Commit
·
7fb25b6
0
Parent(s):
Upload SparseModernBERT α=1.5 checkpoints
Browse files- .gitattributes +2 -0
- all_results.json +9 -0
- checkpoint-100000/config.json +50 -0
- checkpoint-100000/model.safetensors +3 -0
- checkpoint-100000/optimizer.pt +3 -0
- checkpoint-100000/rng_state.pth +0 -0
- checkpoint-100000/scheduler.pt +3 -0
- checkpoint-100000/special_tokens_map.json +37 -0
- checkpoint-100000/tokenizer.json +0 -0
- checkpoint-100000/tokenizer_config.json +945 -0
- checkpoint-100000/trainer_state.json +733 -0
- checkpoint-100000/training_args.bin +0 -0
- config.json +50 -0
- model.safetensors +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- train_results.json +9 -0
- trainer_state.json +742 -0
- training_args.bin +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.0909051256832e+18,
|
| 4 |
+
"train_loss": 1.0107983074951172,
|
| 5 |
+
"train_runtime": 153234.8237,
|
| 6 |
+
"train_samples": 0,
|
| 7 |
+
"train_samples_per_second": 1.305,
|
| 8 |
+
"train_steps_per_second": 0.653
|
| 9 |
+
}
|
checkpoint-100000/config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CustomModernBertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 50281,
|
| 9 |
+
"classifier_activation": "gelu",
|
| 10 |
+
"classifier_bias": false,
|
| 11 |
+
"classifier_dropout": 0.0,
|
| 12 |
+
"classifier_pooling": "mean",
|
| 13 |
+
"cls_token_id": 50281,
|
| 14 |
+
"decoder_bias": true,
|
| 15 |
+
"deterministic_flash_attn": false,
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initial_alpha": 1.01,
|
| 24 |
+
"initializer_cutoff_factor": 2.0,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 1152,
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"local_attention": 128,
|
| 29 |
+
"local_rope_theta": 10000.0,
|
| 30 |
+
"max_position_embeddings": 8192,
|
| 31 |
+
"mlp_bias": false,
|
| 32 |
+
"mlp_dropout": 0.0,
|
| 33 |
+
"model_type": "modernbert",
|
| 34 |
+
"norm_bias": false,
|
| 35 |
+
"norm_eps": 1e-05,
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 22,
|
| 38 |
+
"pad_token_id": 50283,
|
| 39 |
+
"position_embedding_type": "absolute",
|
| 40 |
+
"post_iter": 7,
|
| 41 |
+
"pre_iter": 7,
|
| 42 |
+
"reference_compile": true,
|
| 43 |
+
"sep_token_id": 50282,
|
| 44 |
+
"sparse_pred_ignore_index": -100,
|
| 45 |
+
"sparse_prediction": false,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.48.0.dev0",
|
| 48 |
+
"use_triton_entmax": true,
|
| 49 |
+
"vocab_size": 50368
|
| 50 |
+
}
|
checkpoint-100000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c59b1702cb4ea2c17e77c907e2971df8133e7e45ce8cde85f8c0f295b345ac1f
|
| 3 |
+
size 598635032
|
checkpoint-100000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:379ab967752c713d1d2ebd15c74fdf9ee3fe81a30c246375bd39666a719cc15b
|
| 3 |
+
size 1197357242
|
checkpoint-100000/rng_state.pth
ADDED
|
Binary file (14.2 kB). View file
|
|
|
checkpoint-100000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a0f623996e9bdb0ece1893a6f4719b11c4f7a028d3631455f9f465cd294b823
|
| 3 |
+
size 1064
|
checkpoint-100000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
checkpoint-100000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
checkpoint-100000/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100000000,
|
| 6 |
+
"global_step": 100000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 1.5673162937164307,
|
| 14 |
+
"learning_rate": 9.9003e-06,
|
| 15 |
+
"loss": 1.0389,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 2.175995111465454,
|
| 21 |
+
"learning_rate": 9.8003e-06,
|
| 22 |
+
"loss": 1.0254,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 1.515001654624939,
|
| 28 |
+
"learning_rate": 9.700300000000001e-06,
|
| 29 |
+
"loss": 1.0222,
|
| 30 |
+
"step": 3000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 1.4583686590194702,
|
| 35 |
+
"learning_rate": 9.600300000000002e-06,
|
| 36 |
+
"loss": 1.0159,
|
| 37 |
+
"step": 4000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05,
|
| 41 |
+
"grad_norm": 1.7361509799957275,
|
| 42 |
+
"learning_rate": 9.500300000000001e-06,
|
| 43 |
+
"loss": 1.0143,
|
| 44 |
+
"step": 5000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"grad_norm": 1.4579741954803467,
|
| 49 |
+
"learning_rate": 9.4003e-06,
|
| 50 |
+
"loss": 1.0143,
|
| 51 |
+
"step": 6000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"grad_norm": 1.4651838541030884,
|
| 56 |
+
"learning_rate": 9.300300000000001e-06,
|
| 57 |
+
"loss": 1.016,
|
| 58 |
+
"step": 7000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08,
|
| 62 |
+
"grad_norm": 1.4496525526046753,
|
| 63 |
+
"learning_rate": 9.2003e-06,
|
| 64 |
+
"loss": 1.0077,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09,
|
| 69 |
+
"grad_norm": 1.500932216644287,
|
| 70 |
+
"learning_rate": 9.100300000000002e-06,
|
| 71 |
+
"loss": 1.0102,
|
| 72 |
+
"step": 9000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1,
|
| 76 |
+
"grad_norm": 1.572792887687683,
|
| 77 |
+
"learning_rate": 9.000300000000001e-06,
|
| 78 |
+
"loss": 1.014,
|
| 79 |
+
"step": 10000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11,
|
| 83 |
+
"grad_norm": 1.4459178447723389,
|
| 84 |
+
"learning_rate": 8.900400000000002e-06,
|
| 85 |
+
"loss": 1.0144,
|
| 86 |
+
"step": 11000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12,
|
| 90 |
+
"grad_norm": 1.6553645133972168,
|
| 91 |
+
"learning_rate": 8.800500000000002e-06,
|
| 92 |
+
"loss": 1.0085,
|
| 93 |
+
"step": 12000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"grad_norm": 1.517026424407959,
|
| 98 |
+
"learning_rate": 8.7005e-06,
|
| 99 |
+
"loss": 1.0113,
|
| 100 |
+
"step": 13000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.14,
|
| 104 |
+
"grad_norm": 1.547823429107666,
|
| 105 |
+
"learning_rate": 8.6005e-06,
|
| 106 |
+
"loss": 1.0142,
|
| 107 |
+
"step": 14000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.15,
|
