Training in progress, step 1908
Browse files- .gitattributes +1 -0
- adapter_config.json +15 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +26 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2077 -0
- train.yaml +59 -0
- trainer_log.jsonl +391 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
adapter_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
| 4 |
+
"encoder_hidden_size": 512,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"num_attention_heads": 8,
|
| 7 |
+
"num_layers": 32,
|
| 8 |
+
"num_transformer_submodules": 1,
|
| 9 |
+
"num_virtual_tokens": 32,
|
| 10 |
+
"peft_type": "PREFIX_TUNING",
|
| 11 |
+
"prefix_projection": true,
|
| 12 |
+
"revision": null,
|
| 13 |
+
"task_type": "CAUSAL_LM",
|
| 14 |
+
"token_dim": 1024
|
| 15 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc4b060154c63206032295c4bddff47cafc616185c533a74f1890bb00274895d
|
| 3 |
+
size 8388736
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|eom_id|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|begin_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|eot_id|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|eot_id|>"
|
| 26 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c1dcab308e7cf5970ea38815e0a62887d705c5b436f869ca27a5dcdd40c36a6
|
| 3 |
+
size 17210148
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2077 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|reserved_special_token_2|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_3|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|reserved_special_token_4|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|reserved_special_token_5|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_6|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_7|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_8|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_9|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_10|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_11|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_12|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_13|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_14|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_15|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_16|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_17|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_18|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_19|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_20|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_21|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_22|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_23|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_24|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_25|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_26|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_27|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_28|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_29|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_30|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_31|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_32|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_33|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_34|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_35|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_36|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_37|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_38|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_39|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_40|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_41|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_42|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_43|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_44|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_45|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_46|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_47|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_48|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_49|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_50|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_51|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_52|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_53|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_54|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_55|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_56|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_57|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_58|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_59|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_60|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_61|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_62|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_63|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_64|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_65|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_66|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_67|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_68|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_69|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_70|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_71|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_72|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_73|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_74|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_75|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_76|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_77|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_78|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_79|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_80|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_81|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_82|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_83|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_84|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_85|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_86|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_87|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_88|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_89|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_90|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_91|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_92|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_93|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_94|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_95|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_96|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_97|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_98|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_99|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_100|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_101|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_102|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_103|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_104|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_105|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_106|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_107|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_108|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_109|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_110|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_111|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_112|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_113|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_114|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_115|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_116|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_117|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_118|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_119|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_120|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_121|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_122|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_123|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_124|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_125|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_126|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_127|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_128|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_129|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_130|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_131|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_132|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_133|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_134|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_135|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_136|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_137|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_138|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_139|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_140|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_141|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_142|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_143|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_144|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_145|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_146|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