsed_time": "0:03:37", "remaining_time": "0:12:56"}
+{"current_steps": 660, "total_steps": 2975, "loss": 0.3912, "learning_rate": 0.00019111108727384296, "epoch": 1.1092436974789917, "percentage": 22.18, "elapsed_time": "0:03:41", "remaining_time": "0:12:57"}
+{"current_steps": 670, "total_steps": 2975, "loss": 0.4656, "learning_rate": 0.00019062113260842476, "epoch": 1.1260504201680672, "percentage": 22.52, "elapsed_time": "0:03:44", "remaining_time": "0:12:53"}
+{"current_steps": 680, "total_steps": 2975, "loss": 0.4059, "learning_rate": 0.0001901186975717529, "epoch": 1.1428571428571428, "percentage": 22.86, "elapsed_time": "0:03:48", "remaining_time": "0:12:51"}
+{"current_steps": 690, "total_steps": 2975, "loss": 0.4013, "learning_rate": 0.0001896038513593407, "epoch": 1.1596638655462184, "percentage": 23.19, "elapsed_time": "0:03:51", "remaining_time": "0:12:46"}
+{"current_steps": 700, "total_steps": 2975, "loss": 0.4278, "learning_rate": 0.00018907666487597257, "epoch": 1.1764705882352942, "percentage": 23.53, "elapsed_time": "0:03:54", "remaining_time": "0:12:42"}
+{"current_steps": 710, "total_steps": 2975, "loss": 0.4112, "learning_rate": 0.00018853721072593894, "epoch": 1.1932773109243697, "percentage": 23.87, "elapsed_time": "0:03:57", "remaining_time": "0:12:38"}
+{"current_steps": 720, "total_steps": 2975, "loss": 0.4518, "learning_rate": 0.00018798556320303718, "epoch": 1.2100840336134453, "percentage": 24.2, "elapsed_time": "0:04:01", "remaining_time": "0:12:34"}
+{"current_steps": 730, "total_steps": 2975, "loss": 0.4132, "learning_rate": 0.00018742179828033992, "epoch": 1.226890756302521, "percentage": 24.54, "elapsed_time": "0:04:04", "remaining_time": "0:12:31"}
+{"current_steps": 740, "total_steps": 2975, "loss": 0.4196, "learning_rate": 0.00018684599359973194, "epoch": 1.2436974789915967, "percentage": 24.87, "elapsed_time": "0:04:07", "remaining_time": "0:12:27"}
+{"current_steps": 750, "total_steps": 2975, "loss": 0.427, "learning_rate": 0.00018625822846121727, "epoch": 1.2605042016806722, "percentage": 25.21, "elapsed_time": "0:04:10", "remaining_time": "0:12:24"}
+{"current_steps": 760, "total_steps": 2975, "loss": 0.3879, "learning_rate": 0.0001856585838119981, "epoch": 1.2773109243697478, "percentage": 25.55, "elapsed_time": "0:04:14", "remaining_time": "0:12:20"}
+{"current_steps": 770, "total_steps": 2975, "loss": 0.44, "learning_rate": 0.0001850471422353265, "epoch": 1.2941176470588236, "percentage": 25.88, "elapsed_time": "0:04:17", "remaining_time": "0:12:18"}
+{"current_steps": 780, "total_steps": 2975, "loss": 0.416, "learning_rate": 0.00018442398793913118, "epoch": 1.3109243697478992, "percentage": 26.22, "elapsed_time": "0:04:21", "remaining_time": "0:12:15"}
+{"current_steps": 790, "total_steps": 2975, "loss": 0.4266, "learning_rate": 0.00018378920674442045, "epoch": 1.3277310924369747, "percentage": 26.55, "elapsed_time": "0:04:24", "remaining_time": "0:12:12"}
+{"current_steps": 800, "total_steps": 2975, "loss": 0.4331, "learning_rate": 0.00018314288607346258, "epoch": 1.3445378151260505, "percentage": 26.89, "elapsed_time": "0:04:28", "remaining_time": "0:12:08"}
+{"current_steps": 810, "total_steps": 2975, "loss": 0.4275, "learning_rate": 0.0001824851149377463, "epoch": 1.361344537815126, "percentage": 27.23, "elapsed_time": "0:04:31", "remaining_time": "0:12:04"}
+{"current_steps": 820, "total_steps": 2975, "loss": 0.4285, "learning_rate": 0.00018181598392572203, "epoch": 1.3781512605042017, "percentage": 27.56, "elapsed_time": "0:04:34", "remaining_time": "0:12:00"}
+{"current_steps": 830, "total_steps": 2975, "loss": 0.3888, "learning_rate": 0.0001811355851903259, "epoch": 1.3949579831932772, "percentage": 27.9, "elapsed_time": "0:04:37", "remaining_time": "0:11:58"}
+{"current_steps": 840, "total_steps": 2975, "loss": 0.4299, "learning_rate": 0.0001804440124362885, "epoch": 1.4117647058823528, "percentage": 28.24, "elapsed_time": "0:04:41", "remaining_time": "0:11:55"}
+{"current_steps": 850, "total_steps": 2975, "loss": 0.4012, "learning_rate": 0.00017974136090722985, "epoch": 1.4285714285714286, "percentage": 28.57, "elapsed_time": "0:04:44", "remaining_time": "0:11:51"}
+{"current_steps": 860, "total_steps": 2975, "loss": 0.4103, "learning_rate": 0.00017902772737254238, "epoch": 1.4453781512605042, "percentage": 28.91, "elapsed_time": "0:04:47", "remaining_time": "0:11:48"}
+{"current_steps": 870, "total_steps": 2975, "loss": 0.4378, "learning_rate": 0.00017830321011406386, "epoch": 1.46218487394958, "percentage": 29.24, "elapsed_time": "0:04:51", "remaining_time": "0:11:45"}
+{"current_steps": 880, "total_steps": 2975, "loss": 0.4021, "learning_rate": 0.00017756790891254194, "epoch": 1.4789915966386555, "percentage": 29.58, "elapsed_time": "0:04:55", "remaining_time": "0:11:42"}
+{"current_steps": 890, "total_steps": 2975, "loss": 0.4364, "learning_rate": 0.00017682192503389236, "epoch": 1.495798319327731, "percentage": 29.92, "elapsed_time": "0:04:58", "remaining_time": "0:11:38"}
+{"current_steps": 900, "total_steps": 2975, "loss": 0.3721, "learning_rate": 0.00017606536121525255, "epoch": 1.5126050420168067, "percentage": 30.25, "elapsed_time": "0:05:01", "remaining_time": "0:11:35"}
+{"current_steps": 910, "total_steps": 2975, "loss": 0.4458, "learning_rate": 0.00017529832165083265, "epoch": 1.5294117647058822, "percentage": 30.59, "elapsed_time": "0:05:05", "remaining_time": "0:11:32"}
+{"current_steps": 920, "total_steps": 2975, "loss": 0.4156, "learning_rate": 0.0001745209119775658, "epoch": 1.5462184873949578, "percentage": 30.92, "elapsed_time": "0:05:09", "remaining_time": "0:11:31"}
+{"current_steps": 930, "total_steps": 2975, "loss": 0.4167, "learning_rate": 0.0001737332392605599, "epoch": 1.5630252100840336, "percentage": 31.26, "elapsed_time": "0:05:12", "remaining_time": "0:11:27"}
+{"current_steps": 940, "total_steps": 2975, "loss": 0.4272, "learning_rate": 0.0001729354119783525, "epoch": 1.5798319327731094, "percentage": 31.6, "elapsed_time": "0:05:15", "remaining_time": "0:11:23"}
+{"current_steps": 950, "total_steps": 2975, "loss": 0.3888, "learning_rate": 0.00017212754000797107, "epoch": 1.596638655462185, "percentage": 31.93, "elapsed_time": "0:05:18", "remaining_time": "0:11:19"}
+{"current_steps": 960, "total_steps": 2975, "loss": 0.4319, "learning_rate": 0.00017130973460980077, "epoch": 1.6134453781512605, "percentage": 32.27, "elapsed_time": "0:05:22", "remaining_time": "0:11:16"}
+{"current_steps": 970, "total_steps": 2975, "loss": 0.4168, "learning_rate": 0.00017048210841226155, "epoch": 1.6302521008403361, "percentage": 32.61, "elapsed_time": "0:05:25", "remaining_time": "0:11:13"}
+{"current_steps": 980, "total_steps": 2975, "loss": 0.427, "learning_rate": 0.00016964477539629702, "epoch": 1.6470588235294117, "percentage": 32.94, "elapsed_time": "0:05:28", "remaining_time": "0:11:09"}
+{"current_steps": 990, "total_steps": 2975, "loss": 0.4284, "learning_rate": 0.0001687978508796769, "epoch": 1.6638655462184873, "percentage": 33.28, "elapsed_time": "0:05:32", "remaining_time": "0:11:05"}
+{"current_steps": 1000, "total_steps": 2975, "loss": 0.4081, "learning_rate": 0.00016794145150111542, "epoch": 1.680672268907563, "percentage": 33.61, "elapsed_time": "0:05:35", "remaining_time": "0:11:02"}
+{"current_steps": 1000, "total_steps": 2975, "eval_loss": 0.469873309135437, "epoch": 1.680672268907563, "percentage": 33.61, "elapsed_time": "0:05:43", "remaining_time": "0:11:19"}
+{"current_steps": 1010, "total_steps": 2975, "loss": 0.4571, "learning_rate": 0.00016707569520420785, "epoch": 1.6974789915966386, "percentage": 33.95, "elapsed_time": "0:05:49", "remaining_time": "0:11:19"}
+{"current_steps": 1020, "total_steps": 2975, "loss": 0.417, "learning_rate": 0.00016620070122118724, "epoch": 1.7142857142857144, "percentage": 34.29, "elapsed_time": "0:05:52", "remaining_time": "0:11:15"}
+{"current_steps": 1030, "total_steps": 2975, "loss": 0.4514, "learning_rate": 0.00016531659005650367, "epoch": 1.73109243697479, "percentage": 34.62, "elapsed_time": "0:05:55", "remaining_time": "0:11:11"}
+{"current_steps": 1040, "total_steps": 2975, "loss": 0.4377, "learning_rate": 0.00016442348347022842, "epoch": 1.7478991596638656, "percentage": 34.96, "elapsed_time": "0:05:58", "remaining_time": "0:11:07"}
+{"current_steps": 1050, "total_steps": 2975, "loss": 0.4159, "learning_rate": 0.0001635215044612851, "epoch": 1.7647058823529411, "percentage": 35.29, "elapsed_time": "0:06:01", "remaining_time": "0:11:03"}
+{"current_steps": 1060, "total_steps": 2975, "loss": 0.4243, "learning_rate": 0.00016261077725051015, "epoch": 1.7815126050420167, "percentage": 35.63, "elapsed_time": "0:06:05", "remaining_time": "0:10:59"}
+{"current_steps": 1070, "total_steps": 2975, "loss": 0.3873, "learning_rate": 0.00016169142726354515, "epoch": 1.7983193277310925, "percentage": 35.97, "elapsed_time": "0:06:08", "remaining_time": "0:10:55"}
+{"current_steps": 1080, "total_steps": 2975, "loss": 0.418, "learning_rate": 0.00016076358111356332, "epoch": 1.815126050420168, "percentage": 36.3, "elapsed_time": "0:06:11", "remaining_time": "0:10:51"}
+{"current_steps": 1090, "total_steps": 2975, "loss": 0.4322, "learning_rate": 0.0001598273665838319, "epoch": 1.8319327731092439, "percentage": 36.64, "elapsed_time": "0:06:14", "remaining_time": "0:10:48"}
+{"current_steps": 1100, "total_steps": 2975, "loss": 0.431, "learning_rate": 0.0001588829126101143, "epoch": 1.8487394957983194, "percentage": 36.97, "elapsed_time": "0:06:17", "remaining_time": "0:10:43"}
+{"current_steps": 1110, "total_steps": 2975, "loss": 0.4301, "learning_rate": 0.0001579303492629126, "epoch": 1.865546218487395, "percentage": 37.31, "elapsed_time": "0:06:21", "remaining_time": "0:10:40"}
+{"current_steps": 1120, "total_steps": 2975, "loss": 0.4376, "learning_rate": 0.0001569698077295545, "epoch": 1.8823529411764706, "percentage": 37.65, "elapsed_time": "0:06:24", "remaining_time": "0:10:36"}
+{"current_steps": 1130, "total_steps": 2975, "loss": 0.4321, "learning_rate": 0.00015600142029612596, "epoch": 1.8991596638655461, "percentage": 37.98, "elapsed_time": "0:06:27", "remaining_time": "0:10:32"}
+{"current_steps": 1140, "total_steps": 2975, "loss": 0.4931, "learning_rate": 0.00015502532032925283, "epoch": 1.9159663865546217, "percentage": 38.32, "elapsed_time": "0:06:30", "remaining_time": "0:10:28"}
+{"current_steps": 1150, "total_steps": 2975, "loss": 0.4143, "learning_rate": 0.0001540416422577335, "epoch": 1.9327731092436975, "percentage": 38.66, "elapsed_time": "0:06:33", "remaining_time": "0:10:24"}
+{"current_steps": 1160, "total_steps": 2975, "loss": 0.4577, "learning_rate": 0.00015305052155402545, "epoch": 1.949579831932773, "percentage": 38.99, "elapsed_time": "0:06:37", "remaining_time": "0:10:21"}
+{"current_steps": 1170, "total_steps": 2975, "loss": 0.4184, "learning_rate": 0.0001520520947155877, "epoch": 1.9663865546218489, "percentage": 39.33, "elapsed_time": "0:06:40", "remaining_time": "0:10:18"}
+{"current_steps": 1180, "total_steps": 2975, "loss": 0.3933, "learning_rate": 0.00015104649924608252, "epoch": 1.9831932773109244, "percentage": 39.66, "elapsed_time": "0:06:44", "remaining_time": "0:10:15"}
+{"current_steps": 1190, "total_steps": 2975, "loss": 0.3885, "learning_rate": 0.00015003387363643836, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "0:06:48", "remaining_time": "0:10:12"}
+{"current_steps": 1200, "total_steps": 2975, "loss": 0.3581, "learning_rate": 0.00014901435734577677, "epoch": 2.0168067226890756, "percentage": 40.34, "elapsed_time": "0:06:51", "remaining_time": "0:10:07"}
+{"current_steps": 1210, "total_steps": 2975, "loss": 0.3139, "learning_rate": 0.0001479880907822061, "epoch": 2.033613445378151, "percentage": 40.67, "elapsed_time": "0:06:54", "remaining_time": "0:10:04"}
+{"current_steps": 1220, "total_steps": 2975, "loss": 0.3298, "learning_rate": 0.00014695521528348447, "epoch": 2.0504201680672267, "percentage": 41.01, "elapsed_time": "0:06:57", "remaining_time": "0:10:00"}
+{"current_steps": 1230, "total_steps": 2975, "loss": 0.3193, "learning_rate": 0.00014591587309755464, "epoch": 2.0672268907563027, "percentage": 41.34, "elapsed_time": "0:07:01", "remaining_time": "0:09:57"}
+{"current_steps": 1240, "total_steps": 2975, "loss": 0.3035, "learning_rate": 0.00014487020736295354, "epoch": 2.0840336134453783, "percentage": 41.68, "elapsed_time": "0:07:04", "remaining_time": "0:09:53"}
+{"current_steps": 1250, "total_steps": 2975, "loss": 0.3432, "learning_rate": 0.00014381836208909927, "epoch": 2.100840336134454, "percentage": 42.02, "elapsed_time": "0:07:08", "remaining_time": "0:09:50"}
+{"current_steps": 1260, "total_steps": 2975, "loss": 0.3214, "learning_rate": 0.00014276048213645809, "epoch": 2.1176470588235294, "percentage": 42.35, "elapsed_time": "0:07:11", "remaining_time": "0:09:47"}