| 111 |
+
"grad_norm": 1.4814399480819702,
|
| 112 |
+
"learning_rate": 8.500500000000001e-06,
|
| 113 |
+
"loss": 1.0033,
|
| 114 |
+
"step": 15000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.16,
|
| 118 |
+
"grad_norm": 1.7205946445465088,
|
| 119 |
+
"learning_rate": 8.4005e-06,
|
| 120 |
+
"loss": 1.0132,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.17,
|
| 125 |
+
"grad_norm": 1.655186414718628,
|
| 126 |
+
"learning_rate": 8.300600000000001e-06,
|
| 127 |
+
"loss": 1.0091,
|
| 128 |
+
"step": 17000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.18,
|
| 132 |
+
"grad_norm": 1.5006760358810425,
|
| 133 |
+
"learning_rate": 8.200700000000001e-06,
|
| 134 |
+
"loss": 1.0109,
|
| 135 |
+
"step": 18000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.19,
|
| 139 |
+
"grad_norm": 1.5290812253952026,
|
| 140 |
+
"learning_rate": 8.1007e-06,
|
| 141 |
+
"loss": 1.0114,
|
| 142 |
+
"step": 19000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2,
|
| 146 |
+
"grad_norm": 1.4716876745224,
|
| 147 |
+
"learning_rate": 8.0007e-06,
|
| 148 |
+
"loss": 1.0117,
|
| 149 |
+
"step": 20000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.21,
|
| 153 |
+
"grad_norm": 2.0684456825256348,
|
| 154 |
+
"learning_rate": 7.9007e-06,
|
| 155 |
+
"loss": 1.0063,
|
| 156 |
+
"step": 21000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.22,
|
| 160 |
+
"grad_norm": 1.4653006792068481,
|
| 161 |
+
"learning_rate": 7.8008e-06,
|
| 162 |
+
"loss": 1.0106,
|
| 163 |
+
"step": 22000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.23,
|
| 167 |
+
"grad_norm": 1.6020914316177368,
|
| 168 |
+
"learning_rate": 7.700800000000001e-06,
|
| 169 |
+
"loss": 1.0115,
|
| 170 |
+
"step": 23000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.24,
|
| 174 |
+
"grad_norm": 1.48885977268219,
|
| 175 |
+
"learning_rate": 7.6008e-06,
|
| 176 |
+
"loss": 1.0179,
|
| 177 |
+
"step": 24000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.25,
|
| 181 |
+
"grad_norm": 1.6026817560195923,
|
| 182 |
+
"learning_rate": 7.5008e-06,
|
| 183 |
+
"loss": 1.0098,
|
| 184 |
+
"step": 25000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.26,
|
| 188 |
+
"grad_norm": 1.8403682708740234,
|
| 189 |
+
"learning_rate": 7.400900000000001e-06,
|
| 190 |
+
"loss": 1.0115,
|
| 191 |
+
"step": 26000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.27,
|
| 195 |
+
"grad_norm": 1.908618450164795,
|
| 196 |
+
"learning_rate": 7.300900000000001e-06,
|
| 197 |
+
"loss": 1.0078,
|
| 198 |
+
"step": 27000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.28,
|
| 202 |
+
"grad_norm": 1.61348557472229,
|
| 203 |
+
"learning_rate": 7.201e-06,
|
| 204 |
+
"loss": 1.014,
|
| 205 |
+
"step": 28000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.29,
|
| 209 |
+
"grad_norm": 1.4422307014465332,
|
| 210 |
+
"learning_rate": 7.101e-06,
|
| 211 |
+
"loss": 1.0045,
|
| 212 |
+
"step": 29000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3,
|
| 216 |
+
"grad_norm": 1.5274263620376587,
|
| 217 |
+
"learning_rate": 7.001e-06,
|
| 218 |
+
"loss": 1.007,
|
| 219 |
+
"step": 30000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.31,
|
| 223 |
+
"grad_norm": 1.6283539533615112,
|
| 224 |
+
"learning_rate": 6.9012e-06,
|
| 225 |
+
"loss": 1.0098,
|
| 226 |
+
"step": 31000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.32,
|
| 230 |
+
"grad_norm": 1.4117109775543213,
|
| 231 |
+
"learning_rate": 6.8012e-06,
|
| 232 |
+
"loss": 1.0137,
|
| 233 |
+
"step": 32000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.33,
|
| 237 |
+
"grad_norm": 1.6345027685165405,
|
| 238 |
+
"learning_rate": 6.701200000000001e-06,
|
| 239 |
+
"loss": 1.0195,
|
| 240 |
+
"step": 33000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.34,
|
| 244 |
+
"grad_norm": 1.5019372701644897,
|
| 245 |
+
"learning_rate": 6.601300000000001e-06,
|
| 246 |
+
"loss": 1.0109,
|
| 247 |
+
"step": 34000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.35,
|
| 251 |
+
"grad_norm": 1.5113171339035034,
|
| 252 |
+
"learning_rate": 6.501300000000001e-06,
|
| 253 |
+
"loss": 1.0123,
|
| 254 |
+
"step": 35000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.36,
|
| 258 |
+
"grad_norm": 1.7723476886749268,
|
| 259 |
+
"learning_rate": 6.401400000000001e-06,
|
| 260 |
+
"loss": 1.0123,
|
| 261 |
+
"step": 36000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.37,
|
| 265 |
+
"grad_norm": 1.691326379776001,
|
| 266 |
+
"learning_rate": 6.301400000000001e-06,
|
| 267 |
+
"loss": 1.0168,
|
| 268 |
+
"step": 37000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.38,
|
| 272 |
+
"grad_norm": 1.8816444873809814,
|
| 273 |
+
"learning_rate": 6.2014000000000005e-06,
|
| 274 |
+
"loss": 1.0122,
|
| 275 |
+
"step": 38000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.39,
|
| 279 |
+
"grad_norm": 1.472257137298584,
|
| 280 |
+
"learning_rate": 6.1014000000000006e-06,
|
| 281 |
+
"loss": 1.0154,
|
| 282 |
+
"step": 39000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4,
|
| 286 |
+
"grad_norm": 1.6379979848861694,
|
| 287 |
+
"learning_rate": 6.0015e-06,
|
| 288 |
+
"loss": 1.0083,
|
| 289 |
+
"step": 40000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.41,
|
| 293 |
+
"grad_norm": 1.7332875728607178,
|
| 294 |
+
"learning_rate": 5.9015e-06,
|
| 295 |
+
"loss": 1.0094,
|
| 296 |
+
"step": 41000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.42,
|
| 300 |
+
"grad_norm": 1.7920299768447876,
|
| 301 |
+
"learning_rate": 5.8016000000000005e-06,
|
| 302 |
+
"loss": 1.0223,
|
| 303 |
+
"step": 42000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.43,
|
| 307 |
+
"grad_norm": 1.6276768445968628,
|
| 308 |
+
"learning_rate": 5.701600000000001e-06,
|
| 309 |
+
"loss": 1.0145,
|
| 310 |
+
"step": 43000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.44,
|
| 314 |
+
"grad_norm": 1.84978187084198,
|