_147|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_148|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_149|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_150|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_151|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_152|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_153|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_154|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_155|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_156|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_157|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_158|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_159|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_160|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_161|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_162|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_163|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_164|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_165|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_166|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_167|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_168|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_169|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_170|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_171|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_172|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_173|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_174|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_175|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_176|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_177|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_178|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_179|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_180|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_181|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_182|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_183|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_184|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_185|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_186|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_187|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_188|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_189|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_190|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_191|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_192|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_193|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_194|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_195|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_196|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_197|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_198|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_199|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_200|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_201|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_202|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_203|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_204|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_205|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_206|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_207|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_208|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_209|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_210|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_211|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_212|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_213|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_214|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_215|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_216|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_217|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_218|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_219|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_220|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_221|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_222|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_223|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_224|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_225|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_226|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_227|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_228|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_229|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_230|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_231|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_232|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_233|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_234|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_235|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_236|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_237|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_238|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_239|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_240|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_241|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_242|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_243|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_244|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_245|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_246|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_247|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_248|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_249|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_250|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<|eom_id|>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"additional_special_tokens": [
|
| 2061 |
+
"<|eom_id|>"
|
| 2062 |
+
],
|
| 2063 |
+
"bos_token": "<|begin_of_text|>",
|
| 2064 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
| 2065 |
+
"clean_up_tokenization_spaces": true,
|
| 2066 |
+
"eos_token": "<|eot_id|>",
|
| 2067 |
+
"extra_special_tokens": {},
|
| 2068 |
+
"model_input_names": [
|
| 2069 |
+
"input_ids",
|
| 2070 |
+
"attention_mask"
|
| 2071 |
+
],
|
| 2072 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 2073 |
+
"pad_token": "<|eot_id|>",
|
| 2074 |
+
"padding_side": "right",
|
| 2075 |
+
"split_special_tokens": false,
|
| 2076 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2077 |
+
}
|
train.yaml
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
seed: 123
|
| 2 |
+
|
| 3 |
+
### model
|
| 4 |
+
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
|
| 5 |
+
trust_remote_code: true
|
| 6 |
+
flash_attn: auto
|
| 7 |
+
use_cache: false
|
| 8 |
+
|
| 9 |
+
### method
|
| 10 |
+
stage: sft
|
| 11 |
+
do_train: true
|
| 12 |
+
finetuning_type: prefix-tuning
|
| 13 |
+
task_type: CAUSAL_LM
|
| 14 |
+
num_virtual_tokens: 32
|
| 15 |
+
prefix_projection: true
|
| 16 |
+
encoder_hidden_size: 512
|
| 17 |
+
disable_gradient_checkpointing: true
|
| 18 |
+
|
| 19 |
+
### dataset
|
| 20 |
+
dataset: codealpacapy
|
| 21 |
+
template: llama3
|
| 22 |
+
cutoff_len: 2048
|
| 23 |
+
overwrite_cache: true
|
| 24 |
+
preprocessing_num_workers: 16
|
| 25 |
+
dataloader_num_workers: 4
|
| 26 |
+
packing: false
|
| 27 |
+
|
| 28 |
+
### output
|
| 29 |
+
output_dir: saves/prefix-tuning/llama-3-8b-instruct/train_codealpacapy_1755694512
|
| 30 |
+
logging_steps: 5
|
| 31 |
+
save_steps: 0.05
|
| 32 |
+
overwrite_output_dir: true
|
| 33 |
+
save_only_model: false
|
| 34 |
+
plot_loss: true
|
| 35 |
+
include_num_input_tokens_seen: true
|
| 36 |
+
push_to_hub: true
|
| 37 |
+
push_to_hub_organization: rbelanec
|
| 38 |
+
load_best_model_at_end: false
|
| 39 |
+
save_total_limit: 1
|
| 40 |
+
|
| 41 |
+
### train
|
| 42 |
+
per_device_train_batch_size: 2
|
| 43 |
+
learning_rate: 5.0e-5
|
| 44 |
+
num_train_epochs: 10.0
|
| 45 |
+
weight_decay: 1.0e-5
|
| 46 |
+
lr_scheduler_type: cosine
|
| 47 |
+
bf16: true
|
| 48 |
+
ddp_timeout: 180000000
|
| 49 |
+
resume_from_checkpoint: null
|
| 50 |
+
warmup_ratio: 0.1
|
| 51 |
+
optim: adamw_torch
|
| 52 |
+
report_to:
|
| 53 |
+
- wandb
|
| 54 |
+
|
| 55 |
+
### eval
|
| 56 |
+
per_device_eval_batch_size: 2
|
| 57 |
+
eval_strategy: steps
|
| 58 |
+
eval_steps: 0.05
|
| 59 |
+
val_size: 0.1
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,391 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 38150, "loss": 6.7986, "lr": 5.2424639580602885e-08, "epoch": 0.001310615989515072, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "2:27:04", "throughput": 1023.59, "total_tokens": 1184}
|
| 2 |
+
{"current_steps": 10, "total_steps": 38150, "loss": 6.459, "lr": 1.1795543905635651e-07, "epoch": 0.002621231979030144, "percentage": 0.03, "elapsed_time": "0:00:01", "remaining_time": "1:41:54", "throughput": 1527.05, "total_tokens": 2448}
|
| 3 |
+
{"current_steps": 15, "total_steps": 38150, "loss": 6.3342, "lr": 1.8348623853211012e-07, "epoch": 0.003931847968545216, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:29:22", "throughput": 1957.09, "total_tokens": 4128}
|
| 4 |
+
{"current_steps": 20, "total_steps": 38150, "loss": 6.3733, "lr": 2.490170380078637e-07, "epoch": 0.005242463958060288, "percentage": 0.05, "elapsed_time": "0:00:02", "remaining_time": "1:22:08", "throughput": 2191.02, "total_tokens": 5664}
|
| 5 |
+