+{"current_steps": 1270, "total_steps": 2975, "loss": 0.3571, "learning_rate": 0.0001416967131965941, "epoch": 2.134453781512605, "percentage": 42.69, "elapsed_time": "0:07:14", "remaining_time": "0:09:43"}
+{"current_steps": 1280, "total_steps": 2975, "loss": 0.3357, "learning_rate": 0.00014062720177210455, "epoch": 2.1512605042016806, "percentage": 43.03, "elapsed_time": "0:07:18", "remaining_time": "0:09:40"}
+{"current_steps": 1290, "total_steps": 2975, "loss": 0.3249, "learning_rate": 0.00013955209515644363, "epoch": 2.168067226890756, "percentage": 43.36, "elapsed_time": "0:07:21", "remaining_time": "0:09:36"}
+{"current_steps": 1300, "total_steps": 2975, "loss": 0.3485, "learning_rate": 0.00013847154141363691, "epoch": 2.184873949579832, "percentage": 43.7, "elapsed_time": "0:07:25", "remaining_time": "0:09:33"}
+{"current_steps": 1310, "total_steps": 2975, "loss": 0.3311, "learning_rate": 0.00013738568935789015, "epoch": 2.2016806722689077, "percentage": 44.03, "elapsed_time": "0:07:28", "remaining_time": "0:09:29"}
+{"current_steps": 1320, "total_steps": 2975, "loss": 0.3137, "learning_rate": 0.00013629468853309433, "epoch": 2.2184873949579833, "percentage": 44.37, "elapsed_time": "0:07:31", "remaining_time": "0:09:26"}
+{"current_steps": 1330, "total_steps": 2975, "loss": 0.3484, "learning_rate": 0.00013519868919223069, "epoch": 2.235294117647059, "percentage": 44.71, "elapsed_time": "0:07:34", "remaining_time": "0:09:22"}
+{"current_steps": 1340, "total_steps": 2975, "loss": 0.3316, "learning_rate": 0.00013409784227667762, "epoch": 2.2521008403361344, "percentage": 45.04, "elapsed_time": "0:07:37", "remaining_time": "0:09:18"}
+{"current_steps": 1350, "total_steps": 2975, "loss": 0.3169, "learning_rate": 0.00013299229939542302, "epoch": 2.26890756302521, "percentage": 45.38, "elapsed_time": "0:07:40", "remaining_time": "0:09:14"}
+{"current_steps": 1360, "total_steps": 2975, "loss": 0.3573, "learning_rate": 0.00013188221280418472, "epoch": 2.2857142857142856, "percentage": 45.71, "elapsed_time": "0:07:43", "remaining_time": "0:09:10"}
+{"current_steps": 1370, "total_steps": 2975, "loss": 0.3157, "learning_rate": 0.0001307677353844417, "epoch": 2.302521008403361, "percentage": 46.05, "elapsed_time": "0:07:47", "remaining_time": "0:09:08"}
+{"current_steps": 1380, "total_steps": 2975, "loss": 0.3192, "learning_rate": 0.0001296490206223793, "epoch": 2.3193277310924367, "percentage": 46.39, "elapsed_time": "0:07:51", "remaining_time": "0:09:04"}
+{"current_steps": 1390, "total_steps": 2975, "loss": 0.3136, "learning_rate": 0.000128526222587751, "epoch": 2.3361344537815127, "percentage": 46.72, "elapsed_time": "0:07:55", "remaining_time": "0:09:01"}
+{"current_steps": 1400, "total_steps": 2975, "loss": 0.3157, "learning_rate": 0.00012739949591265975, "epoch": 2.3529411764705883, "percentage": 47.06, "elapsed_time": "0:07:58", "remaining_time": "0:08:58"}
+{"current_steps": 1410, "total_steps": 2975, "loss": 0.3448, "learning_rate": 0.0001262689957702623, "epoch": 2.369747899159664, "percentage": 47.39, "elapsed_time": "0:08:01", "remaining_time": "0:08:54"}
+{"current_steps": 1420, "total_steps": 2975, "loss": 0.3492, "learning_rate": 0.00012513487785339832, "epoch": 2.3865546218487395, "percentage": 47.73, "elapsed_time": "0:08:04", "remaining_time": "0:08:51"}
+{"current_steps": 1430, "total_steps": 2975, "loss": 0.3318, "learning_rate": 0.0001239972983531487, "epoch": 2.403361344537815, "percentage": 48.07, "elapsed_time": "0:08:08", "remaining_time": "0:08:47"}
+{"current_steps": 1440, "total_steps": 2975, "loss": 0.3171, "learning_rate": 0.00012285641393732462, "epoch": 2.4201680672268906, "percentage": 48.4, "elapsed_time": "0:08:11", "remaining_time": "0:08:43"}
+{"current_steps": 1450, "total_steps": 2975, "loss": 0.3426, "learning_rate": 0.00012171238172889135, "epoch": 2.4369747899159666, "percentage": 48.74, "elapsed_time": "0:08:14", "remaining_time": "0:08:39"}
+{"current_steps": 1460, "total_steps": 2975, "loss": 0.3198, "learning_rate": 0.00012056535928432902, "epoch": 2.453781512605042, "percentage": 49.08, "elapsed_time": "0:08:17", "remaining_time": "0:08:36"}
+{"current_steps": 1470, "total_steps": 2975, "loss": 0.3535, "learning_rate": 0.00011941550457193418, "epoch": 2.4705882352941178, "percentage": 49.41, "elapsed_time": "0:08:21", "remaining_time": "0:08:33"}
+{"current_steps": 1480, "total_steps": 2975, "loss": 0.3141, "learning_rate": 0.00011826297595006417, "epoch": 2.4873949579831933, "percentage": 49.75, "elapsed_time": "0:08:24", "remaining_time": "0:08:29"}
+{"current_steps": 1490, "total_steps": 2975, "loss": 0.3435, "learning_rate": 0.00011710793214532791, "epoch": 2.504201680672269, "percentage": 50.08, "elapsed_time": "0:08:28", "remaining_time": "0:08:26"}
+{"current_steps": 1500, "total_steps": 2975, "loss": 0.3532, "learning_rate": 0.00011595053223072623, "epoch": 2.5210084033613445, "percentage": 50.42, "elapsed_time": "0:08:31", "remaining_time": "0:08:23"}
+{"current_steps": 1510, "total_steps": 2975, "loss": 0.327, "learning_rate": 0.00011479093560374406, "epoch": 2.53781512605042, "percentage": 50.76, "elapsed_time": "0:08:34", "remaining_time": "0:08:19"}
+{"current_steps": 1520, "total_steps": 2975, "loss": 0.3564, "learning_rate": 0.00011362930196439832, "epoch": 2.5546218487394956, "percentage": 51.09, "elapsed_time": "0:08:38", "remaining_time": "0:08:15"}
+{"current_steps": 1530, "total_steps": 2975, "loss": 0.3281, "learning_rate": 0.00011246579129324393, "epoch": 2.571428571428571, "percentage": 51.43, "elapsed_time": "0:08:41", "remaining_time": "0:08:12"}
+{"current_steps": 1540, "total_steps": 2975, "loss": 0.3361, "learning_rate": 0.00011130056382934115, "epoch": 2.588235294117647, "percentage": 51.76, "elapsed_time": "0:08:44", "remaining_time": "0:08:08"}
+{"current_steps": 1550, "total_steps": 2975, "loss": 0.3317, "learning_rate": 0.00011013378004818762, "epoch": 2.6050420168067228, "percentage": 52.1, "elapsed_time": "0:08:48", "remaining_time": "0:08:05"}
+{"current_steps": 1560, "total_steps": 2975, "loss": 0.3243, "learning_rate": 0.00010896560063961732, "epoch": 2.6218487394957983, "percentage": 52.44, "elapsed_time": "0:08:51", "remaining_time": "0:08:02"}
+{"current_steps": 1570, "total_steps": 2975, "loss": 0.3443, "learning_rate": 0.00010779618648567058, "epoch": 2.638655462184874, "percentage": 52.77, "elapsed_time": "0:08:54", "remaining_time": "0:07:58"}
+{"current_steps": 1580, "total_steps": 2975, "loss": 0.3314, "learning_rate": 0.00010662569863843725, "epoch": 2.6554621848739495, "percentage": 53.11, "elapsed_time": "0:08:58", "remaining_time": "0:07:55"}
+{"current_steps": 1590, "total_steps": 2975, "loss": 0.3219, "learning_rate": 0.00010545429829787659, "epoch": 2.6722689075630255, "percentage": 53.45, "elapsed_time": "0:09:01", "remaining_time": "0:07:51"}
+{"current_steps": 1600, "total_steps": 2975, "loss": 0.3445, "learning_rate": 0.00010428214678961668, "epoch": 2.689075630252101, "percentage": 53.78, "elapsed_time": "0:09:05", "remaining_time": "0:07:48"}
+{"current_steps": 1610, "total_steps": 2975, "loss": 0.3459, "learning_rate": 0.00010310940554273663, "epoch": 2.7058823529411766, "percentage": 54.12, "elapsed_time": "0:09:08", "remaining_time": "0:07:45"}
+{"current_steps": 1620, "total_steps": 2975, "loss": 0.3121, "learning_rate": 0.00010193623606753464, "epoch": 2.722689075630252, "percentage": 54.45, "elapsed_time": "0:09:11", "remaining_time": "0:07:41"}
+{"current_steps": 1630, "total_steps": 2975, "loss": 0.34, "learning_rate": 0.00010076279993328455, "epoch": 2.7394957983193278, "percentage": 54.79, "elapsed_time": "0:09:14", "remaining_time": "0:07:37"}
+{"current_steps": 1640, "total_steps": 2975, "loss": 0.298, "learning_rate": 9.958925874598464e-05, "epoch": 2.7563025210084033, "percentage": 55.13, "elapsed_time": "0:09:18", "remaining_time": "0:07:34"}
+{"current_steps": 1650, "total_steps": 2975, "loss": 0.3519, "learning_rate": 9.841577412610108e-05, "epoch": 2.773109243697479, "percentage": 55.46, "elapsed_time": "0:09:21", "remaining_time": "0:07:30"}
+{"current_steps": 1660, "total_steps": 2975, "loss": 0.3373, "learning_rate": 9.724250768630959e-05, "epoch": 2.7899159663865545, "percentage": 55.8, "elapsed_time": "0:09:24", "remaining_time": "0:07:27"}
+{"current_steps": 1670, "total_steps": 2975, "loss": 0.3061, "learning_rate": 9.606962100923807e-05, "epoch": 2.80672268907563, "percentage": 56.13, "elapsed_time": "0:09:28", "remaining_time": "0:07:24"}
+{"current_steps": 1680, "total_steps": 2975, "loss": 0.3478, "learning_rate": 9.489727562521332e-05, "epoch": 2.8235294117647056, "percentage": 56.47, "elapsed_time": "0:09:31", "remaining_time": "0:07:20"}
+{"current_steps": 1690, "total_steps": 2975, "loss": 0.3242, "learning_rate": 9.372563299001514e-05, "epoch": 2.8403361344537816, "percentage": 56.81, "elapsed_time": "0:09:34", "remaining_time": "0:07:17"}
+{"current_steps": 1700, "total_steps": 2975, "loss": 0.3093, "learning_rate": 9.255485446264046e-05, "epoch": 2.857142857142857, "percentage": 57.14, "elapsed_time": "0:09:38", "remaining_time": "0:07:13"}
+{"current_steps": 1710, "total_steps": 2975, "loss": 0.3608, "learning_rate": 9.138510128308117e-05, "epoch": 2.8739495798319328, "percentage": 57.48, "elapsed_time": "0:09:41", "remaining_time": "0:07:10"}
+{"current_steps": 1720, "total_steps": 2975, "loss": 0.3247, "learning_rate": 9.021653455011778e-05, "epoch": 2.8907563025210083, "percentage": 57.82, "elapsed_time": "0:09:44", "remaining_time": "0:07:06"}
+{"current_steps": 1730, "total_steps": 2975, "loss": 0.354, "learning_rate": 8.904931519913304e-05, "epoch": 2.907563025210084, "percentage": 58.15, "elapsed_time": "0:09:48", "remaining_time": "0:07:03"}
+{"current_steps": 1740, "total_steps": 2975, "loss": 0.3406, "learning_rate": 8.788360397994785e-05, "epoch": 2.92436974789916, "percentage": 58.49, "elapsed_time": "0:09:51", "remaining_time": "0:07:00"}
+{"current_steps": 1750, "total_steps": 2975, "loss": 0.3388, "learning_rate": 8.671956143468267e-05, "epoch": 2.9411764705882355, "percentage": 58.82, "elapsed_time": "0:09:55", "remaining_time": "0:06:56"}
+{"current_steps": 1760, "total_steps": 2975, "loss": 0.3676, "learning_rate": 8.55573478756477e-05, "epoch": 2.957983193277311, "percentage": 59.16, "elapsed_time": "0:09:58", "remaining_time": "0:06:53"}
+{"current_steps": 1770, "total_steps": 2975, "loss": 0.3152, "learning_rate": 8.439712336326452e-05, "epoch": 2.9747899159663866, "percentage": 59.5, "elapsed_time": "0:10:01", "remaining_time": "0:06:49"}
+{"current_steps": 1780, "total_steps": 2975, "loss": 0.3575, "learning_rate": 8.32390476840227e-05, "epoch": 2.991596638655462, "percentage": 59.83, "elapsed_time": "0:10:05", "remaining_time": "0:06:46"}
+{"current_steps": 1790, "total_steps": 2975, "loss": 0.2936, "learning_rate": 8.208328032847366e-05, "epoch": 3.008403361344538, "percentage": 60.17, "elapsed_time": "0:10:08", "remaining_time": "0:06:42"}
+{"current_steps": 1800, "total_steps": 2975, "loss": 0.2582, "learning_rate": 8.092998046926583e-05, "epoch": 3.0252100840336134, "percentage": 60.5, "elapsed_time": "0:10:11", "remaining_time": "0:06:39"}
+{"current_steps": 1810, "total_steps": 2975, "loss": 0.2324, "learning_rate": 7.977930693922329e-05, "epoch": 3.042016806722689, "percentage": 60.84, "elapsed_time": "0:10:15", "remaining_time": "0:06:35"}
+{"current_steps": 1820, "total_steps": 2975, "loss": 0.2219, "learning_rate": 7.863141820947114e-05, "epoch": 3.0588235294117645, "percentage": 61.18, "elapsed_time": "0:10:18", "remaining_time": "0:06:32"}
+{"current_steps": 1830, "total_steps": 2975, "loss": 0.2201, "learning_rate": 7.748647236761094e-05, "epoch": 3.0756302521008405, "percentage": 61.51, "elapsed_time": "0:10:21", "remaining_time": "0:06:28"}
+{"current_steps": 1840, "total_steps": 2975, "loss": 0.2664, "learning_rate": 7.63446270959488e-05, "epoch": 3.092436974789916, "percentage": 61.85, "elapsed_time": "0:10:24", "remaining_time": "0:06:25"}
+{"current_steps": 1850, "total_steps": 2975, "loss": 0.2426, "learning_rate": 7.520603964977939e-05, "epoch": 3.1092436974789917, "percentage": 62.18, "elapsed_time": "0:10:27", "remaining_time": "0:06:21"}
+{"current_steps": 1860, "total_steps": 2975, "loss": 0.2297, "learning_rate": 7.407086683572846e-05, "epoch": 3.1260504201680672, "percentage": 62.52, "elapsed_time": "0:10:31", "remaining_time": "0:06:18"}
+{"current_steps": 1870, "total_steps": 2975, "loss": 0.257, "learning_rate": 7.293926499015763e-05, "epoch": 3.142857142857143, "percentage": 62.86, "elapsed_time": "0:10:35", "remaining_time": "0:06:15"}