| 315 |
+
"learning_rate": 5.601600000000001e-06,
|
| 316 |
+
"loss": 1.0138,
|
| 317 |
+
"step": 44000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.45,
|
| 321 |
+
"grad_norm": 1.6746885776519775,
|
| 322 |
+
"learning_rate": 5.5016e-06,
|
| 323 |
+
"loss": 1.0137,
|
| 324 |
+
"step": 45000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.46,
|
| 328 |
+
"grad_norm": 7.81512451171875,
|
| 329 |
+
"learning_rate": 5.4018000000000005e-06,
|
| 330 |
+
"loss": 1.0229,
|
| 331 |
+
"step": 46000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.47,
|
| 335 |
+
"grad_norm": 1.868177890777588,
|
| 336 |
+
"learning_rate": 5.301800000000001e-06,
|
| 337 |
+
"loss": 1.0218,
|
| 338 |
+
"step": 47000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.48,
|
| 342 |
+
"grad_norm": 2.3036234378814697,
|
| 343 |
+
"learning_rate": 5.2018e-06,
|
| 344 |
+
"loss": 1.0237,
|
| 345 |
+
"step": 48000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.49,
|
| 349 |
+
"grad_norm": 1.7692339420318604,
|
| 350 |
+
"learning_rate": 5.1020000000000004e-06,
|
| 351 |
+
"loss": 1.0198,
|
| 352 |
+
"step": 49000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5,
|
| 356 |
+
"grad_norm": 1.7446075677871704,
|
| 357 |
+
"learning_rate": 5.0020000000000006e-06,
|
| 358 |
+
"loss": 1.0207,
|
| 359 |
+
"step": 50000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.51,
|
| 363 |
+
"grad_norm": 1.5397661924362183,
|
| 364 |
+
"learning_rate": 4.902000000000001e-06,
|
| 365 |
+
"loss": 1.0189,
|
| 366 |
+
"step": 51000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.52,
|
| 370 |
+
"grad_norm": 1.762879490852356,
|
| 371 |
+
"learning_rate": 4.802000000000001e-06,
|
| 372 |
+
"loss": 1.0174,
|
| 373 |
+
"step": 52000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.53,
|
| 377 |
+
"grad_norm": 1.9986176490783691,
|
| 378 |
+
"learning_rate": 4.702e-06,
|
| 379 |
+
"loss": 1.0181,
|
| 380 |
+
"step": 53000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.54,
|
| 384 |
+
"grad_norm": 1.617098331451416,
|
| 385 |
+
"learning_rate": 4.6021e-06,
|
| 386 |
+
"loss": 1.0043,
|
| 387 |
+
"step": 54000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.55,
|
| 391 |
+
"grad_norm": 2.0762548446655273,
|
| 392 |
+
"learning_rate": 4.5021000000000005e-06,
|
| 393 |
+
"loss": 1.0117,
|
| 394 |
+
"step": 55000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.56,
|
| 398 |
+
"grad_norm": 1.9250789880752563,
|
| 399 |
+
"learning_rate": 4.4022e-06,
|
| 400 |
+
"loss": 1.0128,
|
| 401 |
+
"step": 56000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.57,
|
| 405 |
+
"grad_norm": 1.956571340560913,
|
| 406 |
+
"learning_rate": 4.3022e-06,
|
| 407 |
+
"loss": 1.0134,
|
| 408 |
+
"step": 57000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.58,
|
| 412 |
+
"grad_norm": 1.921067237854004,
|
| 413 |
+
"learning_rate": 4.2022e-06,
|
| 414 |
+
"loss": 1.0135,
|
| 415 |
+
"step": 58000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.59,
|
| 419 |
+
"grad_norm": 1.667677640914917,
|
| 420 |
+
"learning_rate": 4.1022e-06,
|
| 421 |
+
"loss": 1.0211,
|
| 422 |
+
"step": 59000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6,
|
| 426 |
+
"grad_norm": 1.9290637969970703,
|
| 427 |
+
"learning_rate": 4.0024e-06,
|
| 428 |
+
"loss": 1.0073,
|
| 429 |
+
"step": 60000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.61,
|
| 433 |
+
"grad_norm": 1.764079213142395,
|
| 434 |
+
"learning_rate": 3.9024e-06,
|
| 435 |
+
"loss": 1.0151,
|
| 436 |
+
"step": 61000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.62,
|
| 440 |
+
"grad_norm": 1.786582350730896,
|
| 441 |
+
"learning_rate": 3.8024000000000006e-06,
|
| 442 |
+
"loss": 1.0196,
|
| 443 |
+
"step": 62000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.63,
|
| 447 |
+
"grad_norm": 1.597281813621521,
|
| 448 |
+
"learning_rate": 3.7025000000000005e-06,
|
| 449 |
+
"loss": 1.0117,
|
| 450 |
+
"step": 63000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.64,
|
| 454 |
+
"grad_norm": 1.5449904203414917,
|
| 455 |
+
"learning_rate": 3.6025000000000002e-06,
|
| 456 |
+
"loss": 1.0063,
|
| 457 |
+
"step": 64000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.65,
|
| 461 |
+
"grad_norm": 1.5187263488769531,
|
| 462 |
+
"learning_rate": 3.5026000000000006e-06,
|
| 463 |
+
"loss": 1.0087,
|
| 464 |
+
"step": 65000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.66,
|
| 468 |
+
"grad_norm": 2.036907434463501,
|
| 469 |
+
"learning_rate": 3.4026000000000003e-06,
|
| 470 |
+
"loss": 1.0115,
|
| 471 |
+
"step": 66000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.67,
|
| 475 |
+
"grad_norm": 1.8339091539382935,
|
| 476 |
+
"learning_rate": 3.3026000000000004e-06,
|
| 477 |
+
"loss": 1.0055,
|
| 478 |
+
"step": 67000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.68,
|
| 482 |
+
"grad_norm": 1.6574101448059082,
|
| 483 |
+
"learning_rate": 3.2027000000000003e-06,
|
| 484 |
+
"loss": 1.0078,
|
| 485 |
+
"step": 68000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.69,
|
| 489 |
+
"grad_norm": 1.7668465375900269,
|
| 490 |
+
"learning_rate": 3.1028e-06,
|
| 491 |
+
"loss": 1.0012,
|
| 492 |
+
"step": 69000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7,
|
| 496 |
+
"grad_norm": 1.5608104467391968,
|
| 497 |
+
"learning_rate": 3.0028000000000003e-06,
|
| 498 |
+
"loss": 1.0063,
|
| 499 |
+
"step": 70000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.71,
|
| 503 |
+
"grad_norm": 1.808834433555603,
|
| 504 |
+
"learning_rate": 2.9028e-06,
|
| 505 |
+
"loss": 1.0063,
|
| 506 |
+
"step": 71000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.72,
|
| 510 |
+
"grad_norm": 1.8370723724365234,
|
| 511 |
+
"learning_rate": 2.8029e-06,
|
| 512 |
+
"loss": 1.0093,
|
| 513 |
+
"step": 72000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.73,
|
| 517 |
+
"grad_norm": 1.6162232160568237,