{"current_steps": 25, "total_steps": 38150, "loss": 6.993, "lr": 3.1454783748361734e-07, "epoch": 0.00655307994757536, "percentage": 0.07, "elapsed_time": "0:00:03", "remaining_time": "1:17:02", "throughput": 2322.32, "total_tokens": 7040}
|
| 6 |
+
{"current_steps": 30, "total_steps": 38150, "loss": 6.2515, "lr": 3.8007863695937093e-07, "epoch": 0.007863695937090432, "percentage": 0.08, "elapsed_time": "0:00:03", "remaining_time": "1:13:37", "throughput": 2402.37, "total_tokens": 8352}
|
| 7 |
+
{"current_steps": 35, "total_steps": 38150, "loss": 6.3401, "lr": 4.4560943643512453e-07, "epoch": 0.009174311926605505, "percentage": 0.09, "elapsed_time": "0:00:03", "remaining_time": "1:11:08", "throughput": 2469.35, "total_tokens": 9680}
|
| 8 |
+
{"current_steps": 40, "total_steps": 38150, "loss": 6.0357, "lr": 5.111402359108782e-07, "epoch": 0.010484927916120577, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:10:11", "throughput": 2584.56, "total_tokens": 11424}
|
| 9 |
+
{"current_steps": 45, "total_steps": 38150, "loss": 6.1273, "lr": 5.766710353866317e-07, "epoch": 0.011795543905635648, "percentage": 0.12, "elapsed_time": "0:00:04", "remaining_time": "1:08:22", "throughput": 2589.26, "total_tokens": 12544}
|
| 10 |
+
{"current_steps": 50, "total_steps": 38150, "loss": 5.9301, "lr": 6.422018348623854e-07, "epoch": 0.01310615989515072, "percentage": 0.13, "elapsed_time": "0:00:05", "remaining_time": "1:07:58", "throughput": 2636.61, "total_tokens": 14112}
|
| 11 |
+
{"current_steps": 55, "total_steps": 38150, "loss": 6.1987, "lr": 7.07732634338139e-07, "epoch": 0.014416775884665793, "percentage": 0.14, "elapsed_time": "0:00:05", "remaining_time": "1:06:50", "throughput": 2630.44, "total_tokens": 15232}
|
| 12 |
+
{"current_steps": 60, "total_steps": 38150, "loss": 5.5467, "lr": 7.732634338138926e-07, "epoch": 0.015727391874180863, "percentage": 0.16, "elapsed_time": "0:00:06", "remaining_time": "1:06:27", "throughput": 2676.96, "total_tokens": 16816}
|
| 13 |
+
{"current_steps": 65, "total_steps": 38150, "loss": 5.162, "lr": 8.387942332896462e-07, "epoch": 0.01703800786369594, "percentage": 0.17, "elapsed_time": "0:00:06", "remaining_time": "1:05:31", "throughput": 2646.79, "total_tokens": 17760}
|
| 14 |
+
{"current_steps": 70, "total_steps": 38150, "loss": 4.9736, "lr": 9.043250327653998e-07, "epoch": 0.01834862385321101, "percentage": 0.18, "elapsed_time": "0:00:07", "remaining_time": "1:04:47", "throughput": 2655.34, "total_tokens": 18976}
|
| 15 |
+
{"current_steps": 75, "total_steps": 38150, "loss": 4.9793, "lr": 9.698558322411533e-07, "epoch": 0.019659239842726082, "percentage": 0.2, "elapsed_time": "0:00:07", "remaining_time": "1:04:24", "throughput": 2675.69, "total_tokens": 20368}
|
| 16 |
+
{"current_steps": 80, "total_steps": 38150, "loss": 4.6473, "lr": 1.035386631716907e-06, "epoch": 0.020969855832241154, "percentage": 0.21, "elapsed_time": "0:00:08", "remaining_time": "1:03:50", "throughput": 2665.23, "total_tokens": 21456}
|
| 17 |
+
{"current_steps": 85, "total_steps": 38150, "loss": 4.7327, "lr": 1.1009174311926608e-06, "epoch": 0.022280471821756225, "percentage": 0.22, "elapsed_time": "0:00:08", "remaining_time": "1:03:23", "throughput": 2659.75, "total_tokens": 22592}
|
| 18 |
+
{"current_steps": 90, "total_steps": 38150, "loss": 4.7761, "lr": 1.1664482306684142e-06, "epoch": 0.023591087811271297, "percentage": 0.24, "elapsed_time": "0:00:08", "remaining_time": "1:02:51", "throughput": 2660.61, "total_tokens": 23728}
|
| 19 |
+
{"current_steps": 95, "total_steps": 38150, "loss": 4.1649, "lr": 1.2319790301441677e-06, "epoch": 0.02490170380078637, "percentage": 0.25, "elapsed_time": "0:00:09", "remaining_time": "1:02:25", "throughput": 2659.17, "total_tokens": 24864}
|
| 20 |
+
{"current_steps": 100, "total_steps": 38150, "loss": 4.3159, "lr": 1.2975098296199214e-06, "epoch": 0.02621231979030144, "percentage": 0.26, "elapsed_time": "0:00:09", "remaining_time": "1:02:08", "throughput": 2681.31, "total_tokens": 26272}
|
| 21 |
+
{"current_steps": 105, "total_steps": 38150, "loss": 4.3612, "lr": 1.363040629095675e-06, "epoch": 0.027522935779816515, "percentage": 0.28, "elapsed_time": "0:00:10", "remaining_time": "1:01:44", "throughput": 2665.13, "total_tokens": 27248}
|
| 22 |
+
{"current_steps": 110, "total_steps": 38150, "loss": 3.3342, "lr": 1.4285714285714286e-06, "epoch": 0.028833551769331587, "percentage": 0.29, "elapsed_time": "0:00:10", "remaining_time": "1:01:38", "throughput": 2682.59, "total_tokens": 28688}
|
| 23 |
+
{"current_steps": 115, "total_steps": 38150, "loss": 4.3775, "lr": 1.4941022280471821e-06, "epoch": 0.03014416775884666, "percentage": 0.3, "elapsed_time": "0:00:11", "remaining_time": "1:01:20", "throughput": 2677.07, "total_tokens": 29792}
|
| 24 |
+
{"current_steps": 120, "total_steps": 38150, "loss": 3.5152, "lr": 1.559633027522936e-06, "epoch": 0.03145478374836173, "percentage": 0.31, "elapsed_time": "0:00:11", "remaining_time": "1:01:28", "throughput": 2700.12, "total_tokens": 31424}
|
| 25 |
+
{"current_steps": 125, "total_steps": 38150, "loss": 3.867, "lr": 1.6251638269986893e-06, "epoch": 0.0327653997378768, "percentage": 0.33, "elapsed_time": "0:00:12", "remaining_time": "1:01:10", "throughput": 2684.23, "total_tokens": 32384}
|
| 26 |
+
{"current_steps": 130, "total_steps": 38150, "loss": 3.8969, "lr": 1.690694626474443e-06, "epoch": 0.03407601572739188, "percentage": 0.34, "elapsed_time": "0:00:12", "remaining_time": "1:01:01", "throughput": 2700.52, "total_tokens": 33808}
|
| 27 |
+
{"current_steps": 135, "total_steps": 38150, "loss": 3.6425, "lr": 1.7562254259501965e-06, "epoch": 0.035386631716906945, "percentage": 0.35, "elapsed_time": "0:00:12", "remaining_time": "1:00:48", "throughput": 2694.49, "total_tokens": 34912}
|
| 28 |
+
{"current_steps": 140, "total_steps": 38150, "loss": 3.5186, "lr": 1.8217562254259502e-06, "epoch": 0.03669724770642202, "percentage": 0.37, "elapsed_time": "0:00:13", "remaining_time": "1:00:52", "throughput": 2718.47, "total_tokens": 36576}
|
| 29 |
+
{"current_steps": 145, "total_steps": 38150, "loss": 3.6483, "lr": 1.8872870249017041e-06, "epoch": 0.03800786369593709, "percentage": 0.38, "elapsed_time": "0:00:13", "remaining_time": "1:00:44", "throughput": 2708.85, "total_tokens": 37664}
|
| 30 |
+
{"current_steps": 150, "total_steps": 38150, "loss": 3.6386, "lr": 1.9528178243774574e-06, "epoch": 0.039318479685452164, "percentage": 0.39, "elapsed_time": "0:00:14", "remaining_time": "1:00:31", "throughput": 2707.8, "total_tokens": 38816}
|
| 31 |
+
{"current_steps": 155, "total_steps": 38150, "loss": 3.2565, "lr": 2.0183486238532113e-06, "epoch": 0.04062909567496723, "percentage": 0.41, "elapsed_time": "0:00:14", "remaining_time": "1:00:33", "throughput": 2717.24, "total_tokens": 40272}
|
| 32 |
+
{"current_steps": 160, "total_steps": 38150, "loss": 3.3967, "lr": 2.083879423328965e-06, "epoch": 0.04193971166448231, "percentage": 0.42, "elapsed_time": "0:00:15", "remaining_time": "1:00:24", "throughput": 2711.86, "total_tokens": 41392}
|
| 33 |
+
{"current_steps": 165, "total_steps": 38150, "loss": 3.648, "lr": 2.1494102228047183e-06, "epoch": 0.04325032765399738, "percentage": 0.43, "elapsed_time": "0:00:15", "remaining_time": "1:00:28", "throughput": 2738.11, "total_tokens": 43152}
|
| 34 |
+
{"current_steps": 170, "total_steps": 38150, "loss": 3.3635, "lr": 2.2149410222804718e-06, "epoch": 0.04456094364351245, "percentage": 0.45, "elapsed_time": "0:00:16", "remaining_time": "1:00:42", "throughput": 2759.39, "total_tokens": 44992}
|
| 35 |
+
{"current_steps": 175, "total_steps": 38150, "loss": 3.0703, "lr": 2.2804718217562257e-06, "epoch": 0.045871559633027525, "percentage": 0.46, "elapsed_time": "0:00:16", "remaining_time": "1:00:32", "throughput": 2759.11, "total_tokens": 46192}
|
| 36 |
+
{"current_steps": 180, "total_steps": 38150, "loss": 3.4704, "lr": 2.346002621231979e-06, "epoch": 0.047182175622542594, "percentage": 0.47, "elapsed_time": "0:00:17", "remaining_time": "1:00:22", "throughput": 2749.46, "total_tokens": 47216}
|
| 37 |
+
{"current_steps": 185, "total_steps": 38150, "loss": 2.6495, "lr": 2.4115334207077327e-06, "epoch": 0.04849279161205767, "percentage": 0.48, "elapsed_time": "0:00:17", "remaining_time": "1:00:29", "throughput": 2767.49, "total_tokens": 48944}
|
| 38 |
+
{"current_steps": 190, "total_steps": 38150, "loss": 2.7644, "lr": 2.4770642201834866e-06, "epoch": 0.04980340760157274, "percentage": 0.5, "elapsed_time": "0:00:18", "remaining_time": "1:00:21", "throughput": 2773.92, "total_tokens": 50288}
|
| 39 |
+
{"current_steps": 195, "total_steps": 38150, "loss": 2.5845, "lr": 2.54259501965924e-06, "epoch": 0.05111402359108781, "percentage": 0.51, "elapsed_time": "0:00:18", "remaining_time": "1:00:13", "throughput": 2776.72, "total_tokens": 51552}
|
| 40 |
+
{"current_steps": 200, "total_steps": 38150, "loss": 3.2747, "lr": 2.6081258191349936e-06, "epoch": 0.05242463958060288, "percentage": 0.52, "elapsed_time": "0:00:19", "remaining_time": "1:00:17", "throughput": 2797.25, "total_tokens": 53328}
|
| 41 |
+
{"current_steps": 205, "total_steps": 38150, "loss": 2.5992, "lr": 2.673656618610747e-06, "epoch": 0.053735255570117955, "percentage": 0.54, "elapsed_time": "0:00:19", "remaining_time": "1:00:12", "throughput": 2799.51, "total_tokens": 54640}
|
| 42 |
+
{"current_steps": 210, "total_steps": 38150, "loss": 2.7476, "lr": 2.739187418086501e-06, "epoch": 0.05504587155963303, "percentage": 0.55, "elapsed_time": "0:00:19", "remaining_time": "1:00:08", "throughput": 2792.19, "total_tokens": 55776}
|
| 43 |
+
{"current_steps": 215, "total_steps": 38150, "loss": 2.5949, "lr": 2.8047182175622545e-06, "epoch": 0.0563564875491481, "percentage": 0.56, "elapsed_time": "0:00:20", "remaining_time": "1:00:04", "throughput": 2800.67, "total_tokens": 57216}
|
| 44 |
+