+{"current_steps": 1880, "total_steps": 2975, "loss": 0.2374, "learning_rate": 7.181138995763362e-05, "epoch": 3.1596638655462184, "percentage": 63.19, "elapsed_time": "0:10:38", "remaining_time": "0:06:11"}
+{"current_steps": 1890, "total_steps": 2975, "loss": 0.2389, "learning_rate": 7.068739706946517e-05, "epoch": 3.176470588235294, "percentage": 63.53, "elapsed_time": "0:10:41", "remaining_time": "0:06:08"}
+{"current_steps": 1900, "total_steps": 2975, "loss": 0.2466, "learning_rate": 6.956744112231095e-05, "epoch": 3.19327731092437, "percentage": 63.87, "elapsed_time": "0:10:44", "remaining_time": "0:06:04"}
+{"current_steps": 1910, "total_steps": 2975, "loss": 0.2369, "learning_rate": 6.845167635686083e-05, "epoch": 3.2100840336134455, "percentage": 64.2, "elapsed_time": "0:10:47", "remaining_time": "0:06:01"}
+{"current_steps": 1920, "total_steps": 2975, "loss": 0.216, "learning_rate": 6.73402564365938e-05, "epoch": 3.226890756302521, "percentage": 64.54, "elapsed_time": "0:10:51", "remaining_time": "0:05:57"}
+{"current_steps": 1930, "total_steps": 2975, "loss": 0.2449, "learning_rate": 6.623333442661532e-05, "epoch": 3.2436974789915967, "percentage": 64.87, "elapsed_time": "0:10:54", "remaining_time": "0:05:54"}
+{"current_steps": 1940, "total_steps": 2975, "loss": 0.2361, "learning_rate": 6.513106277257728e-05, "epoch": 3.2605042016806722, "percentage": 65.21, "elapsed_time": "0:10:57", "remaining_time": "0:05:50"}
+{"current_steps": 1950, "total_steps": 2975, "loss": 0.2136, "learning_rate": 6.403359327968303e-05, "epoch": 3.277310924369748, "percentage": 65.55, "elapsed_time": "0:11:00", "remaining_time": "0:05:47"}
+{"current_steps": 1960, "total_steps": 2975, "loss": 0.2457, "learning_rate": 6.294107709178079e-05, "epoch": 3.2941176470588234, "percentage": 65.88, "elapsed_time": "0:11:03", "remaining_time": "0:05:43"}
+{"current_steps": 1970, "total_steps": 2975, "loss": 0.2184, "learning_rate": 6.185366467054799e-05, "epoch": 3.310924369747899, "percentage": 66.22, "elapsed_time": "0:11:07", "remaining_time": "0:05:40"}
+{"current_steps": 1980, "total_steps": 2975, "loss": 0.2419, "learning_rate": 6.0771505774769734e-05, "epoch": 3.327731092436975, "percentage": 66.55, "elapsed_time": "0:11:10", "remaining_time": "0:05:37"}
+{"current_steps": 1990, "total_steps": 2975, "loss": 0.2559, "learning_rate": 5.9694749439713936e-05, "epoch": 3.3445378151260505, "percentage": 66.89, "elapsed_time": "0:11:14", "remaining_time": "0:05:33"}
+{"current_steps": 2000, "total_steps": 2975, "loss": 0.2383, "learning_rate": 5.8623543956606074e-05, "epoch": 3.361344537815126, "percentage": 67.23, "elapsed_time": "0:11:17", "remaining_time": "0:05:30"}
+{"current_steps": 2000, "total_steps": 2975, "eval_loss": 0.5869996547698975, "epoch": 3.361344537815126, "percentage": 67.23, "elapsed_time": "0:11:26", "remaining_time": "0:05:34"}
+{"current_steps": 2010, "total_steps": 2975, "loss": 0.2554, "learning_rate": 5.7558036852206596e-05, "epoch": 3.3781512605042017, "percentage": 67.56, "elapsed_time": "0:11:30", "remaining_time": "0:05:31"}
+{"current_steps": 2020, "total_steps": 2975, "loss": 0.2682, "learning_rate": 5.6498374868493296e-05, "epoch": 3.3949579831932772, "percentage": 67.9, "elapsed_time": "0:11:34", "remaining_time": "0:05:28"}
+{"current_steps": 2030, "total_steps": 2975, "loss": 0.2347, "learning_rate": 5.544470394245225e-05, "epoch": 3.411764705882353, "percentage": 68.24, "elapsed_time": "0:11:38", "remaining_time": "0:05:24"}
+{"current_steps": 2040, "total_steps": 2975, "loss": 0.2561, "learning_rate": 5.439716918597906e-05, "epoch": 3.4285714285714284, "percentage": 68.57, "elapsed_time": "0:11:41", "remaining_time": "0:05:21"}
+{"current_steps": 2050, "total_steps": 2975, "loss": 0.2087, "learning_rate": 5.335591486589406e-05, "epoch": 3.4453781512605044, "percentage": 68.91, "elapsed_time": "0:11:44", "remaining_time": "0:05:17"}
+{"current_steps": 2060, "total_steps": 2975, "loss": 0.2323, "learning_rate": 5.232108438407399e-05, "epoch": 3.46218487394958, "percentage": 69.24, "elapsed_time": "0:11:47", "remaining_time": "0:05:14"}
+{"current_steps": 2070, "total_steps": 2975, "loss": 0.2275, "learning_rate": 5.129282025770252e-05, "epoch": 3.4789915966386555, "percentage": 69.58, "elapsed_time": "0:11:52", "remaining_time": "0:05:11"}
+{"current_steps": 2080, "total_steps": 2975, "loss": 0.2136, "learning_rate": 5.027126409964271e-05, "epoch": 3.495798319327731, "percentage": 69.92, "elapsed_time": "0:11:55", "remaining_time": "0:05:08"}
+{"current_steps": 2090, "total_steps": 2975, "loss": 0.2381, "learning_rate": 4.9256556598934054e-05, "epoch": 3.5126050420168067, "percentage": 70.25, "elapsed_time": "0:11:59", "remaining_time": "0:05:04"}
+{"current_steps": 2100, "total_steps": 2975, "loss": 0.2394, "learning_rate": 4.82488375014169e-05, "epoch": 3.5294117647058822, "percentage": 70.59, "elapsed_time": "0:12:02", "remaining_time": "0:05:00"}
+{"current_steps": 2110, "total_steps": 2975, "loss": 0.2411, "learning_rate": 4.7248245590486375e-05, "epoch": 3.546218487394958, "percentage": 70.92, "elapsed_time": "0:12:05", "remaining_time": "0:04:57"}
+{"current_steps": 2120, "total_steps": 2975, "loss": 0.2383, "learning_rate": 4.625491866797917e-05, "epoch": 3.5630252100840334, "percentage": 71.26, "elapsed_time": "0:12:08", "remaining_time": "0:04:53"}
+{"current_steps": 2130, "total_steps": 2975, "loss": 0.264, "learning_rate": 4.526899353519557e-05, "epoch": 3.5798319327731094, "percentage": 71.6, "elapsed_time": "0:12:11", "remaining_time": "0:04:50"}
+{"current_steps": 2140, "total_steps": 2975, "loss": 0.2412, "learning_rate": 4.4290605974058995e-05, "epoch": 3.596638655462185, "percentage": 71.93, "elapsed_time": "0:12:15", "remaining_time": "0:04:46"}
+{"current_steps": 2150, "total_steps": 2975, "loss": 0.2408, "learning_rate": 4.331989072841604e-05, "epoch": 3.6134453781512605, "percentage": 72.27, "elapsed_time": "0:12:18", "remaining_time": "0:04:43"}
+{"current_steps": 2160, "total_steps": 2975, "loss": 0.2347, "learning_rate": 4.235698148547955e-05, "epoch": 3.630252100840336, "percentage": 72.61, "elapsed_time": "0:12:21", "remaining_time": "0:04:39"}
+{"current_steps": 2170, "total_steps": 2975, "loss": 0.2454, "learning_rate": 4.140201085741731e-05, "epoch": 3.6470588235294117, "percentage": 72.94, "elapsed_time": "0:12:25", "remaining_time": "0:04:36"}
+{"current_steps": 2180, "total_steps": 2975, "loss": 0.2381, "learning_rate": 4.0455110363088424e-05, "epoch": 3.6638655462184873, "percentage": 73.28, "elapsed_time": "0:12:28", "remaining_time": "0:04:32"}
+{"current_steps": 2190, "total_steps": 2975, "loss": 0.2432, "learning_rate": 3.9516410409930594e-05, "epoch": 3.6806722689075633, "percentage": 73.61, "elapsed_time": "0:12:31", "remaining_time": "0:04:29"}
+{"current_steps": 2200, "total_steps": 2975, "loss": 0.2387, "learning_rate": 3.858604027600049e-05, "epoch": 3.697478991596639, "percentage": 73.95, "elapsed_time": "0:12:34", "remaining_time": "0:04:25"}
+{"current_steps": 2210, "total_steps": 2975, "loss": 0.2482, "learning_rate": 3.766412809216937e-05, "epoch": 3.7142857142857144, "percentage": 74.29, "elapsed_time": "0:12:38", "remaining_time": "0:04:22"}
+{"current_steps": 2220, "total_steps": 2975, "loss": 0.2524, "learning_rate": 3.675080082447688e-05, "epoch": 3.73109243697479, "percentage": 74.62, "elapsed_time": "0:12:42", "remaining_time": "0:04:19"}
+{"current_steps": 2230, "total_steps": 2975, "loss": 0.2477, "learning_rate": 3.584618425664526e-05, "epoch": 3.7478991596638656, "percentage": 74.96, "elapsed_time": "0:12:45", "remaining_time": "0:04:15"}
+{"current_steps": 2240, "total_steps": 2975, "loss": 0.2194, "learning_rate": 3.495040297275651e-05, "epoch": 3.764705882352941, "percentage": 75.29, "elapsed_time": "0:12:48", "remaining_time": "0:04:12"}
+{"current_steps": 2250, "total_steps": 2975, "loss": 0.2414, "learning_rate": 3.40635803400944e-05, "epoch": 3.7815126050420167, "percentage": 75.63, "elapsed_time": "0:12:52", "remaining_time": "0:04:08"}
+{"current_steps": 2260, "total_steps": 2975, "loss": 0.2218, "learning_rate": 3.3185838492154386e-05, "epoch": 3.7983193277310923, "percentage": 75.97, "elapsed_time": "0:12:55", "remaining_time": "0:04:05"}
+{"current_steps": 2270, "total_steps": 2975, "loss": 0.2312, "learning_rate": 3.231729831182344e-05, "epoch": 3.815126050420168, "percentage": 76.3, "elapsed_time": "0:12:58", "remaining_time": "0:04:01"}
+{"current_steps": 2280, "total_steps": 2975, "loss": 0.2317, "learning_rate": 3.1458079414731955e-05, "epoch": 3.831932773109244, "percentage": 76.64, "elapsed_time": "0:13:01", "remaining_time": "0:03:58"}
+{"current_steps": 2290, "total_steps": 2975, "loss": 0.2222, "learning_rate": 3.060830013278012e-05, "epoch": 3.8487394957983194, "percentage": 76.97, "elapsed_time": "0:13:04", "remaining_time": "0:03:54"}
+{"current_steps": 2300, "total_steps": 2975, "loss": 0.2313, "learning_rate": 2.9768077497841352e-05, "epoch": 3.865546218487395, "percentage": 77.31, "elapsed_time": "0:13:08", "remaining_time": "0:03:51"}
+{"current_steps": 2310, "total_steps": 2975, "loss": 0.231, "learning_rate": 2.8937527225644677e-05, "epoch": 3.8823529411764706, "percentage": 77.65, "elapsed_time": "0:13:11", "remaining_time": "0:03:47"}
+{"current_steps": 2320, "total_steps": 2975, "loss": 0.2504, "learning_rate": 2.8116763699838167e-05, "epoch": 3.899159663865546, "percentage": 77.98, "elapsed_time": "0:13:15", "remaining_time": "0:03:44"}
+{"current_steps": 2330, "total_steps": 2975, "loss": 0.24, "learning_rate": 2.7305899956236046e-05, "epoch": 3.9159663865546217, "percentage": 78.32, "elapsed_time": "0:13:18", "remaining_time": "0:03:41"}
+{"current_steps": 2340, "total_steps": 2975, "loss": 0.2478, "learning_rate": 2.6505047667251437e-05, "epoch": 3.9327731092436977, "percentage": 78.66, "elapsed_time": "0:13:21", "remaining_time": "0:03:37"}
+{"current_steps": 2350, "total_steps": 2975, "loss": 0.2419, "learning_rate": 2.5714317126516763e-05, "epoch": 3.9495798319327733, "percentage": 78.99, "elapsed_time": "0:13:24", "remaining_time": "0:03:34"}
+{"current_steps": 2360, "total_steps": 2975, "loss": 0.2341, "learning_rate": 2.493381723369398e-05, "epoch": 3.966386554621849, "percentage": 79.33, "elapsed_time": "0:13:28", "remaining_time": "0:03:30"}
+{"current_steps": 2370, "total_steps": 2975, "loss": 0.213, "learning_rate": 2.4163655479476943e-05, "epoch": 3.9831932773109244, "percentage": 79.66, "elapsed_time": "0:13:31", "remaining_time": "0:03:27"}
+{"current_steps": 2380, "total_steps": 2975, "loss": 0.2302, "learning_rate": 2.340393793078789e-05, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "0:13:34", "remaining_time": "0:03:23"}
+{"current_steps": 2390, "total_steps": 2975, "loss": 0.1944, "learning_rate": 2.2654769216169602e-05, "epoch": 4.016806722689076, "percentage": 80.34, "elapsed_time": "0:13:38", "remaining_time": "0:03:20"}
+{"current_steps": 2400, "total_steps": 2975, "loss": 0.172, "learning_rate": 2.1916252511376133e-05, "epoch": 4.033613445378151, "percentage": 80.67, "elapsed_time": "0:13:41", "remaining_time": "0:03:16"}
+{"current_steps": 2410, "total_steps": 2975, "loss": 0.166, "learning_rate": 2.1188489525163367e-05, "epoch": 4.050420168067227, "percentage": 81.01, "elapsed_time": "0:13:44", "remaining_time": "0:03:13"}
+{"current_steps": 2420, "total_steps": 2975, "loss": 0.1421, "learning_rate": 2.047158048528165e-05, "epoch": 4.067226890756302, "percentage": 81.34, "elapsed_time": "0:13:47", "remaining_time": "0:03:09"}
+{"current_steps": 2430, "total_steps": 2975, "loss": 0.174, "learning_rate": 1.976562412467232e-05, "epoch": 4.084033613445378, "percentage": 81.68, "elapsed_time": "0:13:51", "remaining_time": "0:03:06"}
+{"current_steps": 2440, "total_steps": 2975, "loss": 0.1725, "learning_rate": 1.9070717667870263e-05, "epoch": 4.100840336134453, "percentage": 82.02, "elapsed_time": "0:13:54", "remaining_time": "0:03:03"}
+{"current_steps": 2450, "total_steps": 2975, "loss": 0.1777, "learning_rate": 1.838695681761412e-05, "epoch": 4.117647058823529, "percentage": 82.35, "elapsed_time": "0:13:58", "remaining_time": "0:02:59"}
+{"current_steps": 2460, "total_steps": 2975, "loss": 0.1541, "learning_rate": 1.7714435741666037e-05, "epoch": 4.1344537815126055, "percentage": 82.69, "elapsed_time": "0:14:01", "remaining_time": "0:02:56"}
+{"current_steps": 2470, "total_steps": 2975, "loss": 0.1905, "learning_rate": 1.7053247059842793e-05, "epoch": 4.151260504201681, "percentage": 83.03, "elapsed_time": "0:14:04", "remaining_time": "0:02:52"}
+{"current_steps": 2480, "total_steps": 2975, "loss": 0.1803, "learning_rate": 1.6403481831260338e-05, "epoch": 4.168067226890757, "percentage": 83.36, "elapsed_time": "0:14:08", "remaining_time": "0:02:49"}