|
| 518 |
+
"learning_rate": 2.7029e-06,
|
| 519 |
+
"loss": 1.0092,
|
| 520 |
+
"step": 73000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.74,
|
| 524 |
+
"grad_norm": 1.728576421737671,
|
| 525 |
+
"learning_rate": 2.6029000000000005e-06,
|
| 526 |
+
"loss": 0.9978,
|
| 527 |
+
"step": 74000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.75,
|
| 531 |
+
"grad_norm": 1.6973289251327515,
|
| 532 |
+
"learning_rate": 2.5029e-06,
|
| 533 |
+
"loss": 1.0086,
|
| 534 |
+
"step": 75000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.76,
|
| 538 |
+
"grad_norm": 2.00152850151062,
|
| 539 |
+
"learning_rate": 2.4029000000000003e-06,
|
| 540 |
+
"loss": 1.0048,
|
| 541 |
+
"step": 76000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.77,
|
| 545 |
+
"grad_norm": 2.0380213260650635,
|
| 546 |
+
"learning_rate": 2.3029e-06,
|
| 547 |
+
"loss": 1.0067,
|
| 548 |
+
"step": 77000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.78,
|
| 552 |
+
"grad_norm": 1.9548099040985107,
|
| 553 |
+
"learning_rate": 2.2031e-06,
|
| 554 |
+
"loss": 1.0196,
|
| 555 |
+
"step": 78000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.79,
|
| 559 |
+
"grad_norm": 1.6247434616088867,
|
| 560 |
+
"learning_rate": 2.1031000000000002e-06,
|
| 561 |
+
"loss": 1.0067,
|
| 562 |
+
"step": 79000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8,
|
| 566 |
+
"grad_norm": 1.6271846294403076,
|
| 567 |
+
"learning_rate": 2.0031e-06,
|
| 568 |
+
"loss": 1.0075,
|
| 569 |
+
"step": 80000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.81,
|
| 573 |
+
"grad_norm": 1.7199640274047852,
|
| 574 |
+
"learning_rate": 1.9031000000000003e-06,
|
| 575 |
+
"loss": 0.9991,
|
| 576 |
+
"step": 81000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.82,
|
| 580 |
+
"grad_norm": 1.5637553930282593,
|
| 581 |
+
"learning_rate": 1.8033e-06,
|
| 582 |
+
"loss": 1.0045,
|
| 583 |
+
"step": 82000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.83,
|
| 587 |
+
"grad_norm": 1.5427855253219604,
|
| 588 |
+
"learning_rate": 1.7033000000000003e-06,
|
| 589 |
+
"loss": 1.0053,
|
| 590 |
+
"step": 83000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.84,
|
| 594 |
+
"grad_norm": 2.7503976821899414,
|
| 595 |
+
"learning_rate": 1.6033000000000002e-06,
|
| 596 |
+
"loss": 1.0032,
|
| 597 |
+
"step": 84000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.85,
|
| 601 |
+
"grad_norm": 1.8314589262008667,
|
| 602 |
+
"learning_rate": 1.5033e-06,
|
| 603 |
+
"loss": 1.0065,
|
| 604 |
+
"step": 85000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.86,
|
| 608 |
+
"grad_norm": 1.925482988357544,
|
| 609 |
+
"learning_rate": 1.4033000000000002e-06,
|
| 610 |
+
"loss": 1.0065,
|
| 611 |
+
"step": 86000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.87,
|
| 615 |
+
"grad_norm": 1.8822989463806152,
|
| 616 |
+
"learning_rate": 1.3033e-06,
|
| 617 |
+
"loss": 1.0104,
|
| 618 |
+
"step": 87000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.88,
|
| 622 |
+
"grad_norm": 1.5026013851165771,
|
| 623 |
+
"learning_rate": 1.2035e-06,
|
| 624 |
+
"loss": 1.0055,
|
| 625 |
+
"step": 88000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.89,
|
| 629 |
+
"grad_norm": 1.8803695440292358,
|
| 630 |
+
"learning_rate": 1.1035000000000001e-06,
|
| 631 |
+
"loss": 1.0017,
|
| 632 |
+
"step": 89000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9,
|
| 636 |
+
"grad_norm": 1.9868890047073364,
|
| 637 |
+
"learning_rate": 1.0035e-06,
|
| 638 |
+
"loss": 0.9994,
|
| 639 |
+
"step": 90000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.91,
|
| 643 |
+
"grad_norm": 1.9017215967178345,
|
| 644 |
+
"learning_rate": 9.035000000000001e-07,
|
| 645 |
+
"loss": 0.9996,
|
| 646 |
+
"step": 91000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.92,
|
| 650 |
+
"grad_norm": 1.4807873964309692,
|
| 651 |
+
"learning_rate": 8.036e-07,
|
| 652 |
+
"loss": 1.0046,
|
| 653 |
+
"step": 92000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.93,
|
| 657 |
+
"grad_norm": 1.6405707597732544,
|
| 658 |
+
"learning_rate": 7.036000000000001e-07,
|
| 659 |
+
"loss": 1.0001,
|
| 660 |
+
"step": 93000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.94,
|
| 664 |
+
"grad_norm": 1.6944319009780884,
|
| 665 |
+
"learning_rate": 6.036e-07,
|
| 666 |
+
"loss": 1.0017,
|
| 667 |
+
"step": 94000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.95,
|
| 671 |
+
"grad_norm": 1.8059883117675781,
|
| 672 |
+
"learning_rate": 5.037e-07,
|
| 673 |
+
"loss": 1.009,
|
| 674 |
+
"step": 95000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.96,
|
| 678 |
+
"grad_norm": 1.6612234115600586,
|
| 679 |
+
"learning_rate": 4.038e-07,
|
| 680 |
+
"loss": 1.0013,
|
| 681 |
+
"step": 96000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.97,
|
| 685 |
+
"grad_norm": 1.8323150873184204,
|
| 686 |
+
"learning_rate": 3.038e-07,
|
| 687 |
+
"loss": 1.0077,
|
| 688 |
+
"step": 97000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.98,
|
| 692 |
+
"grad_norm": 1.857452630996704,
|
| 693 |
+
"learning_rate": 2.038e-07,
|
| 694 |
+
"loss": 0.9959,
|
| 695 |
+
"step": 98000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.99,
|
| 699 |
+
"grad_norm": 1.6731070280075073,
|
| 700 |
+
"learning_rate": 1.0380000000000002e-07,
|
| 701 |
+
"loss": 1.0085,
|
| 702 |
+
"step": 99000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0,
|
| 706 |
+
"grad_norm": 1.7343461513519287,
|
| 707 |
+
"learning_rate": 3.9e-09,
|
| 708 |
+
"loss": 0.9988,
|
| 709 |
+
"step": 100000
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 1000,
|
| 713 |
+
"max_steps": 100000,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 9223372036854775807,
|
| 716 |
+
"save_steps": 20000,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": true
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 1.0909051256832e+18,
|