{"current_steps": 220, "total_steps": 38150, "loss": 2.7169, "lr": 2.870249017038008e-06, "epoch": 0.057667103538663174, "percentage": 0.58, "elapsed_time": "0:00:21", "remaining_time": "1:00:27", "throughput": 2821.08, "total_tokens": 59360}
|
| 45 |
+
{"current_steps": 225, "total_steps": 38150, "loss": 2.8786, "lr": 2.935779816513762e-06, "epoch": 0.05897771952817824, "percentage": 0.59, "elapsed_time": "0:00:21", "remaining_time": "1:00:17", "throughput": 2813.91, "total_tokens": 60384}
|
| 46 |
+
{"current_steps": 230, "total_steps": 38150, "loss": 2.463, "lr": 3.0013106159895154e-06, "epoch": 0.06028833551769332, "percentage": 0.6, "elapsed_time": "0:00:21", "remaining_time": "1:00:16", "throughput": 2821.08, "total_tokens": 61888}
|
| 47 |
+
{"current_steps": 235, "total_steps": 38150, "loss": 2.2599, "lr": 3.066841415465269e-06, "epoch": 0.061598951507208385, "percentage": 0.62, "elapsed_time": "0:00:22", "remaining_time": "1:00:06", "throughput": 2809.23, "total_tokens": 62800}
|
| 48 |
+
{"current_steps": 240, "total_steps": 38150, "loss": 2.3209, "lr": 3.1323722149410228e-06, "epoch": 0.06290956749672345, "percentage": 0.63, "elapsed_time": "0:00:22", "remaining_time": "1:00:02", "throughput": 2817.26, "total_tokens": 64256}
|
| 49 |
+
{"current_steps": 245, "total_steps": 38150, "loss": 2.4618, "lr": 3.1979030144167763e-06, "epoch": 0.06422018348623854, "percentage": 0.64, "elapsed_time": "0:00:23", "remaining_time": "1:00:04", "throughput": 2820.84, "total_tokens": 65728}
|
| 50 |
+
{"current_steps": 250, "total_steps": 38150, "loss": 2.6133, "lr": 3.2634338138925293e-06, "epoch": 0.0655307994757536, "percentage": 0.66, "elapsed_time": "0:00:23", "remaining_time": "0:59:58", "throughput": 2818.61, "total_tokens": 66912}
|
| 51 |
+
{"current_steps": 255, "total_steps": 38150, "loss": 2.2286, "lr": 3.328964613368283e-06, "epoch": 0.06684141546526867, "percentage": 0.67, "elapsed_time": "0:00:24", "remaining_time": "0:59:50", "throughput": 2810.45, "total_tokens": 67904}
|
| 52 |
+
{"current_steps": 260, "total_steps": 38150, "loss": 2.3407, "lr": 3.394495412844037e-06, "epoch": 0.06815203145478375, "percentage": 0.68, "elapsed_time": "0:00:24", "remaining_time": "0:59:47", "throughput": 2821.24, "total_tokens": 69456}
|
| 53 |
+
{"current_steps": 265, "total_steps": 38150, "loss": 2.8786, "lr": 3.4600262123197906e-06, "epoch": 0.06946264744429882, "percentage": 0.69, "elapsed_time": "0:00:25", "remaining_time": "0:59:45", "throughput": 2823.89, "total_tokens": 70832}
|
| 54 |
+
{"current_steps": 270, "total_steps": 38150, "loss": 2.7456, "lr": 3.5255570117955437e-06, "epoch": 0.07077326343381389, "percentage": 0.71, "elapsed_time": "0:00:25", "remaining_time": "0:59:46", "throughput": 2833.83, "total_tokens": 72448}
|
| 55 |
+
{"current_steps": 275, "total_steps": 38150, "loss": 2.5068, "lr": 3.591087811271298e-06, "epoch": 0.07208387942332896, "percentage": 0.72, "elapsed_time": "0:00:26", "remaining_time": "0:59:46", "throughput": 2838.77, "total_tokens": 73920}
|
| 56 |
+
{"current_steps": 280, "total_steps": 38150, "loss": 2.5438, "lr": 3.6566186107470515e-06, "epoch": 0.07339449541284404, "percentage": 0.73, "elapsed_time": "0:00:26", "remaining_time": "0:59:47", "throughput": 2845.44, "total_tokens": 75472}
|
| 57 |
+
{"current_steps": 285, "total_steps": 38150, "loss": 2.4037, "lr": 3.7221494102228046e-06, "epoch": 0.07470511140235911, "percentage": 0.75, "elapsed_time": "0:00:26", "remaining_time": "0:59:46", "throughput": 2851.26, "total_tokens": 76976}
|
| 58 |
+
{"current_steps": 290, "total_steps": 38150, "loss": 2.3192, "lr": 3.787680209698558e-06, "epoch": 0.07601572739187418, "percentage": 0.76, "elapsed_time": "0:00:27", "remaining_time": "0:59:42", "throughput": 2860.21, "total_tokens": 78496}
|
| 59 |
+
{"current_steps": 295, "total_steps": 38150, "loss": 1.9689, "lr": 3.853211009174312e-06, "epoch": 0.07732634338138926, "percentage": 0.77, "elapsed_time": "0:00:27", "remaining_time": "0:59:42", "throughput": 2866.48, "total_tokens": 80032}
|
| 60 |
+
{"current_steps": 300, "total_steps": 38150, "loss": 1.6909, "lr": 3.918741808650066e-06, "epoch": 0.07863695937090433, "percentage": 0.79, "elapsed_time": "0:00:28", "remaining_time": "0:59:35", "throughput": 2862.27, "total_tokens": 81104}
|
| 61 |
+
{"current_steps": 305, "total_steps": 38150, "loss": 1.7138, "lr": 3.984272608125819e-06, "epoch": 0.0799475753604194, "percentage": 0.8, "elapsed_time": "0:00:28", "remaining_time": "0:59:28", "throughput": 2858.98, "total_tokens": 82224}
|
| 62 |
+
{"current_steps": 310, "total_steps": 38150, "loss": 1.7154, "lr": 4.049803407601573e-06, "epoch": 0.08125819134993446, "percentage": 0.81, "elapsed_time": "0:00:29", "remaining_time": "0:59:38", "throughput": 2870.94, "total_tokens": 84160}
|
| 63 |
+
{"current_steps": 315, "total_steps": 38150, "loss": 2.0075, "lr": 4.115334207077327e-06, "epoch": 0.08256880733944955, "percentage": 0.83, "elapsed_time": "0:00:29", "remaining_time": "0:59:34", "throughput": 2872.92, "total_tokens": 85488}
|
| 64 |
+
{"current_steps": 320, "total_steps": 38150, "loss": 2.203, "lr": 4.18086500655308e-06, "epoch": 0.08387942332896461, "percentage": 0.84, "elapsed_time": "0:00:30", "remaining_time": "0:59:30", "throughput": 2872.97, "total_tokens": 86768}
|
| 65 |
+
{"current_steps": 325, "total_steps": 38150, "loss": 1.6721, "lr": 4.246395806028834e-06, "epoch": 0.08519003931847968, "percentage": 0.85, "elapsed_time": "0:00:30", "remaining_time": "0:59:25", "throughput": 2869.67, "total_tokens": 87920}
|
| 66 |
+
{"current_steps": 330, "total_steps": 38150, "loss": 2.5713, "lr": 4.311926605504588e-06, "epoch": 0.08650065530799476, "percentage": 0.87, "elapsed_time": "0:00:31", "remaining_time": "0:59:24", "throughput": 2866.29, "total_tokens": 89136}
|
| 67 |
+
{"current_steps": 335, "total_steps": 38150, "loss": 1.9157, "lr": 4.377457404980341e-06, "epoch": 0.08781127129750983, "percentage": 0.88, "elapsed_time": "0:00:31", "remaining_time": "0:59:19", "throughput": 2868.54, "total_tokens": 90464}
|
| 68 |
+
{"current_steps": 340, "total_steps": 38150, "loss": 1.8514, "lr": 4.442988204456095e-06, "epoch": 0.0891218872870249, "percentage": 0.89, "elapsed_time": "0:00:31", "remaining_time": "0:59:17", "throughput": 2875.73, "total_tokens": 91984}
|
| 69 |
+
{"current_steps": 345, "total_steps": 38150, "loss": 1.3482, "lr": 4.508519003931848e-06, "epoch": 0.09043250327653997, "percentage": 0.9, "elapsed_time": "0:00:32", "remaining_time": "0:59:10", "throughput": 2870.76, "total_tokens": 93024}
|
| 70 |
+
{"current_steps": 350, "total_steps": 38150, "loss": 1.499, "lr": 4.574049803407602e-06, "epoch": 0.09174311926605505, "percentage": 0.92, "elapsed_time": "0:00:32", "remaining_time": "0:59:11", "throughput": 2872.91, "total_tokens": 94464}
|
| 71 |
+
{"current_steps": 355, "total_steps": 38150, "loss": 1.7817, "lr": 4.639580602883356e-06, "epoch": 0.09305373525557012, "percentage": 0.93, "elapsed_time": "0:00:33", "remaining_time": "0:59:07", "throughput": 2871.31, "total_tokens": 95664}
|
| 72 |
+
{"current_steps": 360, "total_steps": 38150, "loss": 1.4435, "lr": 4.705111402359109e-06, "epoch": 0.09436435124508519, "percentage": 0.94, "elapsed_time": "0:00:33", "remaining_time": "0:59:02", "throughput": 2862.42, "total_tokens": 96608}
|
| 73 |
+
{"current_steps": 365, "total_steps": 38150, "loss": 1.3371, "lr": 4.7706422018348626e-06, "epoch": 0.09567496723460026, "percentage": 0.96, "elapsed_time": "0:00:34", "remaining_time": "0:58:59", "throughput": 2865.16, "total_tokens": 97968}
|
| 74 |
+
{"current_steps": 370, "total_steps": 38150, "loss": 1.185, "lr": 4.8361730013106165e-06, "epoch": 0.09698558322411534, "percentage": 0.97, "elapsed_time": "0:00:34", "remaining_time": "0:58:54", "throughput": 2864.09, "total_tokens": 99152}
|
| 75 |
+
{"current_steps": 375, "total_steps": 38150, "loss": 1.2584, "lr": 4.9017038007863695e-06, "epoch": 0.0982961992136304, "percentage": 0.98, "elapsed_time": "0:00:35", "remaining_time": "0:58:52", "throughput": 2868.41, "total_tokens": 100592}
|
| 76 |
+
{"current_steps": 380, "total_steps": 38150, "loss": 1.0506, "lr": 4.9672346002621235e-06, "epoch": 0.09960681520314547, "percentage": 1.0, "elapsed_time": "0:00:35", "remaining_time": "0:58:49", "throughput": 2868.66, "total_tokens": 101856}
|
| 77 |
+
{"current_steps": 385, "total_steps": 38150, "loss": 1.079, "lr": 5.032765399737877e-06, "epoch": 0.10091743119266056, "percentage": 1.01, "elapsed_time": "0:00:35", "remaining_time": "0:58:45", "throughput": 2866.41, "total_tokens": 103024}
|
| 78 |
+
{"current_steps": 390, "total_steps": 38150, "loss": 0.7351, "lr": 5.0982961992136304e-06, "epoch": 0.10222804718217562, "percentage": 1.02, "elapsed_time": "0:00:36", "remaining_time": "0:58:46", "throughput": 2869.46, "total_tokens": 104512}
|
| 79 |
+
{"current_steps": 395, "total_steps": 38150, "loss": 0.7511, "lr": 5.163826998689384e-06, "epoch": 0.10353866317169069, "percentage": 1.04, "elapsed_time": "0:00:36", "remaining_time": "0:58:44", "throughput": 2872.24, "total_tokens": 105904}
|
| 80 |
+
{"current_steps": 400, "total_steps": 38150, "loss": 0.8194, "lr": 5.229357798165138e-06, "epoch": 0.10484927916120576, "percentage": 1.05, "elapsed_time": "0:00:37", "remaining_time": "0:58:40", "throughput": 2870.45, "total_tokens": 107088}
|
| 81 |
+
{"current_steps": 405, "total_steps": 38150, "loss": 1.0875, "lr": 5.294888597640891e-06, "epoch": 0.10615989515072084, "percentage": 1.06, "elapsed_time": "0:00:37", "remaining_time": "0:58:37", "throughput": 2867.92, "total_tokens": 108240}
|
| 82 |
+
{"current_steps": 410, "total_steps": 38150, "loss": 0.818, "lr": 5.360419397116645e-06, "epoch": 0.10747051114023591, "percentage": 1.07, "elapsed_time": "0:00:38", "remaining_time": "0:58:34", "throughput": 2866.87, "total_tokens": 109472}