+{"current_steps": 2490, "total_steps": 2975, "loss": 0.1691, "learning_rate": 1.5765229541792982e-05, "epoch": 4.184873949579832, "percentage": 83.7, "elapsed_time": "0:14:11", "remaining_time": "0:02:45"}
+{"current_steps": 2500, "total_steps": 2975, "loss": 0.1706, "learning_rate": 1.5138578091749334e-05, "epoch": 4.201680672268908, "percentage": 84.03, "elapsed_time": "0:14:14", "remaining_time": "0:02:42"}
+{"current_steps": 2510, "total_steps": 2975, "loss": 0.1795, "learning_rate": 1.4523613783766732e-05, "epoch": 4.218487394957983, "percentage": 84.37, "elapsed_time": "0:14:18", "remaining_time": "0:02:38"}
+{"current_steps": 2520, "total_steps": 2975, "loss": 0.1614, "learning_rate": 1.3920421310925636e-05, "epoch": 4.235294117647059, "percentage": 84.71, "elapsed_time": "0:14:21", "remaining_time": "0:02:35"}
+{"current_steps": 2530, "total_steps": 2975, "loss": 0.1621, "learning_rate": 1.3329083745085547e-05, "epoch": 4.2521008403361344, "percentage": 85.04, "elapsed_time": "0:14:24", "remaining_time": "0:02:32"}
+{"current_steps": 2540, "total_steps": 2975, "loss": 0.1642, "learning_rate": 1.2749682525444407e-05, "epoch": 4.26890756302521, "percentage": 85.38, "elapsed_time": "0:14:27", "remaining_time": "0:02:28"}
+{"current_steps": 2550, "total_steps": 2975, "loss": 0.1581, "learning_rate": 1.2182297447322787e-05, "epoch": 4.285714285714286, "percentage": 85.71, "elapsed_time": "0:14:30", "remaining_time": "0:02:25"}
+{"current_steps": 2560, "total_steps": 2975, "loss": 0.1861, "learning_rate": 1.1627006651174444e-05, "epoch": 4.302521008403361, "percentage": 86.05, "elapsed_time": "0:14:34", "remaining_time": "0:02:21"}
+{"current_steps": 2570, "total_steps": 2975, "loss": 0.1589, "learning_rate": 1.10838866118247e-05, "epoch": 4.319327731092437, "percentage": 86.39, "elapsed_time": "0:14:37", "remaining_time": "0:02:18"}
+{"current_steps": 2580, "total_steps": 2975, "loss": 0.1958, "learning_rate": 1.0553012127938389e-05, "epoch": 4.336134453781512, "percentage": 86.72, "elapsed_time": "0:14:40", "remaining_time": "0:02:14"}
+{"current_steps": 2590, "total_steps": 2975, "loss": 0.1664, "learning_rate": 1.0034456311718609e-05, "epoch": 4.352941176470588, "percentage": 87.06, "elapsed_time": "0:14:44", "remaining_time": "0:02:11"}
+{"current_steps": 2600, "total_steps": 2975, "loss": 0.1713, "learning_rate": 9.528290578837551e-06, "epoch": 4.369747899159664, "percentage": 87.39, "elapsed_time": "0:14:47", "remaining_time": "0:02:08"}
+{"current_steps": 2610, "total_steps": 2975, "loss": 0.1494, "learning_rate": 9.034584638601196e-06, "epoch": 4.38655462184874, "percentage": 87.73, "elapsed_time": "0:14:50", "remaining_time": "0:02:04"}
+{"current_steps": 2620, "total_steps": 2975, "loss": 0.1823, "learning_rate": 8.553406484348914e-06, "epoch": 4.4033613445378155, "percentage": 88.07, "elapsed_time": "0:14:53", "remaining_time": "0:02:01"}
+{"current_steps": 2630, "total_steps": 2975, "loss": 0.1825, "learning_rate": 8.084822384089453e-06, "epoch": 4.420168067226891, "percentage": 88.4, "elapsed_time": "0:14:56", "remaining_time": "0:01:57"}
+{"current_steps": 2640, "total_steps": 2975, "loss": 0.1799, "learning_rate": 7.628896871374358e-06, "epoch": 4.436974789915967, "percentage": 88.74, "elapsed_time": "0:15:00", "remaining_time": "0:01:54"}
+{"current_steps": 2650, "total_steps": 2975, "loss": 0.1707, "learning_rate": 7.185692736410477e-06, "epoch": 4.453781512605042, "percentage": 89.08, "elapsed_time": "0:15:03", "remaining_time": "0:01:50"}
+{"current_steps": 2660, "total_steps": 2975, "loss": 0.1748, "learning_rate": 6.755271017412501e-06, "epoch": 4.470588235294118, "percentage": 89.41, "elapsed_time": "0:15:07", "remaining_time": "0:01:47"}
+{"current_steps": 2670, "total_steps": 2975, "loss": 0.1703, "learning_rate": 6.337690992196688e-06, "epoch": 4.487394957983193, "percentage": 89.75, "elapsed_time": "0:15:10", "remaining_time": "0:01:44"}
+{"current_steps": 2680, "total_steps": 2975, "loss": 0.1717, "learning_rate": 5.933010170017139e-06, "epoch": 4.504201680672269, "percentage": 90.08, "elapsed_time": "0:15:13", "remaining_time": "0:01:40"}
+{"current_steps": 2690, "total_steps": 2975, "loss": 0.1866, "learning_rate": 5.54128428364562e-06, "epoch": 4.5210084033613445, "percentage": 90.42, "elapsed_time": "0:15:18", "remaining_time": "0:01:37"}
+{"current_steps": 2700, "total_steps": 2975, "loss": 0.1659, "learning_rate": 5.162567281696018e-06, "epoch": 4.53781512605042, "percentage": 90.76, "elapsed_time": "0:15:21", "remaining_time": "0:01:33"}
+{"current_steps": 2710, "total_steps": 2975, "loss": 0.166, "learning_rate": 4.796911321194475e-06, "epoch": 4.554621848739496, "percentage": 91.09, "elapsed_time": "0:15:24", "remaining_time": "0:01:30"}
+{"current_steps": 2720, "total_steps": 2975, "loss": 0.1768, "learning_rate": 4.444366760396357e-06, "epoch": 4.571428571428571, "percentage": 91.43, "elapsed_time": "0:15:27", "remaining_time": "0:01:26"}
+{"current_steps": 2730, "total_steps": 2975, "loss": 0.1769, "learning_rate": 4.104982151850911e-06, "epoch": 4.588235294117647, "percentage": 91.76, "elapsed_time": "0:15:30", "remaining_time": "0:01:23"}
+{"current_steps": 2740, "total_steps": 2975, "loss": 0.1708, "learning_rate": 3.7788042357145616e-06, "epoch": 4.605042016806722, "percentage": 92.1, "elapsed_time": "0:15:34", "remaining_time": "0:01:20"}
+{"current_steps": 2750, "total_steps": 2975, "loss": 0.176, "learning_rate": 3.465877933313799e-06, "epoch": 4.621848739495798, "percentage": 92.44, "elapsed_time": "0:15:37", "remaining_time": "0:01:16"}
+{"current_steps": 2760, "total_steps": 2975, "loss": 0.1722, "learning_rate": 3.166246340958712e-06, "epoch": 4.6386554621848735, "percentage": 92.77, "elapsed_time": "0:15:40", "remaining_time": "0:01:13"}
+{"current_steps": 2770, "total_steps": 2975, "loss": 0.1851, "learning_rate": 2.8799507240076406e-06, "epoch": 4.65546218487395, "percentage": 93.11, "elapsed_time": "0:15:44", "remaining_time": "0:01:09"}
+{"current_steps": 2780, "total_steps": 2975, "loss": 0.1671, "learning_rate": 2.607030511184183e-06, "epoch": 4.6722689075630255, "percentage": 93.45, "elapsed_time": "0:15:47", "remaining_time": "0:01:06"}
+{"current_steps": 2790, "total_steps": 2975, "loss": 0.1728, "learning_rate": 2.347523289146991e-06, "epoch": 4.689075630252101, "percentage": 93.78, "elapsed_time": "0:15:50", "remaining_time": "0:01:03"}
+{"current_steps": 2800, "total_steps": 2975, "loss": 0.1549, "learning_rate": 2.101464797313357e-06, "epoch": 4.705882352941177, "percentage": 94.12, "elapsed_time": "0:15:54", "remaining_time": "0:00:59"}
+{"current_steps": 2810, "total_steps": 2975, "loss": 0.1423, "learning_rate": 1.868888922937162e-06, "epoch": 4.722689075630252, "percentage": 94.45, "elapsed_time": "0:15:57", "remaining_time": "0:00:56"}
+{"current_steps": 2820, "total_steps": 2975, "loss": 0.1571, "learning_rate": 1.649827696441919e-06, "epoch": 4.739495798319328, "percentage": 94.79, "elapsed_time": "0:16:00", "remaining_time": "0:00:52"}
+{"current_steps": 2830, "total_steps": 2975, "loss": 0.1624, "learning_rate": 1.4443112870095588e-06, "epoch": 4.756302521008403, "percentage": 95.13, "elapsed_time": "0:16:04", "remaining_time": "0:00:49"}
+{"current_steps": 2840, "total_steps": 2975, "loss": 0.1609, "learning_rate": 1.25236799842543e-06, "epoch": 4.773109243697479, "percentage": 95.46, "elapsed_time": "0:16:07", "remaining_time": "0:00:45"}
+{"current_steps": 2850, "total_steps": 2975, "loss": 0.1664, "learning_rate": 1.0740242651803956e-06, "epoch": 4.7899159663865545, "percentage": 95.8, "elapsed_time": "0:16:11", "remaining_time": "0:00:42"}
+{"current_steps": 2860, "total_steps": 2975, "loss": 0.1793, "learning_rate": 9.093046488302337e-07, "epoch": 4.80672268907563, "percentage": 96.13, "elapsed_time": "0:16:14", "remaining_time": "0:00:39"}
+{"current_steps": 2870, "total_steps": 2975, "loss": 0.1641, "learning_rate": 7.582318346129657e-07, "epoch": 4.823529411764706, "percentage": 96.47, "elapsed_time": "0:16:18", "remaining_time": "0:00:35"}
+{"current_steps": 2880, "total_steps": 2975, "loss": 0.1508, "learning_rate": 6.20826628324711e-07, "epoch": 4.840336134453781, "percentage": 96.81, "elapsed_time": "0:16:21", "remaining_time": "0:00:32"}
+{"current_steps": 2890, "total_steps": 2975, "loss": 0.1628, "learning_rate": 4.971079534542345e-07, "epoch": 4.857142857142857, "percentage": 97.14, "elapsed_time": "0:16:26", "remaining_time": "0:00:29"}
+{"current_steps": 2900, "total_steps": 2975, "loss": 0.1684, "learning_rate": 3.8709284857687546e-07, "epoch": 4.873949579831933, "percentage": 97.48, "elapsed_time": "0:16:29", "remaining_time": "0:00:25"}
+{"current_steps": 2910, "total_steps": 2975, "loss": 0.1619, "learning_rate": 2.9079646500792534e-07, "epoch": 4.890756302521009, "percentage": 97.82, "elapsed_time": "0:16:32", "remaining_time": "0:00:22"}
+{"current_steps": 2920, "total_steps": 2975, "loss": 0.1612, "learning_rate": 2.0823206471599632e-07, "epoch": 4.907563025210084, "percentage": 98.15, "elapsed_time": "0:16:35", "remaining_time": "0:00:18"}
+{"current_steps": 2930, "total_steps": 2975, "loss": 0.1647, "learning_rate": 1.3941101849660466e-07, "epoch": 4.92436974789916, "percentage": 98.49, "elapsed_time": "0:16:39", "remaining_time": "0:00:15"}
+{"current_steps": 2940, "total_steps": 2975, "loss": 0.1611, "learning_rate": 8.434280440616782e-08, "epoch": 4.9411764705882355, "percentage": 98.82, "elapsed_time": "0:16:42", "remaining_time": "0:00:11"}
+{"current_steps": 2950, "total_steps": 2975, "loss": 0.1694, "learning_rate": 4.3035006456670915e-08, "epoch": 4.957983193277311, "percentage": 99.16, "elapsed_time": "0:16:45", "remaining_time": "0:00:08"}
+{"current_steps": 2960, "total_steps": 2975, "loss": 0.1695, "learning_rate": 1.5493313571202093e-08, "epoch": 4.974789915966387, "percentage": 99.5, "elapsed_time": "0:16:49", "remaining_time": "0:00:05"}
+{"current_steps": 2970, "total_steps": 2975, "loss": 0.155, "learning_rate": 1.7215188004904293e-09, "epoch": 4.991596638655462, "percentage": 99.83, "elapsed_time": "0:16:52", "remaining_time": "0:00:01"}
+{"current_steps": 2975, "total_steps": 2975, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:16:55", "remaining_time": "0:00:00"}

code_alpaca/trainer_state.json

@@ -0,0 +1,2137 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 1000,
+  "global_step": 2975,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01680672268907563,
+      "grad_norm": 1.6710422039031982,
+      "learning_rate": 6.7114093959731546e-06,
+      "loss": 1.2952,
+      "step": 10
+    },
+    {
+      "epoch": 0.03361344537815126,
+      "grad_norm": 1.708608865737915,
+      "learning_rate": 1.3422818791946309e-05,
+      "loss": 1.4041,
+      "step": 20
+    },
+    {
+      "epoch": 0.05042016806722689,
+      "grad_norm": 1.9668169021606445,
+      "learning_rate": 2.013422818791946e-05,
+      "loss": 1.2144,
+      "step": 30
+    },
+    {
+      "epoch": 0.06722689075630252,
+      "grad_norm": 1.0957667827606201,
+      "learning_rate": 2.6845637583892618e-05,
+      "loss": 0.8496,
+      "step": 40
+    },
+    {
+      "epoch": 0.08403361344537816,
+      "grad_norm": 0.7974053621292114,
+      "learning_rate": 3.3557046979865775e-05,
+      "loss": 0.642,
+      "step": 50
+    },
+    {
+      "epoch": 0.10084033613445378,
+      "grad_norm": 0.6723673939704895,
+      "learning_rate": 4.026845637583892e-05,
+      "loss": 0.5978,
+      "step": 60
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.7411757707595825,
+      "learning_rate": 4.697986577181208e-05,
+      "loss": 0.5342,
+      "step": 70
+    },
+    {
+      "epoch": 0.13445378151260504,
+      "grad_norm": 0.7030589580535889,
+      "learning_rate": 5.3691275167785237e-05,
+      "loss": 0.536,
+      "step": 80
+    },
+    {
+      "epoch": 0.15126050420168066,
+      "grad_norm": 0.5388085842132568,
+      "learning_rate": 6.04026845637584e-05,
+      "loss": 0.5294,
+      "step": 90
+    },
+    {
+      "epoch": 0.16806722689075632,
+      "grad_norm": 0.5648273229598999,
+      "learning_rate": 6.711409395973155e-05,
+      "loss": 0.5288,
+      "step": 100
+    },
+    {
+      "epoch": 0.18487394957983194,
+      "grad_norm": 0.5652063488960266,
+      "learning_rate": 7.382550335570471e-05,
+      "loss": 0.5467,
+      "step": 110
+    },
+    {
+      "epoch": 0.20168067226890757,
+      "grad_norm": 0.5379688739776611,
+      "learning_rate": 8.053691275167784e-05,
+      "loss": 0.5057,
+      "step": 120
+    },
+    {
+      "epoch": 0.2184873949579832,
+      "grad_norm": 0.7668149471282959,
+      "learning_rate": 8.7248322147651e-05,
+      "loss": 0.5094,
+      "step": 130
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.5256843566894531,
+      "learning_rate": 9.395973154362417e-05,
+      "loss": 0.5195,