| 730 |
+
"train_batch_size": 2,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
checkpoint-100000/training_args.bin
ADDED
|
Binary file (5.5 kB). View file
|
|
|
config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CustomModernBertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 50281,
|
| 9 |
+
"classifier_activation": "gelu",
|
| 10 |
+
"classifier_bias": false,
|
| 11 |
+
"classifier_dropout": 0.0,
|
| 12 |
+
"classifier_pooling": "mean",
|
| 13 |
+
"cls_token_id": 50281,
|
| 14 |
+
"decoder_bias": true,
|
| 15 |
+
"deterministic_flash_attn": false,
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"global_rope_theta": 160000.0,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_activation": "gelu",
|
| 22 |
+
"hidden_size": 768,
|
| 23 |
+
"initial_alpha": 1.01,
|
| 24 |
+
"initializer_cutoff_factor": 2.0,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 1152,
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"local_attention": 128,
|
| 29 |
+
"local_rope_theta": 10000.0,
|
| 30 |
+
"max_position_embeddings": 8192,
|
| 31 |
+
"mlp_bias": false,
|
| 32 |
+
"mlp_dropout": 0.0,
|
| 33 |
+
"model_type": "modernbert",
|
| 34 |
+
"norm_bias": false,
|
| 35 |
+
"norm_eps": 1e-05,
|
| 36 |
+
"num_attention_heads": 12,
|
| 37 |
+
"num_hidden_layers": 22,
|
| 38 |
+
"pad_token_id": 50283,
|
| 39 |
+
"position_embedding_type": "absolute",
|
| 40 |
+
"post_iter": 7,
|
| 41 |
+
"pre_iter": 7,
|
| 42 |
+
"reference_compile": true,
|
| 43 |
+
"sep_token_id": 50282,
|
| 44 |
+
"sparse_pred_ignore_index": -100,
|
| 45 |
+
"sparse_prediction": false,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.48.0.dev0",
|
| 48 |
+
"use_triton_entmax": true,
|
| 49 |
+
"vocab_size": 50368
|
| 50 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c59b1702cb4ea2c17e77c907e2971df8133e7e45ce8cde85f8c0f295b345ac1f
|
| 3 |
+
size 598635032
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.0909051256832e+18,
|
| 4 |
+
"train_loss": 1.0107983074951172,
|
| 5 |
+
"train_runtime": 153234.8237,
|
| 6 |
+
"train_samples": 0,
|
| 7 |
+
"train_samples_per_second": 1.305,
|
| 8 |
+
"train_steps_per_second": 0.653
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,742 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 100000000,
|
| 6 |
+
"global_step": 100000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"grad_norm": 1.5673162937164307,
|
| 14 |
+
"learning_rate": 9.9003e-06,
|
| 15 |
+
"loss": 1.0389,
|
| 16 |
+
"step": 1000
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02,
|
| 20 |
+
"grad_norm": 2.175995111465454,
|
| 21 |
+
"learning_rate": 9.8003e-06,
|
| 22 |
+
"loss": 1.0254,
|
| 23 |
+
"step": 2000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.03,
|
| 27 |
+
"grad_norm": 1.515001654624939,
|
| 28 |
+
"learning_rate": 9.700300000000001e-06,
|
| 29 |
+
"loss": 1.0222,
|
| 30 |
+
"step": 3000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.04,
|
| 34 |
+
"grad_norm": 1.4583686590194702,
|
| 35 |
+
"learning_rate": 9.600300000000002e-06,
|
| 36 |
+
"loss": 1.0159,
|
| 37 |
+
"step": 4000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.05,
|
| 41 |
+
"grad_norm": 1.7361509799957275,
|
| 42 |
+
"learning_rate": 9.500300000000001e-06,
|
| 43 |
+
"loss": 1.0143,
|
| 44 |
+
"step": 5000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06,
|
| 48 |
+
"grad_norm": 1.4579741954803467,
|
| 49 |
+
"learning_rate": 9.4003e-06,
|
| 50 |
+
"loss": 1.0143,
|
| 51 |
+
"step": 6000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"grad_norm": 1.4651838541030884,
|
| 56 |
+
"learning_rate": 9.300300000000001e-06,
|
| 57 |
+
"loss": 1.016,
|
| 58 |
+
"step": 7000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08,
|
| 62 |
+
"grad_norm": 1.4496525526046753,
|
| 63 |
+
"learning_rate": 9.2003e-06,
|
| 64 |
+
"loss": 1.0077,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09,
|
| 69 |
+
"grad_norm": 1.500932216644287,
|
| 70 |
+
"learning_rate": 9.100300000000002e-06,
|
| 71 |
+
"loss": 1.0102,
|
| 72 |
+
"step": 9000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.1,
|
| 76 |
+
"grad_norm": 1.572792887687683,
|
| 77 |
+
"learning_rate": 9.000300000000001e-06,
|
| 78 |
+
"loss": 1.014,
|
| 79 |
+
"step": 10000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.11,
|
| 83 |
+
"grad_norm": 1.4459178447723389,
|
| 84 |
+
"learning_rate": 8.900400000000002e-06,
|
| 85 |
+
"loss": 1.0144,
|
| 86 |
+
"step": 11000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.12,
|
| 90 |
+
"grad_norm": 1.6553645133972168,
|
| 91 |
+
"learning_rate": 8.800500000000002e-06,
|
| 92 |
+
"loss": 1.0085,
|
| 93 |
+
"step": 12000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"grad_norm": 1.517026424407959,
|
| 98 |
+
"learning_rate": 8.7005e-06,
|
| 99 |
+
"loss": 1.0113,
|
| 100 |
+
"step": 13000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.14,
|
| 104 |
+
"grad_norm": 1.547823429107666,
|
| 105 |
+
"learning_rate": 8.6005e-06,
|
| 106 |
+
"loss": 1.0142,
|
| 107 |
+
"step": 14000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.15,
|
| 111 |
+
"grad_norm": 1.4814399480819702,
|
| 112 |
+
"learning_rate": 8.500500000000001e-06,
|
| 113 |
+
"loss": 1.0033,
|
| 114 |
+
"step": 15000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.16,
|
| 118 |
+
"grad_norm": 1.7205946445465088,
|
| 119 |
+
"learning_rate": 8.4005e-06,
|
| 120 |
+
"loss": 1.0132,
|
| 121 |
+
"step": 16000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.17,
|
| 125 |
+
"grad_norm": 1.655186414718628,
|
| 126 |
+
"learning_rate": 8.300600000000001e-06,
|
| 127 |
+
"loss": 1.0091,
|
| 128 |
+
"step": 17000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.18,
|
| 132 |
+
"grad_norm": 1.5006760358810425,
|
| 133 |
+
"learning_rate": 8.200700000000001e-06,
|
| 134 |
+
"loss": 1.0109,
|
| 135 |
+
"step": 18000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.19,