|
| 83 |
+
{"current_steps": 415, "total_steps": 38150, "loss": 0.8605, "lr": 5.425950196592398e-06, "epoch": 0.10878112712975098, "percentage": 1.09, "elapsed_time": "0:00:38", "remaining_time": "0:58:37", "throughput": 2870.78, "total_tokens": 111056}
|
| 84 |
+
{"current_steps": 420, "total_steps": 38150, "loss": 0.6954, "lr": 5.491480996068152e-06, "epoch": 0.11009174311926606, "percentage": 1.1, "elapsed_time": "0:00:39", "remaining_time": "0:58:36", "throughput": 2872.77, "total_tokens": 112448}
|
| 85 |
+
{"current_steps": 425, "total_steps": 38150, "loss": 0.8871, "lr": 5.557011795543906e-06, "epoch": 0.11140235910878113, "percentage": 1.11, "elapsed_time": "0:00:39", "remaining_time": "0:58:33", "throughput": 2871.53, "total_tokens": 113648}
|
| 86 |
+
{"current_steps": 430, "total_steps": 38150, "loss": 1.2326, "lr": 5.622542595019659e-06, "epoch": 0.1127129750982962, "percentage": 1.13, "elapsed_time": "0:00:40", "remaining_time": "0:58:32", "throughput": 2868.82, "total_tokens": 114864}
|
| 87 |
+
{"current_steps": 435, "total_steps": 38150, "loss": 0.8113, "lr": 5.688073394495413e-06, "epoch": 0.11402359108781127, "percentage": 1.14, "elapsed_time": "0:00:40", "remaining_time": "0:58:28", "throughput": 2865.63, "total_tokens": 115968}
|
| 88 |
+
{"current_steps": 440, "total_steps": 38150, "loss": 0.8079, "lr": 5.753604193971167e-06, "epoch": 0.11533420707732635, "percentage": 1.15, "elapsed_time": "0:00:40", "remaining_time": "0:58:31", "throughput": 2872.03, "total_tokens": 117680}
|
| 89 |
+
{"current_steps": 445, "total_steps": 38150, "loss": 0.7636, "lr": 5.81913499344692e-06, "epoch": 0.11664482306684142, "percentage": 1.17, "elapsed_time": "0:00:41", "remaining_time": "0:58:28", "throughput": 2867.45, "total_tokens": 118720}
|
| 90 |
+
{"current_steps": 450, "total_steps": 38150, "loss": 0.5719, "lr": 5.884665792922674e-06, "epoch": 0.11795543905635648, "percentage": 1.18, "elapsed_time": "0:00:41", "remaining_time": "0:58:28", "throughput": 2872.6, "total_tokens": 120288}
|
| 91 |
+
{"current_steps": 455, "total_steps": 38150, "loss": 0.701, "lr": 5.950196592398428e-06, "epoch": 0.11926605504587157, "percentage": 1.19, "elapsed_time": "0:00:42", "remaining_time": "0:58:29", "throughput": 2873.64, "total_tokens": 121728}
|
| 92 |
+
{"current_steps": 460, "total_steps": 38150, "loss": 0.6586, "lr": 6.015727391874181e-06, "epoch": 0.12057667103538663, "percentage": 1.21, "elapsed_time": "0:00:42", "remaining_time": "0:58:26", "throughput": 2871.19, "total_tokens": 122880}
|
| 93 |
+
{"current_steps": 465, "total_steps": 38150, "loss": 0.7658, "lr": 6.081258191349935e-06, "epoch": 0.1218872870249017, "percentage": 1.22, "elapsed_time": "0:00:43", "remaining_time": "0:58:23", "throughput": 2871.33, "total_tokens": 124112}
|
| 94 |
+
{"current_steps": 470, "total_steps": 38150, "loss": 0.954, "lr": 6.146788990825689e-06, "epoch": 0.12319790301441677, "percentage": 1.23, "elapsed_time": "0:00:43", "remaining_time": "0:58:23", "throughput": 2873.75, "total_tokens": 125568}
|
| 95 |
+
{"current_steps": 475, "total_steps": 38150, "loss": 0.6385, "lr": 6.212319790301442e-06, "epoch": 0.12450851900393185, "percentage": 1.25, "elapsed_time": "0:00:44", "remaining_time": "0:58:25", "throughput": 2878.34, "total_tokens": 127216}
|
| 96 |
+
{"current_steps": 480, "total_steps": 38150, "loss": 0.9186, "lr": 6.277850589777196e-06, "epoch": 0.1258191349934469, "percentage": 1.26, "elapsed_time": "0:00:44", "remaining_time": "0:58:25", "throughput": 2877.78, "total_tokens": 128560}
|
| 97 |
+
{"current_steps": 485, "total_steps": 38150, "loss": 0.6429, "lr": 6.343381389252949e-06, "epoch": 0.127129750982962, "percentage": 1.27, "elapsed_time": "0:00:45", "remaining_time": "0:58:25", "throughput": 2878.69, "total_tokens": 129952}
|
| 98 |
+
{"current_steps": 490, "total_steps": 38150, "loss": 0.8343, "lr": 6.408912188728703e-06, "epoch": 0.12844036697247707, "percentage": 1.28, "elapsed_time": "0:00:45", "remaining_time": "0:58:22", "throughput": 2874.05, "total_tokens": 130976}
|
| 99 |
+
{"current_steps": 495, "total_steps": 38150, "loss": 0.4068, "lr": 6.474442988204456e-06, "epoch": 0.12975098296199214, "percentage": 1.3, "elapsed_time": "0:00:46", "remaining_time": "0:58:19", "throughput": 2875.07, "total_tokens": 132256}
|
| 100 |
+
{"current_steps": 500, "total_steps": 38150, "loss": 0.8403, "lr": 6.539973787680211e-06, "epoch": 0.1310615989515072, "percentage": 1.31, "elapsed_time": "0:00:46", "remaining_time": "0:58:25", "throughput": 2884.17, "total_tokens": 134256}
|
| 101 |
+
{"current_steps": 505, "total_steps": 38150, "loss": 0.5071, "lr": 6.605504587155964e-06, "epoch": 0.13237221494102228, "percentage": 1.32, "elapsed_time": "0:00:46", "remaining_time": "0:58:23", "throughput": 2884.99, "total_tokens": 135584}
|
| 102 |
+
{"current_steps": 510, "total_steps": 38150, "loss": 0.6415, "lr": 6.671035386631718e-06, "epoch": 0.13368283093053734, "percentage": 1.34, "elapsed_time": "0:00:47", "remaining_time": "0:58:19", "throughput": 2880.47, "total_tokens": 136576}
|
| 103 |
+
{"current_steps": 515, "total_steps": 38150, "loss": 0.5982, "lr": 6.736566186107471e-06, "epoch": 0.1349934469200524, "percentage": 1.35, "elapsed_time": "0:00:47", "remaining_time": "0:58:17", "throughput": 2882.5, "total_tokens": 137952}
|
| 104 |
+
{"current_steps": 520, "total_steps": 38150, "loss": 0.5363, "lr": 6.8020969855832246e-06, "epoch": 0.1363040629095675, "percentage": 1.36, "elapsed_time": "0:00:48", "remaining_time": "0:58:13", "throughput": 2879.42, "total_tokens": 139024}
|
| 105 |
+
{"current_steps": 525, "total_steps": 38150, "loss": 0.5653, "lr": 6.867627785058978e-06, "epoch": 0.13761467889908258, "percentage": 1.38, "elapsed_time": "0:00:48", "remaining_time": "0:58:14", "throughput": 2880.36, "total_tokens": 140464}
|
| 106 |
+
{"current_steps": 530, "total_steps": 38150, "loss": 0.5365, "lr": 6.933158584534731e-06, "epoch": 0.13892529488859764, "percentage": 1.39, "elapsed_time": "0:00:49", "remaining_time": "0:58:14", "throughput": 2880.73, "total_tokens": 141824}
|
| 107 |
+
{"current_steps": 535, "total_steps": 38150, "loss": 0.5991, "lr": 6.9986893840104855e-06, "epoch": 0.1402359108781127, "percentage": 1.4, "elapsed_time": "0:00:49", "remaining_time": "0:58:11", "throughput": 2877.13, "total_tokens": 142864}
|
| 108 |
+
{"current_steps": 540, "total_steps": 38150, "loss": 0.8474, "lr": 7.064220183486239e-06, "epoch": 0.14154652686762778, "percentage": 1.42, "elapsed_time": "0:00:50", "remaining_time": "0:58:07", "throughput": 2872.51, "total_tokens": 143856}
|
| 109 |
+
{"current_steps": 545, "total_steps": 38150, "loss": 0.5345, "lr": 7.1297509829619924e-06, "epoch": 0.14285714285714285, "percentage": 1.43, "elapsed_time": "0:00:50", "remaining_time": "0:58:08", "throughput": 2872.96, "total_tokens": 145248}
|
| 110 |
+
{"current_steps": 550, "total_steps": 38150, "loss": 0.5313, "lr": 7.195281782437746e-06, "epoch": 0.14416775884665792, "percentage": 1.44, "elapsed_time": "0:00:51", "remaining_time": "0:58:08", "throughput": 2878.61, "total_tokens": 146912}
|
| 111 |
+
{"current_steps": 555, "total_steps": 38150, "loss": 0.5775, "lr": 7.260812581913499e-06, "epoch": 0.145478374836173, "percentage": 1.45, "elapsed_time": "0:00:51", "remaining_time": "0:58:08", "throughput": 2878.48, "total_tokens": 148224}
|
| 112 |
+
{"current_steps": 560, "total_steps": 38150, "loss": 0.5419, "lr": 7.326343381389253e-06, "epoch": 0.14678899082568808, "percentage": 1.47, "elapsed_time": "0:00:51", "remaining_time": "0:58:05", "throughput": 2880.17, "total_tokens": 149568}
|
| 113 |
+
{"current_steps": 565, "total_steps": 38150, "loss": 0.6886, "lr": 7.391874180865006e-06, "epoch": 0.14809960681520315, "percentage": 1.48, "elapsed_time": "0:00:52", "remaining_time": "0:58:05", "throughput": 2880.62, "total_tokens": 150912}
|
| 114 |
+
{"current_steps": 570, "total_steps": 38150, "loss": 0.6381, "lr": 7.457404980340761e-06, "epoch": 0.14941022280471822, "percentage": 1.49, "elapsed_time": "0:00:52", "remaining_time": "0:58:04", "throughput": 2882.75, "total_tokens": 152352}
|
| 115 |
+
{"current_steps": 575, "total_steps": 38150, "loss": 0.4535, "lr": 7.522935779816514e-06, "epoch": 0.15072083879423329, "percentage": 1.51, "elapsed_time": "0:00:53", "remaining_time": "0:58:03", "throughput": 2883.91, "total_tokens": 153728}
|
| 116 |
+
{"current_steps": 580, "total_steps": 38150, "loss": 1.0023, "lr": 7.588466579292268e-06, "epoch": 0.15203145478374835, "percentage": 1.52, "elapsed_time": "0:00:53", "remaining_time": "0:58:03", "throughput": 2885.55, "total_tokens": 155200}
|
| 117 |
+
{"current_steps": 585, "total_steps": 38150, "loss": 0.6087, "lr": 7.653997378768021e-06, "epoch": 0.15334207077326342, "percentage": 1.53, "elapsed_time": "0:00:54", "remaining_time": "0:58:01", "throughput": 2882.93, "total_tokens": 156288}
|
| 118 |
+
{"current_steps": 590, "total_steps": 38150, "loss": 0.6053, "lr": 7.719528178243775e-06, "epoch": 0.15465268676277852, "percentage": 1.55, "elapsed_time": "0:00:54", "remaining_time": "0:58:01", "throughput": 2882.94, "total_tokens": 157664}
|
| 119 |
+
{"current_steps": 595, "total_steps": 38150, "loss": 0.3845, "lr": 7.785058977719529e-06, "epoch": 0.1559633027522936, "percentage": 1.56, "elapsed_time": "0:00:55", "remaining_time": "0:57:58", "throughput": 2881.87, "total_tokens": 158832}
|
| 120 |
+
{"current_steps": 600, "total_steps": 38150, "loss": 0.5163, "lr": 7.850589777195281e-06, "epoch": 0.15727391874180865, "percentage": 1.57, "elapsed_time": "0:00:55", "remaining_time": "0:57:56", "throughput": 2880.14, "total_tokens": 159984}
|
| 121 |
+