+      "step": 140
+    },
+    {
+      "epoch": 0.25210084033613445,
+      "grad_norm": 0.5416532754898071,
+      "learning_rate": 0.00010067114093959733,
+      "loss": 0.4653,
+      "step": 150
+    },
+    {
+      "epoch": 0.2689075630252101,
+      "grad_norm": 0.474119633436203,
+      "learning_rate": 0.00010738255033557047,
+      "loss": 0.4979,
+      "step": 160
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.5296077132225037,
+      "learning_rate": 0.00011409395973154362,
+      "loss": 0.5004,
+      "step": 170
+    },
+    {
+      "epoch": 0.3025210084033613,
+      "grad_norm": 0.4529200494289398,
+      "learning_rate": 0.0001208053691275168,
+      "loss": 0.4975,
+      "step": 180
+    },
+    {
+      "epoch": 0.31932773109243695,
+      "grad_norm": 0.4488178491592407,
+      "learning_rate": 0.00012751677852348994,
+      "loss": 0.4779,
+      "step": 190
+    },
+    {
+      "epoch": 0.33613445378151263,
+      "grad_norm": 0.4906866252422333,
+      "learning_rate": 0.0001342281879194631,
+      "loss": 0.5172,
+      "step": 200
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.647227942943573,
+      "learning_rate": 0.00014093959731543624,
+      "loss": 0.4858,
+      "step": 210
+    },
+    {
+      "epoch": 0.3697478991596639,
+      "grad_norm": 0.5192333459854126,
+      "learning_rate": 0.00014765100671140942,
+      "loss": 0.5518,
+      "step": 220
+    },
+    {
+      "epoch": 0.3865546218487395,
+      "grad_norm": 0.4241911470890045,
+      "learning_rate": 0.00015436241610738256,
+      "loss": 0.4668,
+      "step": 230
+    },
+    {
+      "epoch": 0.40336134453781514,
+      "grad_norm": 0.49162909388542175,
+      "learning_rate": 0.0001610738255033557,
+      "loss": 0.5524,
+      "step": 240
+    },
+    {
+      "epoch": 0.42016806722689076,
+      "grad_norm": 0.45716652274131775,
+      "learning_rate": 0.00016778523489932888,
+      "loss": 0.4681,
+      "step": 250
+    },
+    {
+      "epoch": 0.4369747899159664,
+      "grad_norm": 0.46797800064086914,
+      "learning_rate": 0.000174496644295302,
+      "loss": 0.4922,
+      "step": 260
+    },
+    {
+      "epoch": 0.453781512605042,
+      "grad_norm": 0.5456430315971375,
+      "learning_rate": 0.00018120805369127517,
+      "loss": 0.4656,
+      "step": 270
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.41116565465927124,
+      "learning_rate": 0.00018791946308724833,
+      "loss": 0.4973,
+      "step": 280
+    },
+    {
+      "epoch": 0.48739495798319327,
+      "grad_norm": 0.47659677267074585,
+      "learning_rate": 0.0001946308724832215,
+      "loss": 0.4703,
+      "step": 290
+    },
+    {
+      "epoch": 0.5042016806722689,
+      "grad_norm": 0.4758327007293701,
+      "learning_rate": 0.00019999972455632807,
+      "loss": 0.4574,
+      "step": 300
+    },
+    {
+      "epoch": 0.5210084033613446,
+      "grad_norm": 0.38325995206832886,
+      "learning_rate": 0.00019999008418713482,
+      "loss": 0.4596,
+      "step": 310
+    },
+    {
+      "epoch": 0.5378151260504201,
+      "grad_norm": 0.5056403875350952,
+      "learning_rate": 0.00019996667315169163,
+      "loss": 0.4853,
+      "step": 320
+    },
+    {
+      "epoch": 0.5546218487394958,
+      "grad_norm": 0.49656251072883606,
+      "learning_rate": 0.00019992949467417378,
+      "loss": 0.4407,
+      "step": 330
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.49380919337272644,
+      "learning_rate": 0.00019987855387481305,
+      "loss": 0.4614,
+      "step": 340
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.47169238328933716,
+      "learning_rate": 0.0001998138577691925,
+      "loss": 0.4619,
+      "step": 350
+    },
+    {
+      "epoch": 0.6050420168067226,
+      "grad_norm": 0.34966766834259033,
+      "learning_rate": 0.00019973541526728048,
+      "loss": 0.4828,
+      "step": 360
+    },
+    {
+      "epoch": 0.6218487394957983,
+      "grad_norm": 0.4971473217010498,
+      "learning_rate": 0.0001996432371722033,
+      "loss": 0.4406,
+      "step": 370
+    },
+    {
+      "epoch": 0.6386554621848739,
+      "grad_norm": 0.3743559420108795,
+      "learning_rate": 0.00019953733617875759,
+      "loss": 0.4854,
+      "step": 380
+    },
+    {
+      "epoch": 0.6554621848739496,
+      "grad_norm": 0.3752104341983795,
+      "learning_rate": 0.00019941772687166192,
+      "loss": 0.4921,
+      "step": 390
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 0.4422326982021332,
+      "learning_rate": 0.00019928442572354814,
+      "loss": 0.4802,
+      "step": 400
+    },
+    {
+      "epoch": 0.6890756302521008,
+      "grad_norm": 0.4718156158924103,
+      "learning_rate": 0.00019913745109269288,
+      "loss": 0.5042,
+      "step": 410
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.4682941734790802,
+      "learning_rate": 0.00019897682322048908,
+      "loss": 0.4865,
+      "step": 420
+    },
+    {
+      "epoch": 0.7226890756302521,
+      "grad_norm": 0.5025270581245422,
+      "learning_rate": 0.0001988025642286585,
+      "loss": 0.4781,
+      "step": 430
+    },
+    {
+      "epoch": 0.7394957983193278,
+      "grad_norm": 0.6233184337615967,
+      "learning_rate": 0.000198614698116205,
+      "loss": 0.5091,
+      "step": 440
+    },
+    {
+      "epoch": 0.7563025210084033,
+      "grad_norm": 0.354615718126297,
+      "learning_rate": 0.00019841325075610944,
+      "loss": 0.5004,
+      "step": 450
+    },
+    {
+      "epoch": 0.773109243697479,
+      "grad_norm": 0.42839425802230835,
+      "learning_rate": 0.00019819824989176645,
+      "loss": 0.4652,
+      "step": 460
+    },
+    {
+      "epoch": 0.7899159663865546,
+      "grad_norm": 0.379213809967041,
+      "learning_rate": 0.00019796972513316355,
+      "loss": 0.4739,
+      "step": 470
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 0.4357176423072815,
+      "learning_rate": 0.00019772770795280329,
+      "loss": 0.5072,
+      "step": 480
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.4875657856464386,
+      "learning_rate": 0.00019747223168136886,
+      "loss": 0.5094,
+      "step": 490
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "grad_norm": 0.4749436676502228,
+      "learning_rate": 0.00019720333150313377,
+      "loss": 0.4812,
+      "step": 500
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.446424663066864,
+      "learning_rate": 0.0001969210444511162,
+      "loss": 0.4823,
+      "step": 510
+    },
+    {
+      "epoch": 0.8739495798319328,
+      "grad_norm": 0.4699801802635193,
+      "learning_rate": 0.00019662540940197892,
+      "loss": 0.4559,
+      "step": 520
+    },
+    {
+      "epoch": 0.8907563025210085,
+      "grad_norm": 0.4818078875541687,
+      "learning_rate": 0.00019631646707067511,
+      "loss": 0.4803,
+      "step": 530
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": 0.4135447144508362,
+      "learning_rate": 0.000195994260004841,
+      "loss": 0.4481,
+      "step": 540
+    },
+    {
+      "epoch": 0.9243697478991597,
+      "grad_norm": 0.3625709116458893,
+      "learning_rate": 0.00019565883257893635,
+      "loss": 0.4606,
+      "step": 550
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.6398768424987793,
+      "learning_rate": 0.00019531023098813316,
+      "loss": 0.4819,
+      "step": 560
+    },
+    {
+      "epoch": 0.957983193277311,
+      "grad_norm": 0.40339210629463196,
+      "learning_rate": 0.00019494850324195353,
+      "loss": 0.4742,
+      "step": 570
+    },
+    {
+      "epoch": 0.9747899159663865,
+      "grad_norm": 0.37650129199028015,
+      "learning_rate": 0.00019457369915765798,
+      "loss": 0.4514,
+      "step": 580
+    },
+    {
+      "epoch": 0.9915966386554622,
+      "grad_norm": 0.41677525639533997,
+      "learning_rate": 0.00019418587035338432,
+      "loss": 0.4849,
+      "step": 590
+    },
+    {
+      "epoch": 1.0084033613445378,
+      "grad_norm": 0.44225984811782837,
+      "learning_rate": 0.0001937850702410391,
+      "loss": 0.4626,
+      "step": 600
+    },
+    {
+      "epoch": 1.0252100840336134,
+      "grad_norm": 0.4943791627883911,
+      "learning_rate": 0.00019337135401894146,
+      "loss": 0.4441,
+      "step": 610
+    },
+    {
+      "epoch": 1.0420168067226891,
+      "grad_norm": 0.38774925470352173,
+      "learning_rate": 0.0001929447786642213,
+      "loss": 0.4287,
+      "step": 620
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.4631214737892151,
+      "learning_rate": 0.00019250540292497235,
+      "loss": 0.4369,
+      "step": 630
+    },
+    {
+      "epoch": 1.0756302521008403,
+      "grad_norm": 0.5732137560844421,
+      "learning_rate": 0.00019205328731216147,
+      "loss": 0.4119,
+      "step": 640
+    },
+    {
+      "epoch": 1.092436974789916,
+      "grad_norm": 0.5002462863922119,
+      "learning_rate": 0.00019158849409129484,
+      "loss": 0.4172,
+      "step": 650
+    },
+    {
+      "epoch": 1.1092436974789917,
+      "grad_norm": 0.6402649879455566,
+      "learning_rate": 0.00019111108727384296,
+      "loss": 0.3912,
+      "step": 660
+    },
+    {
+      "epoch": 1.1260504201680672,
+      "grad_norm": 0.5174903869628906,
+      "learning_rate": 0.00019062113260842476,
+      "loss": 0.4656,
+      "step": 670
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.4554598033428192,
+      "learning_rate": 0.0001901186975717529,
+      "loss": 0.4059,
+      "step": 680
+    },
+    {
+      "epoch": 1.1596638655462184,
+      "grad_norm": 0.480656236410141,
+      "learning_rate": 0.0001896038513593407,
+      "loss": 0.4013,
+      "step": 690
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.40827691555023193,
+      "learning_rate": 0.00018907666487597257,
+      "loss": 0.4278,
+      "step": 700
+    },
+    {
+      "epoch": 1.1932773109243697,
+      "grad_norm": 0.4276060163974762,
+      "learning_rate": 0.00018853721072593894,
+      "loss": 0.4112,
+      "step": 710
+    },
+    {
+      "epoch": 1.2100840336134453,
+      "grad_norm": 0.5786320567131042,
+      "learning_rate": 0.00018798556320303718,
+      "loss": 0.4518,
+      "step": 720
+    },
+    {
+      "epoch": 1.226890756302521,
+      "grad_norm": 0.37131550908088684,
+      "learning_rate": 0.00018742179828033992,
+      "loss": 0.4132,
+      "step": 730
+    },
+    {
+      "epoch": 1.2436974789915967,
+      "grad_norm": 0.4482327401638031,
+      "learning_rate": 0.00018684599359973194,
+      "loss": 0.4196,
+      "step": 740
+    },
+    {
+      "epoch": 1.2605042016806722,
+      "grad_norm": 0.6399847269058228,
+      "learning_rate": 0.00018625822846121727,
+      "loss": 0.427,
+      "step": 750
+    },
+    {
+      "epoch": 1.2773109243697478,
+      "grad_norm": 0.5624536871910095,
+      "learning_rate": 0.0001856585838119981,
+      "loss": 0.3879,
+      "step": 760
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.4050937592983246,
+      "learning_rate": 0.0001850471422353265,
+      "loss": 0.44,
+      "step": 770
+    },
+    {
+      "epoch": 1.3109243697478992,
+      "grad_norm": 0.4883362054824829,
+      "learning_rate": 0.00018442398793913118,
+      "loss": 0.416,
+      "step": 780
+    },
+    {
+      "epoch": 1.3277310924369747,
+      "grad_norm": 0.5154753923416138,
+      "learning_rate": 0.00018378920674442045,
+      "loss": 0.4266,
+      "step": 790
+    },
+    {
+      "epoch": 1.3445378151260505,
+      "grad_norm": 0.5751391649246216,
+      "learning_rate": 0.00018314288607346258,
+      "loss": 0.4331,
+      "step": 800
+    },
+    {
+      "epoch": 1.361344537815126,
+      "grad_norm": 0.5200420618057251,
+      "learning_rate": 0.0001824851149377463,
+      "loss": 0.4275,
+      "step": 810
+    },
+    {
+      "epoch": 1.3781512605042017,
+      "grad_norm": 0.5671929121017456,
+      "learning_rate": 0.00018181598392572203,
+      "loss": 0.4285,
+      "step": 820
+    },
+    {
+      "epoch": 1.3949579831932772,
+      "grad_norm": 0.5295830368995667,
+      "learning_rate": 0.0001811355851903259,
+      "loss": 0.3888,
+      "step": 830
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.4832970201969147,
+      "learning_rate": 0.0001804440124362885,
+      "loss": 0.4299,
+      "step": 840
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.4614173173904419,
+      "learning_rate": 0.00017974136090722985,
+      "loss": 0.4012,
+      "step": 850
+    },
+    {
+      "epoch": 1.4453781512605042,
+      "grad_norm": 0.5086454153060913,
+      "learning_rate": 0.00017902772737254238,
+      "loss": 0.4103,
+      "step": 860
+    },
+    {
+      "epoch": 1.46218487394958,
+      "grad_norm": 0.6145858764648438,
+      "learning_rate": 0.00017830321011406386,