|
| 139 |
+
"grad_norm": 1.5290812253952026,
|
| 140 |
+
"learning_rate": 8.1007e-06,
|
| 141 |
+
"loss": 1.0114,
|
| 142 |
+
"step": 19000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2,
|
| 146 |
+
"grad_norm": 1.4716876745224,
|
| 147 |
+
"learning_rate": 8.0007e-06,
|
| 148 |
+
"loss": 1.0117,
|
| 149 |
+
"step": 20000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.21,
|
| 153 |
+
"grad_norm": 2.0684456825256348,
|
| 154 |
+
"learning_rate": 7.9007e-06,
|
| 155 |
+
"loss": 1.0063,
|
| 156 |
+
"step": 21000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.22,
|
| 160 |
+
"grad_norm": 1.4653006792068481,
|
| 161 |
+
"learning_rate": 7.8008e-06,
|
| 162 |
+
"loss": 1.0106,
|
| 163 |
+
"step": 22000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.23,
|
| 167 |
+
"grad_norm": 1.6020914316177368,
|
| 168 |
+
"learning_rate": 7.700800000000001e-06,
|
| 169 |
+
"loss": 1.0115,
|
| 170 |
+
"step": 23000
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.24,
|
| 174 |
+
"grad_norm": 1.48885977268219,
|
| 175 |
+
"learning_rate": 7.6008e-06,
|
| 176 |
+
"loss": 1.0179,
|
| 177 |
+
"step": 24000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.25,
|
| 181 |
+
"grad_norm": 1.6026817560195923,
|
| 182 |
+
"learning_rate": 7.5008e-06,
|
| 183 |
+
"loss": 1.0098,
|
| 184 |
+
"step": 25000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.26,
|
| 188 |
+
"grad_norm": 1.8403682708740234,
|
| 189 |
+
"learning_rate": 7.400900000000001e-06,
|
| 190 |
+
"loss": 1.0115,
|
| 191 |
+
"step": 26000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.27,
|
| 195 |
+
"grad_norm": 1.908618450164795,
|
| 196 |
+
"learning_rate": 7.300900000000001e-06,
|
| 197 |
+
"loss": 1.0078,
|
| 198 |
+
"step": 27000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.28,
|
| 202 |
+
"grad_norm": 1.61348557472229,
|
| 203 |
+
"learning_rate": 7.201e-06,
|
| 204 |
+
"loss": 1.014,
|
| 205 |
+
"step": 28000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.29,
|
| 209 |
+
"grad_norm": 1.4422307014465332,
|
| 210 |
+
"learning_rate": 7.101e-06,
|
| 211 |
+
"loss": 1.0045,
|
| 212 |
+
"step": 29000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.3,
|
| 216 |
+
"grad_norm": 1.5274263620376587,
|
| 217 |
+
"learning_rate": 7.001e-06,
|
| 218 |
+
"loss": 1.007,
|
| 219 |
+
"step": 30000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.31,
|
| 223 |
+
"grad_norm": 1.6283539533615112,
|
| 224 |
+
"learning_rate": 6.9012e-06,
|
| 225 |
+
"loss": 1.0098,
|
| 226 |
+
"step": 31000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.32,
|
| 230 |
+
"grad_norm": 1.4117109775543213,
|
| 231 |
+
"learning_rate": 6.8012e-06,
|
| 232 |
+
"loss": 1.0137,
|
| 233 |
+
"step": 32000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.33,
|
| 237 |
+
"grad_norm": 1.6345027685165405,
|
| 238 |
+
"learning_rate": 6.701200000000001e-06,
|
| 239 |
+
"loss": 1.0195,
|
| 240 |
+
"step": 33000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.34,
|
| 244 |
+
"grad_norm": 1.5019372701644897,
|
| 245 |
+
"learning_rate": 6.601300000000001e-06,
|
| 246 |
+
"loss": 1.0109,
|
| 247 |
+
"step": 34000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.35,
|
| 251 |
+
"grad_norm": 1.5113171339035034,
|
| 252 |
+
"learning_rate": 6.501300000000001e-06,
|
| 253 |
+
"loss": 1.0123,
|
| 254 |
+
"step": 35000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.36,
|
| 258 |
+
"grad_norm": 1.7723476886749268,
|
| 259 |
+
"learning_rate": 6.401400000000001e-06,
|
| 260 |
+
"loss": 1.0123,
|
| 261 |
+
"step": 36000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.37,
|
| 265 |
+
"grad_norm": 1.691326379776001,
|
| 266 |
+
"learning_rate": 6.301400000000001e-06,
|
| 267 |
+
"loss": 1.0168,
|
| 268 |
+
"step": 37000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.38,
|
| 272 |
+
"grad_norm": 1.8816444873809814,
|
| 273 |
+
"learning_rate": 6.2014000000000005e-06,
|
| 274 |
+
"loss": 1.0122,
|
| 275 |
+
"step": 38000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.39,
|
| 279 |
+
"grad_norm": 1.472257137298584,
|
| 280 |
+
"learning_rate": 6.1014000000000006e-06,
|
| 281 |
+
"loss": 1.0154,
|
| 282 |
+
"step": 39000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4,
|
| 286 |
+
"grad_norm": 1.6379979848861694,
|
| 287 |
+
"learning_rate": 6.0015e-06,
|
| 288 |
+
"loss": 1.0083,
|
| 289 |
+
"step": 40000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.41,
|
| 293 |
+
"grad_norm": 1.7332875728607178,
|
| 294 |
+
"learning_rate": 5.9015e-06,
|
| 295 |
+
"loss": 1.0094,
|
| 296 |
+
"step": 41000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.42,
|
| 300 |
+
"grad_norm": 1.7920299768447876,
|
| 301 |
+
"learning_rate": 5.8016000000000005e-06,
|
| 302 |
+
"loss": 1.0223,
|
| 303 |
+
"step": 42000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.43,
|
| 307 |
+
"grad_norm": 1.6276768445968628,
|
| 308 |
+
"learning_rate": 5.701600000000001e-06,
|
| 309 |
+
"loss": 1.0145,
|
| 310 |
+
"step": 43000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.44,
|
| 314 |
+
"grad_norm": 1.84978187084198,
|
| 315 |
+
"learning_rate": 5.601600000000001e-06,
|
| 316 |
+
"loss": 1.0138,
|
| 317 |
+
"step": 44000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.45,
|
| 321 |
+
"grad_norm": 1.6746885776519775,
|
| 322 |
+
"learning_rate": 5.5016e-06,
|
| 323 |
+
"loss": 1.0137,
|
| 324 |
+
"step": 45000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.46,
|
| 328 |
+
"grad_norm": 7.81512451171875,
|
| 329 |
+
"learning_rate": 5.4018000000000005e-06,
|
| 330 |
+
"loss": 1.0229,
|
| 331 |
+
"step": 46000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.47,
|
| 335 |
+
"grad_norm": 1.868177890777588,
|
| 336 |
+
"learning_rate": 5.301800000000001e-06,
|
| 337 |
+
"loss": 1.0218,
|
| 338 |
+
"step": 47000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.48,
|