{"current_steps": 605, "total_steps": 38150, "loss": 0.5095, "lr": 7.916120576671037e-06, "epoch": 0.15858453473132372, "percentage": 1.59, "elapsed_time": "0:00:56", "remaining_time": "0:57:55", "throughput": 2879.06, "total_tokens": 161248}
|
| 122 |
+
{"current_steps": 610, "total_steps": 38150, "loss": 0.6285, "lr": 7.981651376146789e-06, "epoch": 0.1598951507208388, "percentage": 1.6, "elapsed_time": "0:00:56", "remaining_time": "0:57:53", "throughput": 2880.71, "total_tokens": 162608}
|
| 123 |
+
{"current_steps": 615, "total_steps": 38150, "loss": 0.5152, "lr": 8.047182175622543e-06, "epoch": 0.16120576671035386, "percentage": 1.61, "elapsed_time": "0:00:56", "remaining_time": "0:57:50", "throughput": 2878.36, "total_tokens": 163696}
|
| 124 |
+
{"current_steps": 620, "total_steps": 38150, "loss": 0.6275, "lr": 8.112712975098297e-06, "epoch": 0.16251638269986893, "percentage": 1.63, "elapsed_time": "0:00:57", "remaining_time": "0:57:51", "throughput": 2878.13, "total_tokens": 165056}
|
| 125 |
+
{"current_steps": 625, "total_steps": 38150, "loss": 0.4361, "lr": 8.17824377457405e-06, "epoch": 0.16382699868938402, "percentage": 1.64, "elapsed_time": "0:00:57", "remaining_time": "0:57:54", "throughput": 2883.14, "total_tokens": 166848}
|
| 126 |
+
{"current_steps": 630, "total_steps": 38150, "loss": 0.6254, "lr": 8.243774574049803e-06, "epoch": 0.1651376146788991, "percentage": 1.65, "elapsed_time": "0:00:58", "remaining_time": "0:57:54", "throughput": 2883.48, "total_tokens": 168240}
|
| 127 |
+
{"current_steps": 635, "total_steps": 38150, "loss": 0.7787, "lr": 8.309305373525557e-06, "epoch": 0.16644823066841416, "percentage": 1.66, "elapsed_time": "0:00:58", "remaining_time": "0:57:56", "throughput": 2885.93, "total_tokens": 169840}
|
| 128 |
+
{"current_steps": 640, "total_steps": 38150, "loss": 0.6294, "lr": 8.374836173001311e-06, "epoch": 0.16775884665792923, "percentage": 1.68, "elapsed_time": "0:00:59", "remaining_time": "0:57:55", "throughput": 2886.64, "total_tokens": 171152}
|
| 129 |
+
{"current_steps": 645, "total_steps": 38150, "loss": 0.7506, "lr": 8.440366972477065e-06, "epoch": 0.1690694626474443, "percentage": 1.69, "elapsed_time": "0:00:59", "remaining_time": "0:57:51", "throughput": 2883.04, "total_tokens": 172144}
|
| 130 |
+
{"current_steps": 650, "total_steps": 38150, "loss": 0.5968, "lr": 8.505897771952819e-06, "epoch": 0.17038007863695936, "percentage": 1.7, "elapsed_time": "0:01:00", "remaining_time": "0:57:51", "throughput": 2882.42, "total_tokens": 173440}
|
| 131 |
+
{"current_steps": 655, "total_steps": 38150, "loss": 0.6292, "lr": 8.571428571428573e-06, "epoch": 0.17169069462647443, "percentage": 1.72, "elapsed_time": "0:01:00", "remaining_time": "0:57:52", "throughput": 2883.37, "total_tokens": 174928}
|
| 132 |
+
{"current_steps": 660, "total_steps": 38150, "loss": 0.5797, "lr": 8.636959370904325e-06, "epoch": 0.17300131061598953, "percentage": 1.73, "elapsed_time": "0:01:01", "remaining_time": "0:57:53", "throughput": 2889.1, "total_tokens": 176672}
|
| 133 |
+
{"current_steps": 665, "total_steps": 38150, "loss": 0.883, "lr": 8.702490170380079e-06, "epoch": 0.1743119266055046, "percentage": 1.74, "elapsed_time": "0:01:01", "remaining_time": "0:57:52", "throughput": 2884.61, "total_tokens": 177712}
|
| 134 |
+
{"current_steps": 670, "total_steps": 38150, "loss": 0.773, "lr": 8.768020969855833e-06, "epoch": 0.17562254259501967, "percentage": 1.76, "elapsed_time": "0:01:02", "remaining_time": "0:57:54", "throughput": 2885.71, "total_tokens": 179232}
|
| 135 |
+
{"current_steps": 675, "total_steps": 38150, "loss": 0.516, "lr": 8.833551769331587e-06, "epoch": 0.17693315858453473, "percentage": 1.77, "elapsed_time": "0:01:02", "remaining_time": "0:57:55", "throughput": 2886.0, "total_tokens": 180688}
|
| 136 |
+
{"current_steps": 680, "total_steps": 38150, "loss": 0.6025, "lr": 8.89908256880734e-06, "epoch": 0.1782437745740498, "percentage": 1.78, "elapsed_time": "0:01:03", "remaining_time": "0:57:53", "throughput": 2884.65, "total_tokens": 181824}
|
| 137 |
+
{"current_steps": 685, "total_steps": 38150, "loss": 0.7081, "lr": 8.964613368283094e-06, "epoch": 0.17955439056356487, "percentage": 1.8, "elapsed_time": "0:01:03", "remaining_time": "0:57:50", "throughput": 2880.39, "total_tokens": 182768}
|
| 138 |
+
{"current_steps": 690, "total_steps": 38150, "loss": 0.7526, "lr": 9.030144167758847e-06, "epoch": 0.18086500655307994, "percentage": 1.81, "elapsed_time": "0:01:03", "remaining_time": "0:57:49", "throughput": 2882.85, "total_tokens": 184240}
|
| 139 |
+
{"current_steps": 695, "total_steps": 38150, "loss": 0.5776, "lr": 9.0956749672346e-06, "epoch": 0.182175622542595, "percentage": 1.82, "elapsed_time": "0:01:04", "remaining_time": "0:57:47", "throughput": 2878.43, "total_tokens": 185200}
|
| 140 |
+
{"current_steps": 700, "total_steps": 38150, "loss": 0.4367, "lr": 9.161205766710354e-06, "epoch": 0.1834862385321101, "percentage": 1.83, "elapsed_time": "0:01:04", "remaining_time": "0:57:46", "throughput": 2877.67, "total_tokens": 186464}
|
| 141 |
+
{"current_steps": 705, "total_steps": 38150, "loss": 0.4508, "lr": 9.226736566186107e-06, "epoch": 0.18479685452162517, "percentage": 1.85, "elapsed_time": "0:01:05", "remaining_time": "0:57:44", "throughput": 2878.09, "total_tokens": 187728}
|
| 142 |
+
{"current_steps": 710, "total_steps": 38150, "loss": 0.5393, "lr": 9.29226736566186e-06, "epoch": 0.18610747051114024, "percentage": 1.86, "elapsed_time": "0:01:05", "remaining_time": "0:57:43", "throughput": 2876.78, "total_tokens": 188944}
|
| 143 |
+
{"current_steps": 715, "total_steps": 38150, "loss": 0.641, "lr": 9.357798165137616e-06, "epoch": 0.1874180865006553, "percentage": 1.87, "elapsed_time": "0:01:06", "remaining_time": "0:57:41", "throughput": 2877.93, "total_tokens": 190288}
|
| 144 |
+
{"current_steps": 720, "total_steps": 38150, "loss": 0.398, "lr": 9.423328964613368e-06, "epoch": 0.18872870249017037, "percentage": 1.89, "elapsed_time": "0:01:06", "remaining_time": "0:57:38", "throughput": 2874.66, "total_tokens": 191264}
|
| 145 |
+
{"current_steps": 725, "total_steps": 38150, "loss": 0.6598, "lr": 9.488859764089122e-06, "epoch": 0.19003931847968544, "percentage": 1.9, "elapsed_time": "0:01:06", "remaining_time": "0:57:36", "throughput": 2872.44, "total_tokens": 192336}
|
| 146 |
+
{"current_steps": 730, "total_steps": 38150, "loss": 0.5838, "lr": 9.554390563564876e-06, "epoch": 0.1913499344692005, "percentage": 1.91, "elapsed_time": "0:01:07", "remaining_time": "0:57:34", "throughput": 2872.72, "total_tokens": 193584}
|
| 147 |
+
{"current_steps": 735, "total_steps": 38150, "loss": 0.5564, "lr": 9.619921363040628e-06, "epoch": 0.1926605504587156, "percentage": 1.93, "elapsed_time": "0:01:07", "remaining_time": "0:57:32", "throughput": 2872.0, "total_tokens": 194800}
|
| 148 |
+
{"current_steps": 740, "total_steps": 38150, "loss": 0.5241, "lr": 9.685452162516382e-06, "epoch": 0.19397116644823068, "percentage": 1.94, "elapsed_time": "0:01:08", "remaining_time": "0:57:32", "throughput": 2872.98, "total_tokens": 196192}
|
| 149 |
+
{"current_steps": 745, "total_steps": 38150, "loss": 0.5093, "lr": 9.750982961992136e-06, "epoch": 0.19528178243774574, "percentage": 1.95, "elapsed_time": "0:01:08", "remaining_time": "0:57:30", "throughput": 2869.86, "total_tokens": 197200}
|
| 150 |
+
{"current_steps": 750, "total_steps": 38150, "loss": 0.7171, "lr": 9.81651376146789e-06, "epoch": 0.1965923984272608, "percentage": 1.97, "elapsed_time": "0:01:09", "remaining_time": "0:57:28", "throughput": 2868.76, "total_tokens": 198384}
|
| 151 |
+
{"current_steps": 755, "total_steps": 38150, "loss": 0.6555, "lr": 9.882044560943644e-06, "epoch": 0.19790301441677588, "percentage": 1.98, "elapsed_time": "0:01:09", "remaining_time": "0:57:27", "throughput": 2869.18, "total_tokens": 199680}
|
| 152 |
+
{"current_steps": 760, "total_steps": 38150, "loss": 0.527, "lr": 9.947575360419398e-06, "epoch": 0.19921363040629095, "percentage": 1.99, "elapsed_time": "0:01:10", "remaining_time": "0:57:25", "throughput": 2869.32, "total_tokens": 200960}
|
| 153 |
+
{"current_steps": 765, "total_steps": 38150, "loss": 0.6909, "lr": 1.0013106159895152e-05, "epoch": 0.20052424639580602, "percentage": 2.01, "elapsed_time": "0:01:10", "remaining_time": "0:57:29", "throughput": 2877.86, "total_tokens": 203120}
|
| 154 |
+
{"current_steps": 770, "total_steps": 38150, "loss": 0.798, "lr": 1.0078636959370904e-05, "epoch": 0.2018348623853211, "percentage": 2.02, "elapsed_time": "0:01:11", "remaining_time": "0:57:31", "throughput": 2881.54, "total_tokens": 204848}
|
| 155 |
+
{"current_steps": 775, "total_steps": 38150, "loss": 0.6908, "lr": 1.0144167758846658e-05, "epoch": 0.20314547837483618, "percentage": 2.03, "elapsed_time": "0:01:11", "remaining_time": "0:57:29", "throughput": 2881.19, "total_tokens": 206080}
|
| 156 |
+
{"current_steps": 780, "total_steps": 38150, "loss": 0.6829, "lr": 1.0209698558322412e-05, "epoch": 0.20445609436435125, "percentage": 2.04, "elapsed_time": "0:01:12", "remaining_time": "0:57:30", "throughput": 2886.78, "total_tokens": 207920}
|
| 157 |
+
{"current_steps": 785, "total_steps": 38150, "loss": 0.6658, "lr": 1.0275229357798166e-05, "epoch": 0.20576671035386632, "percentage": 2.06, "elapsed_time": "0:01:12", "remaining_time": "0:57:28", "throughput": 2885.08, "total_tokens": 209040}
|
| 158 |
+
{"current_steps": 790, "total_steps": 38150, "loss": 0.5424, "lr": 1.034076015727392e-05, "epoch": 0.20707732634338138, "percentage": 2.07, "elapsed_time": "0:01:12", "remaining_time": "0:57:27", "throughput": 2886.11, "total_tokens": 210384}
|
| 159 |
+
{"current_steps": 795, "total_steps": 38150, "loss": 0.6535, "lr": 1.0406290956749674e-05, "epoch": 0.20838794233289645, "percentage": 2.08, "elapsed_time": "0:01:13", "remaining_time": "0:57:30", "throughput": 2887.46, "total_tokens": 212032}