+      "loss": 0.4378,
+      "step": 870
+    },
+    {
+      "epoch": 1.4789915966386555,
+      "grad_norm": 0.4497447907924652,
+      "learning_rate": 0.00017756790891254194,
+      "loss": 0.4021,
+      "step": 880
+    },
+    {
+      "epoch": 1.495798319327731,
+      "grad_norm": 0.4918227195739746,
+      "learning_rate": 0.00017682192503389236,
+      "loss": 0.4364,
+      "step": 890
+    },
+    {
+      "epoch": 1.5126050420168067,
+      "grad_norm": 0.7057837247848511,
+      "learning_rate": 0.00017606536121525255,
+      "loss": 0.3721,
+      "step": 900
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.5684515237808228,
+      "learning_rate": 0.00017529832165083265,
+      "loss": 0.4458,
+      "step": 910
+    },
+    {
+      "epoch": 1.5462184873949578,
+      "grad_norm": 0.6396010518074036,
+      "learning_rate": 0.0001745209119775658,
+      "loss": 0.4156,
+      "step": 920
+    },
+    {
+      "epoch": 1.5630252100840336,
+      "grad_norm": 0.5182276368141174,
+      "learning_rate": 0.0001737332392605599,
+      "loss": 0.4167,
+      "step": 930
+    },
+    {
+      "epoch": 1.5798319327731094,
+      "grad_norm": 0.4409577548503876,
+      "learning_rate": 0.0001729354119783525,
+      "loss": 0.4272,
+      "step": 940
+    },
+    {
+      "epoch": 1.596638655462185,
+      "grad_norm": 0.4636439085006714,
+      "learning_rate": 0.00017212754000797107,
+      "loss": 0.3888,
+      "step": 950
+    },
+    {
+      "epoch": 1.6134453781512605,
+      "grad_norm": 0.5916410684585571,
+      "learning_rate": 0.00017130973460980077,
+      "loss": 0.4319,
+      "step": 960
+    },
+    {
+      "epoch": 1.6302521008403361,
+      "grad_norm": 0.48982053995132446,
+      "learning_rate": 0.00017048210841226155,
+      "loss": 0.4168,
+      "step": 970
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.8442604541778564,
+      "learning_rate": 0.00016964477539629702,
+      "loss": 0.427,
+      "step": 980
+    },
+    {
+      "epoch": 1.6638655462184873,
+      "grad_norm": 0.5364897847175598,
+      "learning_rate": 0.0001687978508796769,
+      "loss": 0.4284,
+      "step": 990
+    },
+    {
+      "epoch": 1.680672268907563,
+      "grad_norm": 0.5252152681350708,
+      "learning_rate": 0.00016794145150111542,
+      "loss": 0.4081,
+      "step": 1000
+    },
+    {
+      "epoch": 1.680672268907563,
+      "eval_loss": 0.469873309135437,
+      "eval_runtime": 8.5876,
+      "eval_samples_per_second": 116.564,
+      "eval_steps_per_second": 14.672,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6974789915966386,
+      "grad_norm": 0.5419629812240601,
+      "learning_rate": 0.00016707569520420785,
+      "loss": 0.4571,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.447343647480011,
+      "learning_rate": 0.00016620070122118724,
+      "loss": 0.417,
+      "step": 1020
+    },
+    {
+      "epoch": 1.73109243697479,
+      "grad_norm": 0.7582902908325195,
+      "learning_rate": 0.00016531659005650367,
+      "loss": 0.4514,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7478991596638656,
+      "grad_norm": 0.5247509479522705,
+      "learning_rate": 0.00016442348347022842,
+      "loss": 0.4377,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.525404155254364,
+      "learning_rate": 0.0001635215044612851,
+      "loss": 0.4159,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7815126050420167,
+      "grad_norm": 0.5584174990653992,
+      "learning_rate": 0.00016261077725051015,
+      "loss": 0.4243,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7983193277310925,
+      "grad_norm": 0.4921722114086151,
+      "learning_rate": 0.00016169142726354515,
+      "loss": 0.3873,
+      "step": 1070
+    },
+    {
+      "epoch": 1.815126050420168,
+      "grad_norm": 0.5573268532752991,
+      "learning_rate": 0.00016076358111356332,
+      "loss": 0.418,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8319327731092439,
+      "grad_norm": 0.5113047361373901,
+      "learning_rate": 0.0001598273665838319,
+      "loss": 0.4322,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8487394957983194,
+      "grad_norm": 0.48914453387260437,
+      "learning_rate": 0.0001588829126101143,
+      "loss": 0.431,
+      "step": 1100
+    },
+    {
+      "epoch": 1.865546218487395,
+      "grad_norm": 0.4903518259525299,
+      "learning_rate": 0.0001579303492629126,
+      "loss": 0.4301,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.6053085923194885,
+      "learning_rate": 0.0001569698077295545,
+      "loss": 0.4376,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8991596638655461,
+      "grad_norm": 0.6364733576774597,
+      "learning_rate": 0.00015600142029612596,
+      "loss": 0.4321,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9159663865546217,
+      "grad_norm": 0.5780381560325623,
+      "learning_rate": 0.00015502532032925283,
+      "loss": 0.4931,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9327731092436975,
+      "grad_norm": 0.5068004131317139,
+      "learning_rate": 0.0001540416422577335,
+      "loss": 0.4143,
+      "step": 1150
+    },
+    {
+      "epoch": 1.949579831932773,
+      "grad_norm": 0.44138628244400024,
+      "learning_rate": 0.00015305052155402545,
+      "loss": 0.4577,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9663865546218489,
+      "grad_norm": 0.542020857334137,
+      "learning_rate": 0.0001520520947155877,
+      "loss": 0.4184,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9831932773109244,
+      "grad_norm": 0.38625264167785645,
+      "learning_rate": 0.00015104649924608252,
+      "loss": 0.3933,
+      "step": 1180
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.42412513494491577,
+      "learning_rate": 0.00015003387363643836,
+      "loss": 0.3885,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0168067226890756,
+      "grad_norm": 0.4694175720214844,
+      "learning_rate": 0.00014901435734577677,
+      "loss": 0.3581,
+      "step": 1200
+    },
+    {
+      "epoch": 2.033613445378151,
+      "grad_norm": 0.5906610488891602,
+      "learning_rate": 0.0001479880907822061,
+      "loss": 0.3139,
+      "step": 1210
+    },
+    {
+      "epoch": 2.0504201680672267,
+      "grad_norm": 0.6226663589477539,
+      "learning_rate": 0.00014695521528348447,
+      "loss": 0.3298,
+      "step": 1220
+    },
+    {
+      "epoch": 2.0672268907563027,
+      "grad_norm": 0.5035540461540222,
+      "learning_rate": 0.00014591587309755464,
+      "loss": 0.3193,
+      "step": 1230
+    },
+    {
+      "epoch": 2.0840336134453783,
+      "grad_norm": 0.5115870237350464,
+      "learning_rate": 0.00014487020736295354,
+      "loss": 0.3035,
+      "step": 1240
+    },
+    {
+      "epoch": 2.100840336134454,
+      "grad_norm": 0.5900698304176331,
+      "learning_rate": 0.00014381836208909927,
+      "loss": 0.3432,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.4748307466506958,
+      "learning_rate": 0.00014276048213645809,
+      "loss": 0.3214,
+      "step": 1260
+    },
+    {
+      "epoch": 2.134453781512605,
+      "grad_norm": 0.9723687767982483,
+      "learning_rate": 0.0001416967131965941,
+      "loss": 0.3571,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1512605042016806,
+      "grad_norm": 0.46582403779029846,
+      "learning_rate": 0.00014062720177210455,
+      "loss": 0.3357,
+      "step": 1280
+    },
+    {
+      "epoch": 2.168067226890756,
+      "grad_norm": 0.6172323226928711,
+      "learning_rate": 0.00013955209515644363,
+      "loss": 0.3249,
+      "step": 1290
+    },
+    {
+      "epoch": 2.184873949579832,
+      "grad_norm": 0.6465519070625305,
+      "learning_rate": 0.00013847154141363691,
+      "loss": 0.3485,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2016806722689077,
+      "grad_norm": 0.560625433921814,
+      "learning_rate": 0.00013738568935789015,
+      "loss": 0.3311,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2184873949579833,
+      "grad_norm": 0.6312292218208313,
+      "learning_rate": 0.00013629468853309433,
+      "loss": 0.3137,
+      "step": 1320
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.7188405990600586,
+      "learning_rate": 0.00013519868919223069,
+      "loss": 0.3484,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2521008403361344,
+      "grad_norm": 0.4797142446041107,
+      "learning_rate": 0.00013409784227667762,
+      "loss": 0.3316,
+      "step": 1340
+    },
+    {
+      "epoch": 2.26890756302521,
+      "grad_norm": 0.5650676488876343,
+      "learning_rate": 0.00013299229939542302,
+      "loss": 0.3169,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.7440696358680725,
+      "learning_rate": 0.00013188221280418472,
+      "loss": 0.3573,
+      "step": 1360
+    },
+    {
+      "epoch": 2.302521008403361,
+      "grad_norm": 0.5263564586639404,
+      "learning_rate": 0.0001307677353844417,
+      "loss": 0.3157,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3193277310924367,
+      "grad_norm": 0.8205832839012146,
+      "learning_rate": 0.0001296490206223793,
+      "loss": 0.3192,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3361344537815127,
+      "grad_norm": 0.6581016778945923,
+      "learning_rate": 0.000128526222587751,
+      "loss": 0.3136,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.6751677393913269,
+      "learning_rate": 0.00012739949591265975,
+      "loss": 0.3157,
+      "step": 1400
+    },
+    {
+      "epoch": 2.369747899159664,
+      "grad_norm": 0.7323719263076782,
+      "learning_rate": 0.0001262689957702623,
+      "loss": 0.3448,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3865546218487395,
+      "grad_norm": 0.6688811182975769,
+      "learning_rate": 0.00012513487785339832,
+      "loss": 0.3492,
+      "step": 1420
+    },
+    {
+      "epoch": 2.403361344537815,
+      "grad_norm": 0.7764780521392822,
+      "learning_rate": 0.0001239972983531487,
+      "loss": 0.3318,
+      "step": 1430
+    },
+    {
+      "epoch": 2.4201680672268906,
+      "grad_norm": 0.7399850487709045,
+      "learning_rate": 0.00012285641393732462,
+      "loss": 0.3171,
+      "step": 1440
+    },
+    {
+      "epoch": 2.4369747899159666,
+      "grad_norm": 0.9961610436439514,
+      "learning_rate": 0.00012171238172889135,
+      "loss": 0.3426,
+      "step": 1450
+    },
+    {
+      "epoch": 2.453781512605042,
+      "grad_norm": 0.6966540813446045,
+      "learning_rate": 0.00012056535928432902,
+      "loss": 0.3198,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.5827167630195618,
+      "learning_rate": 0.00011941550457193418,
+      "loss": 0.3535,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4873949579831933,
+      "grad_norm": 0.6033148765563965,
+      "learning_rate": 0.00011826297595006417,
+      "loss": 0.3141,
+      "step": 1480
+    },
+    {
+      "epoch": 2.504201680672269,
+      "grad_norm": 0.7176485061645508,
+      "learning_rate": 0.00011710793214532791,
+      "loss": 0.3435,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5210084033613445,
+      "grad_norm": 0.626823365688324,
+      "learning_rate": 0.00011595053223072623,
+      "loss": 0.3532,
+      "step": 1500
+    },
+    {
+      "epoch": 2.53781512605042,
+      "grad_norm": 0.6843551993370056,
+      "learning_rate": 0.00011479093560374406,
+      "loss": 0.327,
+      "step": 1510
+    },
+    {
+      "epoch": 2.5546218487394956,
+      "grad_norm": 0.7965649962425232,
+      "learning_rate": 0.00011362930196439832,
+      "loss": 0.3564,
+      "step": 1520
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.5511319041252136,
+      "learning_rate": 0.00011246579129324393,
+      "loss": 0.3281,
+      "step": 1530
+    },
+    {
+      "epoch": 2.588235294117647,
+      "grad_norm": 0.6023262143135071,
+      "learning_rate": 0.00011130056382934115,
+      "loss": 0.3361,
+      "step": 1540
+    },
+    {
+      "epoch": 2.6050420168067228,
+      "grad_norm": 0.7548812627792358,
+      "learning_rate": 0.00011013378004818762,
+      "loss": 0.3317,
+      "step": 1550
+    },
+    {
+      "epoch": 2.6218487394957983,
+      "grad_norm": 0.5712910294532776,
+      "learning_rate": 0.00010896560063961732,
+      "loss": 0.3243,
+      "step": 1560
+    },
+    {
+      "epoch": 2.638655462184874,
+      "grad_norm": 0.686442494392395,
+      "learning_rate": 0.00010779618648567058,
+      "loss": 0.3443,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6554621848739495,
+      "grad_norm": 0.6805222034454346,
+      "learning_rate": 0.00010662569863843725,
+      "loss": 0.3314,
+      "step": 1580
+    },
+    {
+      "epoch": 2.6722689075630255,
+      "grad_norm": 0.776661217212677,