| 342 |
+
"grad_norm": 2.3036234378814697,
|
| 343 |
+
"learning_rate": 5.2018e-06,
|
| 344 |
+
"loss": 1.0237,
|
| 345 |
+
"step": 48000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.49,
|
| 349 |
+
"grad_norm": 1.7692339420318604,
|
| 350 |
+
"learning_rate": 5.1020000000000004e-06,
|
| 351 |
+
"loss": 1.0198,
|
| 352 |
+
"step": 49000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5,
|
| 356 |
+
"grad_norm": 1.7446075677871704,
|
| 357 |
+
"learning_rate": 5.0020000000000006e-06,
|
| 358 |
+
"loss": 1.0207,
|
| 359 |
+
"step": 50000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.51,
|
| 363 |
+
"grad_norm": 1.5397661924362183,
|
| 364 |
+
"learning_rate": 4.902000000000001e-06,
|
| 365 |
+
"loss": 1.0189,
|
| 366 |
+
"step": 51000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.52,
|
| 370 |
+
"grad_norm": 1.762879490852356,
|
| 371 |
+
"learning_rate": 4.802000000000001e-06,
|
| 372 |
+
"loss": 1.0174,
|
| 373 |
+
"step": 52000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.53,
|
| 377 |
+
"grad_norm": 1.9986176490783691,
|
| 378 |
+
"learning_rate": 4.702e-06,
|
| 379 |
+
"loss": 1.0181,
|
| 380 |
+
"step": 53000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.54,
|
| 384 |
+
"grad_norm": 1.617098331451416,
|
| 385 |
+
"learning_rate": 4.6021e-06,
|
| 386 |
+
"loss": 1.0043,
|
| 387 |
+
"step": 54000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.55,
|
| 391 |
+
"grad_norm": 2.0762548446655273,
|
| 392 |
+
"learning_rate": 4.5021000000000005e-06,
|
| 393 |
+
"loss": 1.0117,
|
| 394 |
+
"step": 55000
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.56,
|
| 398 |
+
"grad_norm": 1.9250789880752563,
|
| 399 |
+
"learning_rate": 4.4022e-06,
|
| 400 |
+
"loss": 1.0128,
|
| 401 |
+
"step": 56000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.57,
|
| 405 |
+
"grad_norm": 1.956571340560913,
|
| 406 |
+
"learning_rate": 4.3022e-06,
|
| 407 |
+
"loss": 1.0134,
|
| 408 |
+
"step": 57000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.58,
|
| 412 |
+
"grad_norm": 1.921067237854004,
|
| 413 |
+
"learning_rate": 4.2022e-06,
|
| 414 |
+
"loss": 1.0135,
|
| 415 |
+
"step": 58000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.59,
|
| 419 |
+
"grad_norm": 1.667677640914917,
|
| 420 |
+
"learning_rate": 4.1022e-06,
|
| 421 |
+
"loss": 1.0211,
|
| 422 |
+
"step": 59000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6,
|
| 426 |
+
"grad_norm": 1.9290637969970703,
|
| 427 |
+
"learning_rate": 4.0024e-06,
|
| 428 |
+
"loss": 1.0073,
|
| 429 |
+
"step": 60000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.61,
|
| 433 |
+
"grad_norm": 1.764079213142395,
|
| 434 |
+
"learning_rate": 3.9024e-06,
|
| 435 |
+
"loss": 1.0151,
|
| 436 |
+
"step": 61000
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.62,
|
| 440 |
+
"grad_norm": 1.786582350730896,
|
| 441 |
+
"learning_rate": 3.8024000000000006e-06,
|
| 442 |
+
"loss": 1.0196,
|
| 443 |
+
"step": 62000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.63,
|
| 447 |
+
"grad_norm": 1.597281813621521,
|
| 448 |
+
"learning_rate": 3.7025000000000005e-06,
|
| 449 |
+
"loss": 1.0117,
|
| 450 |
+
"step": 63000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.64,
|
| 454 |
+
"grad_norm": 1.5449904203414917,
|
| 455 |
+
"learning_rate": 3.6025000000000002e-06,
|
| 456 |
+
"loss": 1.0063,
|
| 457 |
+
"step": 64000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.65,
|
| 461 |
+
"grad_norm": 1.5187263488769531,
|
| 462 |
+
"learning_rate": 3.5026000000000006e-06,
|
| 463 |
+
"loss": 1.0087,
|
| 464 |
+
"step": 65000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.66,
|
| 468 |
+
"grad_norm": 2.036907434463501,
|
| 469 |
+
"learning_rate": 3.4026000000000003e-06,
|
| 470 |
+
"loss": 1.0115,
|
| 471 |
+
"step": 66000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.67,
|
| 475 |
+
"grad_norm": 1.8339091539382935,
|
| 476 |
+
"learning_rate": 3.3026000000000004e-06,
|
| 477 |
+
"loss": 1.0055,
|
| 478 |
+
"step": 67000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.68,
|
| 482 |
+
"grad_norm": 1.6574101448059082,
|
| 483 |
+
"learning_rate": 3.2027000000000003e-06,
|
| 484 |
+
"loss": 1.0078,
|
| 485 |
+
"step": 68000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.69,
|
| 489 |
+
"grad_norm": 1.7668465375900269,
|
| 490 |
+
"learning_rate": 3.1028e-06,
|
| 491 |
+
"loss": 1.0012,
|
| 492 |
+
"step": 69000
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7,
|
| 496 |
+
"grad_norm": 1.5608104467391968,
|
| 497 |
+
"learning_rate": 3.0028000000000003e-06,
|
| 498 |
+
"loss": 1.0063,
|
| 499 |
+
"step": 70000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.71,
|
| 503 |
+
"grad_norm": 1.808834433555603,
|
| 504 |
+
"learning_rate": 2.9028e-06,
|
| 505 |
+
"loss": 1.0063,
|
| 506 |
+
"step": 71000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.72,
|
| 510 |
+
"grad_norm": 1.8370723724365234,
|
| 511 |
+
"learning_rate": 2.8029e-06,
|
| 512 |
+
"loss": 1.0093,
|
| 513 |
+
"step": 72000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.73,
|
| 517 |
+
"grad_norm": 1.6162232160568237,
|
| 518 |
+
"learning_rate": 2.7029e-06,
|
| 519 |
+
"loss": 1.0092,
|
| 520 |
+
"step": 73000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.74,
|
| 524 |
+
"grad_norm": 1.728576421737671,
|
| 525 |
+
"learning_rate": 2.6029000000000005e-06,
|
| 526 |
+
"loss": 0.9978,
|
| 527 |
+
"step": 74000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.75,
|
| 531 |
+
"grad_norm": 1.6973289251327515,
|
| 532 |
+
"learning_rate": 2.5029e-06,
|
| 533 |
+
"loss": 1.0086,
|
| 534 |
+
"step": 75000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.76,
|
| 538 |
+
"grad_norm": 2.00152850151062,
|
| 539 |
+
"learning_rate": 2.4029000000000003e-06,
|
| 540 |
+
"loss": 1.0048,
|
| 541 |
+
"step": 76000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.77,
|