|
| 160 |
+
{"current_steps": 800, "total_steps": 38150, "loss": 0.6656, "lr": 1.0471821756225426e-05, "epoch": 0.20969855832241152, "percentage": 2.1, "elapsed_time": "0:01:13", "remaining_time": "0:57:27", "throughput": 2882.88, "total_tokens": 212896}
|
| 161 |
+
{"current_steps": 805, "total_steps": 38150, "loss": 0.8836, "lr": 1.053735255570118e-05, "epoch": 0.21100917431192662, "percentage": 2.11, "elapsed_time": "0:01:14", "remaining_time": "0:57:28", "throughput": 2883.7, "total_tokens": 214352}
|
| 162 |
+
{"current_steps": 810, "total_steps": 38150, "loss": 0.7186, "lr": 1.0602883355176934e-05, "epoch": 0.21231979030144169, "percentage": 2.12, "elapsed_time": "0:01:14", "remaining_time": "0:57:27", "throughput": 2883.41, "total_tokens": 215664}
|
| 163 |
+
{"current_steps": 815, "total_steps": 38150, "loss": 0.5419, "lr": 1.0668414154652686e-05, "epoch": 0.21363040629095675, "percentage": 2.14, "elapsed_time": "0:01:15", "remaining_time": "0:57:28", "throughput": 2884.42, "total_tokens": 217104}
|
| 164 |
+
{"current_steps": 820, "total_steps": 38150, "loss": 0.6325, "lr": 1.0733944954128442e-05, "epoch": 0.21494102228047182, "percentage": 2.15, "elapsed_time": "0:01:15", "remaining_time": "0:57:25", "throughput": 2882.93, "total_tokens": 218224}
|
| 165 |
+
{"current_steps": 825, "total_steps": 38150, "loss": 0.5473, "lr": 1.0799475753604196e-05, "epoch": 0.2162516382699869, "percentage": 2.16, "elapsed_time": "0:01:16", "remaining_time": "0:57:24", "throughput": 2884.0, "total_tokens": 219584}
|
| 166 |
+
{"current_steps": 830, "total_steps": 38150, "loss": 0.6417, "lr": 1.0865006553079948e-05, "epoch": 0.21756225425950196, "percentage": 2.18, "elapsed_time": "0:01:16", "remaining_time": "0:57:23", "throughput": 2884.84, "total_tokens": 220912}
|
| 167 |
+
{"current_steps": 835, "total_steps": 38150, "loss": 0.4998, "lr": 1.0930537352555702e-05, "epoch": 0.21887287024901703, "percentage": 2.19, "elapsed_time": "0:01:17", "remaining_time": "0:57:23", "throughput": 2884.82, "total_tokens": 222272}
|
| 168 |
+
{"current_steps": 840, "total_steps": 38150, "loss": 0.6581, "lr": 1.0996068152031456e-05, "epoch": 0.22018348623853212, "percentage": 2.2, "elapsed_time": "0:01:17", "remaining_time": "0:57:22", "throughput": 2884.7, "total_tokens": 223600}
|
| 169 |
+
{"current_steps": 845, "total_steps": 38150, "loss": 0.8038, "lr": 1.1061598951507208e-05, "epoch": 0.2214941022280472, "percentage": 2.21, "elapsed_time": "0:01:18", "remaining_time": "0:57:26", "throughput": 2885.5, "total_tokens": 225232}
|
| 170 |
+
{"current_steps": 850, "total_steps": 38150, "loss": 0.5353, "lr": 1.1127129750982962e-05, "epoch": 0.22280471821756226, "percentage": 2.23, "elapsed_time": "0:01:18", "remaining_time": "0:57:24", "throughput": 2885.75, "total_tokens": 226512}
|
| 171 |
+
{"current_steps": 855, "total_steps": 38150, "loss": 0.7659, "lr": 1.1192660550458717e-05, "epoch": 0.22411533420707733, "percentage": 2.24, "elapsed_time": "0:01:18", "remaining_time": "0:57:22", "throughput": 2883.44, "total_tokens": 227552}
|
| 172 |
+
{"current_steps": 860, "total_steps": 38150, "loss": 0.6396, "lr": 1.125819134993447e-05, "epoch": 0.2254259501965924, "percentage": 2.25, "elapsed_time": "0:01:19", "remaining_time": "0:57:20", "throughput": 2881.31, "total_tokens": 228608}
|
| 173 |
+
{"current_steps": 865, "total_steps": 38150, "loss": 0.369, "lr": 1.1323722149410223e-05, "epoch": 0.22673656618610746, "percentage": 2.27, "elapsed_time": "0:01:19", "remaining_time": "0:57:21", "throughput": 2882.87, "total_tokens": 230192}
|
| 174 |
+
{"current_steps": 870, "total_steps": 38150, "loss": 0.5466, "lr": 1.1389252948885977e-05, "epoch": 0.22804718217562253, "percentage": 2.28, "elapsed_time": "0:01:20", "remaining_time": "0:57:22", "throughput": 2884.9, "total_tokens": 231776}
|
| 175 |
+
{"current_steps": 875, "total_steps": 38150, "loss": 0.7968, "lr": 1.145478374836173e-05, "epoch": 0.22935779816513763, "percentage": 2.29, "elapsed_time": "0:01:20", "remaining_time": "0:57:21", "throughput": 2885.05, "total_tokens": 233104}
|
| 176 |
+
{"current_steps": 880, "total_steps": 38150, "loss": 0.6053, "lr": 1.1520314547837483e-05, "epoch": 0.2306684141546527, "percentage": 2.31, "elapsed_time": "0:01:21", "remaining_time": "0:57:19", "throughput": 2882.88, "total_tokens": 234128}
|
| 177 |
+
{"current_steps": 885, "total_steps": 38150, "loss": 0.6386, "lr": 1.1585845347313237e-05, "epoch": 0.23197903014416776, "percentage": 2.32, "elapsed_time": "0:01:21", "remaining_time": "0:57:17", "throughput": 2882.33, "total_tokens": 235312}
|
| 178 |
+
{"current_steps": 890, "total_steps": 38150, "loss": 0.5435, "lr": 1.1651376146788991e-05, "epoch": 0.23328964613368283, "percentage": 2.33, "elapsed_time": "0:01:22", "remaining_time": "0:57:19", "throughput": 2883.63, "total_tokens": 236896}
|
| 179 |
+
{"current_steps": 895, "total_steps": 38150, "loss": 0.621, "lr": 1.1716906946264745e-05, "epoch": 0.2346002621231979, "percentage": 2.35, "elapsed_time": "0:01:22", "remaining_time": "0:57:17", "throughput": 2881.21, "total_tokens": 237936}
|
| 180 |
+
{"current_steps": 900, "total_steps": 38150, "loss": 0.6815, "lr": 1.1782437745740499e-05, "epoch": 0.23591087811271297, "percentage": 2.36, "elapsed_time": "0:01:23", "remaining_time": "0:57:18", "throughput": 2883.31, "total_tokens": 239552}
|
| 181 |
+
{"current_steps": 905, "total_steps": 38150, "loss": 0.5094, "lr": 1.1847968545216253e-05, "epoch": 0.23722149410222804, "percentage": 2.37, "elapsed_time": "0:01:23", "remaining_time": "0:57:17", "throughput": 2883.61, "total_tokens": 240832}
|
| 182 |
+
{"current_steps": 910, "total_steps": 38150, "loss": 0.618, "lr": 1.1913499344692005e-05, "epoch": 0.23853211009174313, "percentage": 2.39, "elapsed_time": "0:01:23", "remaining_time": "0:57:16", "throughput": 2883.99, "total_tokens": 242192}
|
| 183 |
+
{"current_steps": 915, "total_steps": 38150, "loss": 0.6321, "lr": 1.197903014416776e-05, "epoch": 0.2398427260812582, "percentage": 2.4, "elapsed_time": "0:01:24", "remaining_time": "0:57:14", "throughput": 2884.25, "total_tokens": 243456}
|
| 184 |
+
{"current_steps": 920, "total_steps": 38150, "loss": 0.7367, "lr": 1.2044560943643513e-05, "epoch": 0.24115334207077327, "percentage": 2.41, "elapsed_time": "0:01:24", "remaining_time": "0:57:17", "throughput": 2889.4, "total_tokens": 245424}
|
| 185 |
+
{"current_steps": 925, "total_steps": 38150, "loss": 0.5099, "lr": 1.2110091743119267e-05, "epoch": 0.24246395806028834, "percentage": 2.42, "elapsed_time": "0:01:25", "remaining_time": "0:57:16", "throughput": 2889.47, "total_tokens": 246752}
|
| 186 |
+
{"current_steps": 930, "total_steps": 38150, "loss": 0.5029, "lr": 1.2175622542595021e-05, "epoch": 0.2437745740498034, "percentage": 2.44, "elapsed_time": "0:01:25", "remaining_time": "0:57:16", "throughput": 2890.8, "total_tokens": 248256}
|
| 187 |
+
{"current_steps": 935, "total_steps": 38150, "loss": 0.501, "lr": 1.2241153342070775e-05, "epoch": 0.24508519003931847, "percentage": 2.45, "elapsed_time": "0:01:26", "remaining_time": "0:57:16", "throughput": 2891.28, "total_tokens": 249648}
|
| 188 |
+
{"current_steps": 940, "total_steps": 38150, "loss": 0.652, "lr": 1.2306684141546527e-05, "epoch": 0.24639580602883354, "percentage": 2.46, "elapsed_time": "0:01:26", "remaining_time": "0:57:20", "throughput": 2895.09, "total_tokens": 251600}
|
| 189 |
+
{"current_steps": 945, "total_steps": 38150, "loss": 0.5978, "lr": 1.2372214941022281e-05, "epoch": 0.24770642201834864, "percentage": 2.48, "elapsed_time": "0:01:27", "remaining_time": "0:57:18", "throughput": 2891.94, "total_tokens": 252544}
|
| 190 |
+
{"current_steps": 950, "total_steps": 38150, "loss": 1.0158, "lr": 1.2437745740498035e-05, "epoch": 0.2490170380078637, "percentage": 2.49, "elapsed_time": "0:01:27", "remaining_time": "0:57:16", "throughput": 2891.54, "total_tokens": 253776}
|
| 191 |
+
{"current_steps": 955, "total_steps": 38150, "loss": 0.4462, "lr": 1.2503276539973787e-05, "epoch": 0.2503276539973788, "percentage": 2.5, "elapsed_time": "0:01:28", "remaining_time": "0:57:16", "throughput": 2892.38, "total_tokens": 255232}
|
| 192 |
+
{"current_steps": 960, "total_steps": 38150, "loss": 0.6149, "lr": 1.2568807339449543e-05, "epoch": 0.2516382699868938, "percentage": 2.52, "elapsed_time": "0:01:28", "remaining_time": "0:57:16", "throughput": 2892.97, "total_tokens": 256640}
|
| 193 |
+
{"current_steps": 965, "total_steps": 38150, "loss": 0.5854, "lr": 1.2634338138925295e-05, "epoch": 0.2529488859764089, "percentage": 2.53, "elapsed_time": "0:01:29", "remaining_time": "0:57:15", "throughput": 2891.52, "total_tokens": 257760}
|
| 194 |
+
{"current_steps": 970, "total_steps": 38150, "loss": 0.4989, "lr": 1.2699868938401049e-05, "epoch": 0.254259501965924, "percentage": 2.54, "elapsed_time": "0:01:29", "remaining_time": "0:57:13", "throughput": 2890.98, "total_tokens": 258960}
|
| 195 |
+
{"current_steps": 975, "total_steps": 38150, "loss": 0.4653, "lr": 1.2765399737876801e-05, "epoch": 0.25557011795543905, "percentage": 2.56, "elapsed_time": "0:01:30", "remaining_time": "0:57:14", "throughput": 2892.14, "total_tokens": 260528}
|
| 196 |
+
{"current_steps": 980, "total_steps": 38150, "loss": 0.5024, "lr": 1.2830930537352557e-05, "epoch": 0.25688073394495414, "percentage": 2.57, "elapsed_time": "0:01:30", "remaining_time": "0:57:13", "throughput": 2891.57, "total_tokens": 261744}
|
| 197 |
+
{"current_steps": 985, "total_steps": 38150, "loss": 0.6827, "lr": 1.289646133682831e-05, "epoch": 0.2581913499344692, "percentage": 2.58, "elapsed_time": "0:01:30", "remaining_time": "0:57:11", "throughput": 2891.17, "total_tokens": 262928}
|
| 198 |
+