+      "learning_rate": 0.00010545429829787659,
+      "loss": 0.3219,
+      "step": 1590
+    },
+    {
+      "epoch": 2.689075630252101,
+      "grad_norm": 0.5905969142913818,
+      "learning_rate": 0.00010428214678961668,
+      "loss": 0.3445,
+      "step": 1600
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 0.5671495199203491,
+      "learning_rate": 0.00010310940554273663,
+      "loss": 0.3459,
+      "step": 1610
+    },
+    {
+      "epoch": 2.722689075630252,
+      "grad_norm": 0.7796810269355774,
+      "learning_rate": 0.00010193623606753464,
+      "loss": 0.3121,
+      "step": 1620
+    },
+    {
+      "epoch": 2.7394957983193278,
+      "grad_norm": 0.6266621947288513,
+      "learning_rate": 0.00010076279993328455,
+      "loss": 0.34,
+      "step": 1630
+    },
+    {
+      "epoch": 2.7563025210084033,
+      "grad_norm": 0.6675502061843872,
+      "learning_rate": 9.958925874598464e-05,
+      "loss": 0.298,
+      "step": 1640
+    },
+    {
+      "epoch": 2.773109243697479,
+      "grad_norm": 0.6532730460166931,
+      "learning_rate": 9.841577412610108e-05,
+      "loss": 0.3519,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7899159663865545,
+      "grad_norm": 0.8185803890228271,
+      "learning_rate": 9.724250768630959e-05,
+      "loss": 0.3373,
+      "step": 1660
+    },
+    {
+      "epoch": 2.80672268907563,
+      "grad_norm": 0.6204152703285217,
+      "learning_rate": 9.606962100923807e-05,
+      "loss": 0.3061,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8235294117647056,
+      "grad_norm": 0.5997849702835083,
+      "learning_rate": 9.489727562521332e-05,
+      "loss": 0.3478,
+      "step": 1680
+    },
+    {
+      "epoch": 2.8403361344537816,
+      "grad_norm": 0.6466342806816101,
+      "learning_rate": 9.372563299001514e-05,
+      "loss": 0.3242,
+      "step": 1690
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.8826155662536621,
+      "learning_rate": 9.255485446264046e-05,
+      "loss": 0.3093,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8739495798319328,
+      "grad_norm": 0.9787838459014893,
+      "learning_rate": 9.138510128308117e-05,
+      "loss": 0.3608,
+      "step": 1710
+    },
+    {
+      "epoch": 2.8907563025210083,
+      "grad_norm": 0.7216944098472595,
+      "learning_rate": 9.021653455011778e-05,
+      "loss": 0.3247,
+      "step": 1720
+    },
+    {
+      "epoch": 2.907563025210084,
+      "grad_norm": 0.7170887589454651,
+      "learning_rate": 8.904931519913304e-05,
+      "loss": 0.354,
+      "step": 1730
+    },
+    {
+      "epoch": 2.92436974789916,
+      "grad_norm": 0.6556657552719116,
+      "learning_rate": 8.788360397994785e-05,
+      "loss": 0.3406,
+      "step": 1740
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.7959017157554626,
+      "learning_rate": 8.671956143468267e-05,
+      "loss": 0.3388,
+      "step": 1750
+    },
+    {
+      "epoch": 2.957983193277311,
+      "grad_norm": 0.7491987347602844,
+      "learning_rate": 8.55573478756477e-05,
+      "loss": 0.3676,
+      "step": 1760
+    },
+    {
+      "epoch": 2.9747899159663866,
+      "grad_norm": 0.7010266780853271,
+      "learning_rate": 8.439712336326452e-05,
+      "loss": 0.3152,
+      "step": 1770
+    },
+    {
+      "epoch": 2.991596638655462,
+      "grad_norm": 0.7219695448875427,
+      "learning_rate": 8.32390476840227e-05,
+      "loss": 0.3575,
+      "step": 1780
+    },
+    {
+      "epoch": 3.008403361344538,
+      "grad_norm": 0.8448328971862793,
+      "learning_rate": 8.208328032847366e-05,
+      "loss": 0.2936,
+      "step": 1790
+    },
+    {
+      "epoch": 3.0252100840336134,
+      "grad_norm": 0.575706958770752,
+      "learning_rate": 8.092998046926583e-05,
+      "loss": 0.2582,
+      "step": 1800
+    },
+    {
+      "epoch": 3.042016806722689,
+      "grad_norm": 0.8433834910392761,
+      "learning_rate": 7.977930693922329e-05,
+      "loss": 0.2324,
+      "step": 1810
+    },
+    {
+      "epoch": 3.0588235294117645,
+      "grad_norm": 0.8530866503715515,
+      "learning_rate": 7.863141820947114e-05,
+      "loss": 0.2219,
+      "step": 1820
+    },
+    {
+      "epoch": 3.0756302521008405,
+      "grad_norm": 0.7315991520881653,
+      "learning_rate": 7.748647236761094e-05,
+      "loss": 0.2201,
+      "step": 1830
+    },
+    {
+      "epoch": 3.092436974789916,
+      "grad_norm": 0.7668396234512329,
+      "learning_rate": 7.63446270959488e-05,
+      "loss": 0.2664,
+      "step": 1840
+    },
+    {
+      "epoch": 3.1092436974789917,
+      "grad_norm": 0.7540835738182068,
+      "learning_rate": 7.520603964977939e-05,
+      "loss": 0.2426,
+      "step": 1850
+    },
+    {
+      "epoch": 3.1260504201680672,
+      "grad_norm": 0.756682276725769,
+      "learning_rate": 7.407086683572846e-05,
+      "loss": 0.2297,
+      "step": 1860
+    },
+    {
+      "epoch": 3.142857142857143,
+      "grad_norm": 0.7847204804420471,
+      "learning_rate": 7.293926499015763e-05,
+      "loss": 0.257,
+      "step": 1870
+    },
+    {
+      "epoch": 3.1596638655462184,
+      "grad_norm": 0.909298837184906,
+      "learning_rate": 7.181138995763362e-05,
+      "loss": 0.2374,
+      "step": 1880
+    },
+    {
+      "epoch": 3.176470588235294,
+      "grad_norm": 1.1145635843276978,
+      "learning_rate": 7.068739706946517e-05,
+      "loss": 0.2389,
+      "step": 1890
+    },
+    {
+      "epoch": 3.19327731092437,
+      "grad_norm": 0.7492973804473877,
+      "learning_rate": 6.956744112231095e-05,
+      "loss": 0.2466,
+      "step": 1900
+    },
+    {
+      "epoch": 3.2100840336134455,
+      "grad_norm": 0.7049612998962402,
+      "learning_rate": 6.845167635686083e-05,
+      "loss": 0.2369,
+      "step": 1910
+    },
+    {
+      "epoch": 3.226890756302521,
+      "grad_norm": 0.6115100979804993,
+      "learning_rate": 6.73402564365938e-05,
+      "loss": 0.216,
+      "step": 1920
+    },
+    {
+      "epoch": 3.2436974789915967,
+      "grad_norm": 0.7355627417564392,
+      "learning_rate": 6.623333442661532e-05,
+      "loss": 0.2449,
+      "step": 1930
+    },
+    {
+      "epoch": 3.2605042016806722,
+      "grad_norm": 0.8105019927024841,
+      "learning_rate": 6.513106277257728e-05,
+      "loss": 0.2361,
+      "step": 1940
+    },
+    {
+      "epoch": 3.277310924369748,
+      "grad_norm": 0.6543210744857788,
+      "learning_rate": 6.403359327968303e-05,
+      "loss": 0.2136,
+      "step": 1950
+    },
+    {
+      "epoch": 3.2941176470588234,
+      "grad_norm": 1.191417932510376,
+      "learning_rate": 6.294107709178079e-05,
+      "loss": 0.2457,
+      "step": 1960
+    },
+    {
+      "epoch": 3.310924369747899,
+      "grad_norm": 0.8825222849845886,
+      "learning_rate": 6.185366467054799e-05,
+      "loss": 0.2184,
+      "step": 1970
+    },
+    {
+      "epoch": 3.327731092436975,
+      "grad_norm": 0.8879269361495972,
+      "learning_rate": 6.0771505774769734e-05,
+      "loss": 0.2419,
+      "step": 1980
+    },
+    {
+      "epoch": 3.3445378151260505,
+      "grad_norm": 0.692824125289917,
+      "learning_rate": 5.9694749439713936e-05,
+      "loss": 0.2559,
+      "step": 1990
+    },
+    {
+      "epoch": 3.361344537815126,
+      "grad_norm": 0.7757511138916016,
+      "learning_rate": 5.8623543956606074e-05,
+      "loss": 0.2383,
+      "step": 2000
+    },
+    {
+      "epoch": 3.361344537815126,
+      "eval_loss": 0.5869996547698975,
+      "eval_runtime": 8.7439,
+      "eval_samples_per_second": 114.479,
+      "eval_steps_per_second": 14.41,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3781512605042017,
+      "grad_norm": 0.8735210299491882,
+      "learning_rate": 5.7558036852206596e-05,
+      "loss": 0.2554,
+      "step": 2010
+    },
+    {
+      "epoch": 3.3949579831932772,
+      "grad_norm": 0.9418761134147644,
+      "learning_rate": 5.6498374868493296e-05,
+      "loss": 0.2682,
+      "step": 2020
+    },
+    {
+      "epoch": 3.411764705882353,
+      "grad_norm": 0.7112303972244263,
+      "learning_rate": 5.544470394245225e-05,
+      "loss": 0.2347,
+      "step": 2030
+    },
+    {
+      "epoch": 3.4285714285714284,
+      "grad_norm": 1.082740068435669,
+      "learning_rate": 5.439716918597906e-05,
+      "loss": 0.2561,
+      "step": 2040
+    },
+    {
+      "epoch": 3.4453781512605044,
+      "grad_norm": 0.7755303382873535,
+      "learning_rate": 5.335591486589406e-05,
+      "loss": 0.2087,
+      "step": 2050
+    },
+    {
+      "epoch": 3.46218487394958,
+      "grad_norm": 0.8446845412254333,
+      "learning_rate": 5.232108438407399e-05,
+      "loss": 0.2323,
+      "step": 2060
+    },
+    {
+      "epoch": 3.4789915966386555,
+      "grad_norm": 0.8153941035270691,
+      "learning_rate": 5.129282025770252e-05,
+      "loss": 0.2275,
+      "step": 2070
+    },
+    {
+      "epoch": 3.495798319327731,
+      "grad_norm": 0.7065542340278625,
+      "learning_rate": 5.027126409964271e-05,
+      "loss": 0.2136,
+      "step": 2080
+    },
+    {
+      "epoch": 3.5126050420168067,
+      "grad_norm": 1.1057276725769043,
+      "learning_rate": 4.9256556598934054e-05,
+      "loss": 0.2381,
+      "step": 2090
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 0.6242520809173584,
+      "learning_rate": 4.82488375014169e-05,
+      "loss": 0.2394,
+      "step": 2100
+    },
+    {
+      "epoch": 3.546218487394958,
+      "grad_norm": 0.6137174367904663,
+      "learning_rate": 4.7248245590486375e-05,
+      "loss": 0.2411,
+      "step": 2110
+    },
+    {
+      "epoch": 3.5630252100840334,
+      "grad_norm": 0.8595492839813232,
+      "learning_rate": 4.625491866797917e-05,
+      "loss": 0.2383,
+      "step": 2120
+    },
+    {
+      "epoch": 3.5798319327731094,
+      "grad_norm": 0.7664365768432617,
+      "learning_rate": 4.526899353519557e-05,
+      "loss": 0.264,
+      "step": 2130
+    },
+    {
+      "epoch": 3.596638655462185,
+      "grad_norm": 1.2114841938018799,
+      "learning_rate": 4.4290605974058995e-05,
+      "loss": 0.2412,
+      "step": 2140
+    },
+    {
+      "epoch": 3.6134453781512605,
+      "grad_norm": 0.8489940166473389,
+      "learning_rate": 4.331989072841604e-05,
+      "loss": 0.2408,
+      "step": 2150
+    },
+    {
+      "epoch": 3.630252100840336,
+      "grad_norm": 0.7826299071311951,
+      "learning_rate": 4.235698148547955e-05,
+      "loss": 0.2347,
+      "step": 2160
+    },
+    {
+      "epoch": 3.6470588235294117,
+      "grad_norm": 0.9073792099952698,
+      "learning_rate": 4.140201085741731e-05,
+      "loss": 0.2454,
+      "step": 2170
+    },
+    {
+      "epoch": 3.6638655462184873,
+      "grad_norm": 0.8302606344223022,
+      "learning_rate": 4.0455110363088424e-05,
+      "loss": 0.2381,
+      "step": 2180
+    },
+    {
+      "epoch": 3.6806722689075633,
+      "grad_norm": 0.7296493649482727,
+      "learning_rate": 3.9516410409930594e-05,
+      "loss": 0.2432,
+      "step": 2190
+    },
+    {
+      "epoch": 3.697478991596639,
+      "grad_norm": 0.8790242075920105,
+      "learning_rate": 3.858604027600049e-05,
+      "loss": 0.2387,
+      "step": 2200
+    },
+    {
+      "epoch": 3.7142857142857144,
+      "grad_norm": 0.8583736419677734,
+      "learning_rate": 3.766412809216937e-05,
+      "loss": 0.2482,
+      "step": 2210
+    },
+    {
+      "epoch": 3.73109243697479,
+      "grad_norm": 0.8858778476715088,
+      "learning_rate": 3.675080082447688e-05,
+      "loss": 0.2524,
+      "step": 2220
+    },
+    {
+      "epoch": 3.7478991596638656,
+      "grad_norm": 0.896706759929657,
+      "learning_rate": 3.584618425664526e-05,
+      "loss": 0.2477,
+      "step": 2230
+    },
+    {
+      "epoch": 3.764705882352941,
+      "grad_norm": 0.7617205381393433,
+      "learning_rate": 3.495040297275651e-05,
+      "loss": 0.2194,
+      "step": 2240
+    },
+    {
+      "epoch": 3.7815126050420167,
+      "grad_norm": 0.7257958650588989,
+      "learning_rate": 3.40635803400944e-05,
+      "loss": 0.2414,
+      "step": 2250
+    },
+    {
+      "epoch": 3.7983193277310923,
+      "grad_norm": 0.83749920129776,
+      "learning_rate": 3.3185838492154386e-05,
+      "loss": 0.2218,
+      "step": 2260
+    },
+    {
+      "epoch": 3.815126050420168,
+      "grad_norm": 1.028795599937439,
+      "learning_rate": 3.231729831182344e-05,
+      "loss": 0.2312,
+      "step": 2270
+    },
+    {
+      "epoch": 3.831932773109244,
+      "grad_norm": 0.8044925332069397,
+      "learning_rate": 3.1458079414731955e-05,
+      "loss": 0.2317,
+      "step": 2280
+    },
+    {
+      "epoch": 3.8487394957983194,
+      "grad_norm": 0.7760542035102844,
+      "learning_rate": 3.060830013278012e-05,