| 545 |
+
"grad_norm": 2.0380213260650635,
|
| 546 |
+
"learning_rate": 2.3029e-06,
|
| 547 |
+
"loss": 1.0067,
|
| 548 |
+
"step": 77000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.78,
|
| 552 |
+
"grad_norm": 1.9548099040985107,
|
| 553 |
+
"learning_rate": 2.2031e-06,
|
| 554 |
+
"loss": 1.0196,
|
| 555 |
+
"step": 78000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.79,
|
| 559 |
+
"grad_norm": 1.6247434616088867,
|
| 560 |
+
"learning_rate": 2.1031000000000002e-06,
|
| 561 |
+
"loss": 1.0067,
|
| 562 |
+
"step": 79000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8,
|
| 566 |
+
"grad_norm": 1.6271846294403076,
|
| 567 |
+
"learning_rate": 2.0031e-06,
|
| 568 |
+
"loss": 1.0075,
|
| 569 |
+
"step": 80000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.81,
|
| 573 |
+
"grad_norm": 1.7199640274047852,
|
| 574 |
+
"learning_rate": 1.9031000000000003e-06,
|
| 575 |
+
"loss": 0.9991,
|
| 576 |
+
"step": 81000
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.82,
|
| 580 |
+
"grad_norm": 1.5637553930282593,
|
| 581 |
+
"learning_rate": 1.8033e-06,
|
| 582 |
+
"loss": 1.0045,
|
| 583 |
+
"step": 82000
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.83,
|
| 587 |
+
"grad_norm": 1.5427855253219604,
|
| 588 |
+
"learning_rate": 1.7033000000000003e-06,
|
| 589 |
+
"loss": 1.0053,
|
| 590 |
+
"step": 83000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.84,
|
| 594 |
+
"grad_norm": 2.7503976821899414,
|
| 595 |
+
"learning_rate": 1.6033000000000002e-06,
|
| 596 |
+
"loss": 1.0032,
|
| 597 |
+
"step": 84000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.85,
|
| 601 |
+
"grad_norm": 1.8314589262008667,
|
| 602 |
+
"learning_rate": 1.5033e-06,
|
| 603 |
+
"loss": 1.0065,
|
| 604 |
+
"step": 85000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.86,
|
| 608 |
+
"grad_norm": 1.925482988357544,
|
| 609 |
+
"learning_rate": 1.4033000000000002e-06,
|
| 610 |
+
"loss": 1.0065,
|
| 611 |
+
"step": 86000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.87,
|
| 615 |
+
"grad_norm": 1.8822989463806152,
|
| 616 |
+
"learning_rate": 1.3033e-06,
|
| 617 |
+
"loss": 1.0104,
|
| 618 |
+
"step": 87000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.88,
|
| 622 |
+
"grad_norm": 1.5026013851165771,
|
| 623 |
+
"learning_rate": 1.2035e-06,
|
| 624 |
+
"loss": 1.0055,
|
| 625 |
+
"step": 88000
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.89,
|
| 629 |
+
"grad_norm": 1.8803695440292358,
|
| 630 |
+
"learning_rate": 1.1035000000000001e-06,
|
| 631 |
+
"loss": 1.0017,
|
| 632 |
+
"step": 89000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9,
|
| 636 |
+
"grad_norm": 1.9868890047073364,
|
| 637 |
+
"learning_rate": 1.0035e-06,
|
| 638 |
+
"loss": 0.9994,
|
| 639 |
+
"step": 90000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.91,
|
| 643 |
+
"grad_norm": 1.9017215967178345,
|
| 644 |
+
"learning_rate": 9.035000000000001e-07,
|
| 645 |
+
"loss": 0.9996,
|
| 646 |
+
"step": 91000
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.92,
|
| 650 |
+
"grad_norm": 1.4807873964309692,
|
| 651 |
+
"learning_rate": 8.036e-07,
|
| 652 |
+
"loss": 1.0046,
|
| 653 |
+
"step": 92000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.93,
|
| 657 |
+
"grad_norm": 1.6405707597732544,
|
| 658 |
+
"learning_rate": 7.036000000000001e-07,
|
| 659 |
+
"loss": 1.0001,
|
| 660 |
+
"step": 93000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.94,
|
| 664 |
+
"grad_norm": 1.6944319009780884,
|
| 665 |
+
"learning_rate": 6.036e-07,
|
| 666 |
+
"loss": 1.0017,
|
| 667 |
+
"step": 94000
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.95,
|
| 671 |
+
"grad_norm": 1.8059883117675781,
|
| 672 |
+
"learning_rate": 5.037e-07,
|
| 673 |
+
"loss": 1.009,
|
| 674 |
+
"step": 95000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.96,
|
| 678 |
+
"grad_norm": 1.6612234115600586,
|
| 679 |
+
"learning_rate": 4.038e-07,
|
| 680 |
+
"loss": 1.0013,
|
| 681 |
+
"step": 96000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.97,
|
| 685 |
+
"grad_norm": 1.8323150873184204,
|
| 686 |
+
"learning_rate": 3.038e-07,
|
| 687 |
+
"loss": 1.0077,
|
| 688 |
+
"step": 97000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.98,
|
| 692 |
+
"grad_norm": 1.857452630996704,
|
| 693 |
+
"learning_rate": 2.038e-07,
|
| 694 |
+
"loss": 0.9959,
|
| 695 |
+
"step": 98000
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.99,
|
| 699 |
+
"grad_norm": 1.6731070280075073,
|
| 700 |
+
"learning_rate": 1.0380000000000002e-07,
|
| 701 |
+
"loss": 1.0085,
|
| 702 |
+
"step": 99000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.0,
|
| 706 |
+
"grad_norm": 1.7343461513519287,
|
| 707 |
+
"learning_rate": 3.9e-09,
|
| 708 |
+
"loss": 0.9988,
|
| 709 |
+
"step": 100000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 1.0,
|
| 713 |
+
"step": 100000,
|
| 714 |
+
"total_flos": 1.0909051256832e+18,
|
| 715 |
+
"train_loss": 1.0107983074951172,
|
| 716 |
+
"train_runtime": 153234.8237,
|
| 717 |
+
"train_samples_per_second": 1.305,
|
| 718 |
+
"train_steps_per_second": 0.653
|
| 719 |
+
}
|
| 720 |
+
],
|
| 721 |
+
"logging_steps": 1000,
|
| 722 |
+
"max_steps": 100000,
|
| 723 |
+
"num_input_tokens_seen": 0,
|
| 724 |
+
"num_train_epochs": 9223372036854775807,
|
| 725 |
+
"save_steps": 20000,
|
| 726 |
+
"stateful_callbacks": {
|
| 727 |
+
"TrainerControl": {
|
| 728 |
+
"args": {
|
| 729 |
+
"should_epoch_stop": false,
|
| 730 |
+
"should_evaluate": false,
|
| 731 |
+
"should_log": false,
|
| 732 |
+
"should_save": true,
|
| 733 |
+
"should_training_stop": true
|
| 734 |
+
},
|
| 735 |
+
"attributes": {}
|
| 736 |
+
}
|
| 737 |
+
},
|
| 738 |
+
"total_flos": 1.0909051256832e+18,
|
| 739 |
+
"train_batch_size": 2,
|
| 740 |
+
"trial_name": null,
|
| 741 |
+
"trial_params": null
|
| 742 |
+
}
|
training_args.bin
ADDED
|
Binary file (5.5 kB). View file
|
|
|