+      "loss": 0.2222,
+      "step": 2290
+    },
+    {
+      "epoch": 3.865546218487395,
+      "grad_norm": 0.7686411738395691,
+      "learning_rate": 2.9768077497841352e-05,
+      "loss": 0.2313,
+      "step": 2300
+    },
+    {
+      "epoch": 3.8823529411764706,
+      "grad_norm": 0.700995147228241,
+      "learning_rate": 2.8937527225644677e-05,
+      "loss": 0.231,
+      "step": 2310
+    },
+    {
+      "epoch": 3.899159663865546,
+      "grad_norm": 0.9482907652854919,
+      "learning_rate": 2.8116763699838167e-05,
+      "loss": 0.2504,
+      "step": 2320
+    },
+    {
+      "epoch": 3.9159663865546217,
+      "grad_norm": 0.9015063047409058,
+      "learning_rate": 2.7305899956236046e-05,
+      "loss": 0.24,
+      "step": 2330
+    },
+    {
+      "epoch": 3.9327731092436977,
+      "grad_norm": 0.9054192900657654,
+      "learning_rate": 2.6505047667251437e-05,
+      "loss": 0.2478,
+      "step": 2340
+    },
+    {
+      "epoch": 3.9495798319327733,
+      "grad_norm": 0.9170212745666504,
+      "learning_rate": 2.5714317126516763e-05,
+      "loss": 0.2419,
+      "step": 2350
+    },
+    {
+      "epoch": 3.966386554621849,
+      "grad_norm": 1.029768466949463,
+      "learning_rate": 2.493381723369398e-05,
+      "loss": 0.2341,
+      "step": 2360
+    },
+    {
+      "epoch": 3.9831932773109244,
+      "grad_norm": 0.6440130472183228,
+      "learning_rate": 2.4163655479476943e-05,
+      "loss": 0.213,
+      "step": 2370
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8131651282310486,
+      "learning_rate": 2.340393793078789e-05,
+      "loss": 0.2302,
+      "step": 2380
+    },
+    {
+      "epoch": 4.016806722689076,
+      "grad_norm": 0.7478677034378052,
+      "learning_rate": 2.2654769216169602e-05,
+      "loss": 0.1944,
+      "step": 2390
+    },
+    {
+      "epoch": 4.033613445378151,
+      "grad_norm": 0.7543561458587646,
+      "learning_rate": 2.1916252511376133e-05,
+      "loss": 0.172,
+      "step": 2400
+    },
+    {
+      "epoch": 4.050420168067227,
+      "grad_norm": 0.7355443239212036,
+      "learning_rate": 2.1188489525163367e-05,
+      "loss": 0.166,
+      "step": 2410
+    },
+    {
+      "epoch": 4.067226890756302,
+      "grad_norm": 0.7719018459320068,
+      "learning_rate": 2.047158048528165e-05,
+      "loss": 0.1421,
+      "step": 2420
+    },
+    {
+      "epoch": 4.084033613445378,
+      "grad_norm": 0.7346205115318298,
+      "learning_rate": 1.976562412467232e-05,
+      "loss": 0.174,
+      "step": 2430
+    },
+    {
+      "epoch": 4.100840336134453,
+      "grad_norm": 0.960121214389801,
+      "learning_rate": 1.9070717667870263e-05,
+      "loss": 0.1725,
+      "step": 2440
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.8343680500984192,
+      "learning_rate": 1.838695681761412e-05,
+      "loss": 0.1777,
+      "step": 2450
+    },
+    {
+      "epoch": 4.1344537815126055,
+      "grad_norm": 0.9134616851806641,
+      "learning_rate": 1.7714435741666037e-05,
+      "loss": 0.1541,
+      "step": 2460
+    },
+    {
+      "epoch": 4.151260504201681,
+      "grad_norm": 0.9840583801269531,
+      "learning_rate": 1.7053247059842793e-05,
+      "loss": 0.1905,
+      "step": 2470
+    },
+    {
+      "epoch": 4.168067226890757,
+      "grad_norm": 0.7404395341873169,
+      "learning_rate": 1.6403481831260338e-05,
+      "loss": 0.1803,
+      "step": 2480
+    },
+    {
+      "epoch": 4.184873949579832,
+      "grad_norm": 1.0390299558639526,
+      "learning_rate": 1.5765229541792982e-05,
+      "loss": 0.1691,
+      "step": 2490
+    },
+    {
+      "epoch": 4.201680672268908,
+      "grad_norm": 0.8568964600563049,
+      "learning_rate": 1.5138578091749334e-05,
+      "loss": 0.1706,
+      "step": 2500
+    },
+    {
+      "epoch": 4.218487394957983,
+      "grad_norm": 0.9740147590637207,
+      "learning_rate": 1.4523613783766732e-05,
+      "loss": 0.1795,
+      "step": 2510
+    },
+    {
+      "epoch": 4.235294117647059,
+      "grad_norm": 0.9405394792556763,
+      "learning_rate": 1.3920421310925636e-05,
+      "loss": 0.1614,
+      "step": 2520
+    },
+    {
+      "epoch": 4.2521008403361344,
+      "grad_norm": 0.8562027215957642,
+      "learning_rate": 1.3329083745085547e-05,
+      "loss": 0.1621,
+      "step": 2530
+    },
+    {
+      "epoch": 4.26890756302521,
+      "grad_norm": 0.8962126970291138,
+      "learning_rate": 1.2749682525444407e-05,
+      "loss": 0.1642,
+      "step": 2540
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.9526483416557312,
+      "learning_rate": 1.2182297447322787e-05,
+      "loss": 0.1581,
+      "step": 2550
+    },
+    {
+      "epoch": 4.302521008403361,
+      "grad_norm": 0.7188050746917725,
+      "learning_rate": 1.1627006651174444e-05,
+      "loss": 0.1861,
+      "step": 2560
+    },
+    {
+      "epoch": 4.319327731092437,
+      "grad_norm": 0.8526328206062317,
+      "learning_rate": 1.10838866118247e-05,
+      "loss": 0.1589,
+      "step": 2570
+    },
+    {
+      "epoch": 4.336134453781512,
+      "grad_norm": 0.845211923122406,
+      "learning_rate": 1.0553012127938389e-05,
+      "loss": 0.1958,
+      "step": 2580
+    },
+    {
+      "epoch": 4.352941176470588,
+      "grad_norm": 0.9076491594314575,
+      "learning_rate": 1.0034456311718609e-05,
+      "loss": 0.1664,
+      "step": 2590
+    },
+    {
+      "epoch": 4.369747899159664,
+      "grad_norm": 1.0046247243881226,
+      "learning_rate": 9.528290578837551e-06,
+      "loss": 0.1713,
+      "step": 2600
+    },
+    {
+      "epoch": 4.38655462184874,
+      "grad_norm": 0.7860477566719055,
+      "learning_rate": 9.034584638601196e-06,
+      "loss": 0.1494,
+      "step": 2610
+    },
+    {
+      "epoch": 4.4033613445378155,
+      "grad_norm": 1.0020995140075684,
+      "learning_rate": 8.553406484348914e-06,
+      "loss": 0.1823,
+      "step": 2620
+    },
+    {
+      "epoch": 4.420168067226891,
+      "grad_norm": 1.2964270114898682,
+      "learning_rate": 8.084822384089453e-06,
+      "loss": 0.1825,
+      "step": 2630
+    },
+    {
+      "epoch": 4.436974789915967,
+      "grad_norm": 1.0893545150756836,
+      "learning_rate": 7.628896871374358e-06,
+      "loss": 0.1799,
+      "step": 2640
+    },
+    {
+      "epoch": 4.453781512605042,
+      "grad_norm": 0.8512413501739502,
+      "learning_rate": 7.185692736410477e-06,
+      "loss": 0.1707,
+      "step": 2650
+    },
+    {
+      "epoch": 4.470588235294118,
+      "grad_norm": 1.3223856687545776,
+      "learning_rate": 6.755271017412501e-06,
+      "loss": 0.1748,
+      "step": 2660
+    },
+    {
+      "epoch": 4.487394957983193,
+      "grad_norm": 1.0431852340698242,
+      "learning_rate": 6.337690992196688e-06,
+      "loss": 0.1703,
+      "step": 2670
+    },
+    {
+      "epoch": 4.504201680672269,
+      "grad_norm": 1.3509666919708252,
+      "learning_rate": 5.933010170017139e-06,
+      "loss": 0.1717,
+      "step": 2680
+    },
+    {
+      "epoch": 4.5210084033613445,
+      "grad_norm": 0.9030164480209351,
+      "learning_rate": 5.54128428364562e-06,
+      "loss": 0.1866,
+      "step": 2690
+    },
+    {
+      "epoch": 4.53781512605042,
+      "grad_norm": 0.9294901490211487,
+      "learning_rate": 5.162567281696018e-06,
+      "loss": 0.1659,
+      "step": 2700
+    },
+    {
+      "epoch": 4.554621848739496,
+      "grad_norm": 0.887606680393219,
+      "learning_rate": 4.796911321194475e-06,
+      "loss": 0.166,
+      "step": 2710
+    },
+    {
+      "epoch": 4.571428571428571,
+      "grad_norm": 0.8213235139846802,
+      "learning_rate": 4.444366760396357e-06,
+      "loss": 0.1768,
+      "step": 2720
+    },
+    {
+      "epoch": 4.588235294117647,
+      "grad_norm": 0.9339560270309448,
+      "learning_rate": 4.104982151850911e-06,
+      "loss": 0.1769,
+      "step": 2730
+    },
+    {
+      "epoch": 4.605042016806722,
+      "grad_norm": 0.8878592252731323,
+      "learning_rate": 3.7788042357145616e-06,
+      "loss": 0.1708,
+      "step": 2740
+    },
+    {
+      "epoch": 4.621848739495798,
+      "grad_norm": 0.8466598987579346,
+      "learning_rate": 3.465877933313799e-06,
+      "loss": 0.176,
+      "step": 2750
+    },
+    {
+      "epoch": 4.6386554621848735,
+      "grad_norm": 0.8101462721824646,
+      "learning_rate": 3.166246340958712e-06,
+      "loss": 0.1722,
+      "step": 2760
+    },
+    {
+      "epoch": 4.65546218487395,
+      "grad_norm": 1.1340394020080566,
+      "learning_rate": 2.8799507240076406e-06,
+      "loss": 0.1851,
+      "step": 2770
+    },
+    {
+      "epoch": 4.6722689075630255,
+      "grad_norm": 1.2405331134796143,
+      "learning_rate": 2.607030511184183e-06,
+      "loss": 0.1671,
+      "step": 2780
+    },
+    {
+      "epoch": 4.689075630252101,
+      "grad_norm": 0.8664318323135376,
+      "learning_rate": 2.347523289146991e-06,
+      "loss": 0.1728,
+      "step": 2790
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.9817457795143127,
+      "learning_rate": 2.101464797313357e-06,
+      "loss": 0.1549,
+      "step": 2800
+    },
+    {
+      "epoch": 4.722689075630252,
+      "grad_norm": 0.8827335834503174,
+      "learning_rate": 1.868888922937162e-06,
+      "loss": 0.1423,
+      "step": 2810
+    },
+    {
+      "epoch": 4.739495798319328,
+      "grad_norm": 0.7880733609199524,
+      "learning_rate": 1.649827696441919e-06,
+      "loss": 0.1571,
+      "step": 2820
+    },
+    {
+      "epoch": 4.756302521008403,
+      "grad_norm": 1.198318600654602,
+      "learning_rate": 1.4443112870095588e-06,
+      "loss": 0.1624,
+      "step": 2830
+    },
+    {
+      "epoch": 4.773109243697479,
+      "grad_norm": 0.7685941457748413,
+      "learning_rate": 1.25236799842543e-06,
+      "loss": 0.1609,
+      "step": 2840
+    },
+    {
+      "epoch": 4.7899159663865545,
+      "grad_norm": 0.929218053817749,
+      "learning_rate": 1.0740242651803956e-06,
+      "loss": 0.1664,
+      "step": 2850
+    },
+    {
+      "epoch": 4.80672268907563,
+      "grad_norm": 0.9220144152641296,
+      "learning_rate": 9.093046488302337e-07,
+      "loss": 0.1793,
+      "step": 2860
+    },
+    {
+      "epoch": 4.823529411764706,
+      "grad_norm": 0.8192142844200134,
+      "learning_rate": 7.582318346129657e-07,
+      "loss": 0.1641,
+      "step": 2870
+    },
+    {
+      "epoch": 4.840336134453781,
+      "grad_norm": 0.8484081029891968,
+      "learning_rate": 6.20826628324711e-07,
+      "loss": 0.1508,
+      "step": 2880
+    },
+    {
+      "epoch": 4.857142857142857,
+      "grad_norm": 1.0260757207870483,
+      "learning_rate": 4.971079534542345e-07,
+      "loss": 0.1628,
+      "step": 2890
+    },
+    {
+      "epoch": 4.873949579831933,
+      "grad_norm": 0.9038840532302856,
+      "learning_rate": 3.8709284857687546e-07,
+      "loss": 0.1684,
+      "step": 2900
+    },
+    {
+      "epoch": 4.890756302521009,
+      "grad_norm": 0.7963437438011169,
+      "learning_rate": 2.9079646500792534e-07,
+      "loss": 0.1619,
+      "step": 2910
+    },
+    {
+      "epoch": 4.907563025210084,
+      "grad_norm": 0.8787494897842407,
+      "learning_rate": 2.0823206471599632e-07,
+      "loss": 0.1612,
+      "step": 2920
+    },
+    {
+      "epoch": 4.92436974789916,
+      "grad_norm": 1.0699881315231323,
+      "learning_rate": 1.3941101849660466e-07,
+      "loss": 0.1647,
+      "step": 2930
+    },
+    {
+      "epoch": 4.9411764705882355,
+      "grad_norm": 0.6501001715660095,
+      "learning_rate": 8.434280440616782e-08,
+      "loss": 0.1611,
+      "step": 2940
+    },
+    {
+      "epoch": 4.957983193277311,
+      "grad_norm": 0.9485645890235901,
+      "learning_rate": 4.3035006456670915e-08,
+      "loss": 0.1694,
+      "step": 2950
+    },
+    {
+      "epoch": 4.974789915966387,
+      "grad_norm": 0.8494912385940552,
+      "learning_rate": 1.5493313571202093e-08,
+      "loss": 0.1695,
+      "step": 2960
+    },
+    {
+      "epoch": 4.991596638655462,
+      "grad_norm": 0.9211341738700867,
+      "learning_rate": 1.7215188004904293e-09,
+      "loss": 0.155,
+      "step": 2970
+    },
+    {
+      "epoch": 5.0,
+      "step": 2975,
+      "total_flos": 2.1667263896407245e+17,
+      "train_loss": 0.34065224741687294,
+      "train_runtime": 1015.5372,
+      "train_samples_per_second": 93.62,
+      "train_steps_per_second": 2.929
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2975,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1667263896407245e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

code_alpaca/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a2a23609d87bc2dfe5a4fed09d881d61b8ca6708160a22f644979307a9407c
+size 5432