{"current_steps": 990, "total_steps": 38150, "loss": 0.5349, "lr": 1.2961992136304063e-05, "epoch": 0.2595019659239843, "percentage": 2.6, "elapsed_time": "0:01:31", "remaining_time": "0:57:10", "throughput": 2893.06, "total_tokens": 264384}
|
| 199 |
+
{"current_steps": 995, "total_steps": 38150, "loss": 0.9413, "lr": 1.3027522935779818e-05, "epoch": 0.2608125819134993, "percentage": 2.61, "elapsed_time": "0:01:31", "remaining_time": "0:57:08", "throughput": 2890.48, "total_tokens": 265392}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 38150, "loss": 0.8985, "lr": 1.309305373525557e-05, "epoch": 0.2621231979030144, "percentage": 2.62, "elapsed_time": "0:01:32", "remaining_time": "0:57:07", "throughput": 2890.03, "total_tokens": 266608}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 38150, "loss": 0.5641, "lr": 1.3158584534731325e-05, "epoch": 0.2634338138925295, "percentage": 2.63, "elapsed_time": "0:01:32", "remaining_time": "0:57:05", "throughput": 2891.09, "total_tokens": 267984}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 38150, "loss": 0.7562, "lr": 1.3224115334207077e-05, "epoch": 0.26474442988204455, "percentage": 2.65, "elapsed_time": "0:01:33", "remaining_time": "0:57:03", "throughput": 2888.45, "total_tokens": 268944}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 38150, "loss": 0.5354, "lr": 1.328964613368283e-05, "epoch": 0.26605504587155965, "percentage": 2.66, "elapsed_time": "0:01:33", "remaining_time": "0:57:04", "throughput": 2891.66, "total_tokens": 270672}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 38150, "loss": 0.483, "lr": 1.3355176933158586e-05, "epoch": 0.2673656618610747, "percentage": 2.67, "elapsed_time": "0:01:34", "remaining_time": "0:57:04", "throughput": 2893.46, "total_tokens": 272208}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 38150, "loss": 0.6171, "lr": 1.3420707732634339e-05, "epoch": 0.2686762778505898, "percentage": 2.69, "elapsed_time": "0:01:34", "remaining_time": "0:57:10", "throughput": 2900.13, "total_tokens": 274720}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 38150, "loss": 2.272, "lr": 1.3486238532110092e-05, "epoch": 0.2699868938401048, "percentage": 2.7, "elapsed_time": "0:01:35", "remaining_time": "0:57:09", "throughput": 2897.18, "total_tokens": 275664}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 38150, "loss": 0.7778, "lr": 1.3551769331585845e-05, "epoch": 0.2712975098296199, "percentage": 2.71, "elapsed_time": "0:01:35", "remaining_time": "0:57:10", "throughput": 2901.12, "total_tokens": 277568}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 38150, "loss": 0.493, "lr": 1.36173001310616e-05, "epoch": 0.272608125819135, "percentage": 2.73, "elapsed_time": "0:01:36", "remaining_time": "0:57:10", "throughput": 2900.63, "total_tokens": 278848}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 38150, "loss": 0.4935, "lr": 1.3682830930537352e-05, "epoch": 0.27391874180865006, "percentage": 2.74, "elapsed_time": "0:01:36", "remaining_time": "0:57:08", "throughput": 2899.38, "total_tokens": 279968}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 38150, "loss": 0.8195, "lr": 1.3748361730013106e-05, "epoch": 0.27522935779816515, "percentage": 2.75, "elapsed_time": "0:01:37", "remaining_time": "0:57:07", "throughput": 2898.76, "total_tokens": 281184}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 38150, "loss": 0.4179, "lr": 1.3813892529488862e-05, "epoch": 0.2765399737876802, "percentage": 2.77, "elapsed_time": "0:01:37", "remaining_time": "0:57:06", "throughput": 2899.25, "total_tokens": 282576}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 38150, "loss": 0.4908, "lr": 1.3879423328964614e-05, "epoch": 0.2778505897771953, "percentage": 2.78, "elapsed_time": "0:01:37", "remaining_time": "0:57:06", "throughput": 2900.64, "total_tokens": 284064}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 38150, "loss": 0.5646, "lr": 1.3944954128440368e-05, "epoch": 0.27916120576671033, "percentage": 2.79, "elapsed_time": "0:01:38", "remaining_time": "0:57:05", "throughput": 2899.45, "total_tokens": 285200}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 38150, "loss": 0.5693, "lr": 1.401048492791612e-05, "epoch": 0.2804718217562254, "percentage": 2.8, "elapsed_time": "0:01:38", "remaining_time": "0:57:04", "throughput": 2898.49, "total_tokens": 286432}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 38150, "loss": 0.5216, "lr": 1.4076015727391876e-05, "epoch": 0.2817824377457405, "percentage": 2.82, "elapsed_time": "0:01:39", "remaining_time": "0:57:04", "throughput": 2899.3, "total_tokens": 287888}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 38150, "loss": 0.6007, "lr": 1.4141546526867626e-05, "epoch": 0.28309305373525556, "percentage": 2.83, "elapsed_time": "0:01:39", "remaining_time": "0:57:03", "throughput": 2899.06, "total_tokens": 289120}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 38150, "loss": 0.7544, "lr": 1.4207077326343382e-05, "epoch": 0.28440366972477066, "percentage": 2.84, "elapsed_time": "0:01:40", "remaining_time": "0:57:01", "throughput": 2895.92, "total_tokens": 290032}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 38150, "loss": 0.4716, "lr": 1.4272608125819138e-05, "epoch": 0.2857142857142857, "percentage": 2.86, "elapsed_time": "0:01:40", "remaining_time": "0:57:00", "throughput": 2896.07, "total_tokens": 291328}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 38150, "loss": 0.3886, "lr": 1.4338138925294888e-05, "epoch": 0.2870249017038008, "percentage": 2.87, "elapsed_time": "0:01:41", "remaining_time": "0:57:04", "throughput": 2901.58, "total_tokens": 293632}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 38150, "loss": 0.734, "lr": 1.4403669724770644e-05, "epoch": 0.28833551769331583, "percentage": 2.88, "elapsed_time": "0:01:41", "remaining_time": "0:57:03", "throughput": 2900.8, "total_tokens": 294880}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 38150, "loss": 0.5104, "lr": 1.4469200524246396e-05, "epoch": 0.28964613368283093, "percentage": 2.9, "elapsed_time": "0:01:42", "remaining_time": "0:57:02", "throughput": 2901.41, "total_tokens": 296208}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 38150, "loss": 0.5594, "lr": 1.453473132372215e-05, "epoch": 0.290956749672346, "percentage": 2.91, "elapsed_time": "0:01:42", "remaining_time": "0:57:02", "throughput": 2902.96, "total_tokens": 297760}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 38150, "loss": 0.5377, "lr": 1.4600262123197902e-05, "epoch": 0.29226736566186107, "percentage": 2.92, "elapsed_time": "0:01:42", "remaining_time": "0:57:01", "throughput": 2901.39, "total_tokens": 298832}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 38150, "loss": 0.559, "lr": 1.4665792922673658e-05, "epoch": 0.29357798165137616, "percentage": 2.94, "elapsed_time": "0:01:43", "remaining_time": "0:56:59", "throughput": 2901.54, "total_tokens": 300112}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 38150, "loss": 0.634, "lr": 1.4731323722149412e-05, "epoch": 0.2948885976408912, "percentage": 2.95, "elapsed_time": "0:01:43", "remaining_time": "0:56:57", "throughput": 2900.68, "total_tokens": 301248}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 38150, "loss": 0.5054, "lr": 1.4796854521625164e-05, "epoch": 0.2961992136304063, "percentage": 2.96, "elapsed_time": "0:01:44", "remaining_time": "0:56:57", "throughput": 2901.31, "total_tokens": 302656}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 38150, "loss": 0.5848, "lr": 1.486238532110092e-05, "epoch": 0.29750982961992134, "percentage": 2.98, "elapsed_time": "0:01:44", "remaining_time": "0:56:56", "throughput": 2901.6, "total_tokens": 304000}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 38150, "loss": 0.6479, "lr": 1.4927916120576672e-05, "epoch": 0.29882044560943644, "percentage": 2.99, "elapsed_time": "0:01:45", "remaining_time": "0:56:56", "throughput": 2902.49, "total_tokens": 305472}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 38150, "loss": 0.345, "lr": 1.4993446920052426e-05, "epoch": 0.30013106159895153, "percentage": 3.0, "elapsed_time": "0:01:45", "remaining_time": "0:56:54", "throughput": 2900.24, "total_tokens": 306448}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 38150, "loss": 0.8363, "lr": 1.5058977719528178e-05, "epoch": 0.30144167758846657, "percentage": 3.01, "elapsed_time": "0:01:46", "remaining_time": "0:56:53", "throughput": 2899.69, "total_tokens": 307632}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 38150, "loss": 0.3954, "lr": 1.5124508519003932e-05, "epoch": 0.30275229357798167, "percentage": 3.03, "elapsed_time": "0:01:46", "remaining_time": "0:56:51", "throughput": 2898.88, "total_tokens": 308784}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 38150, "loss": 0.5174, "lr": 1.5190039318479687e-05, "epoch": 0.3040629095674967, "percentage": 3.04, "elapsed_time": "0:01:46", "remaining_time": "0:56:51", "throughput": 2898.95, "total_tokens": 310096}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 38150, "loss": 1.2299, "lr": 1.525557011795544e-05, "epoch": 0.3053735255570118, "percentage": 3.05, "elapsed_time": "0:01:47", "remaining_time": "0:56:50", "throughput": 2899.48, "total_tokens": 311472}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 38150, "loss": 0.6401, "lr": 1.5321100917431195e-05, "epoch": 0.30668414154652685, "percentage": 3.07, "elapsed_time": "0:01:47", "remaining_time": "0:56:49", "throughput": 2898.75, "total_tokens": 312704}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 38150, "loss": 0.4761, "lr": 1.5386631716906946e-05, "epoch": 0.30799475753604194, "percentage": 3.08, "elapsed_time": "0:01:48", "remaining_time": "0:56:48", "throughput": 2898.03, "total_tokens": 313888}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 38150, "loss": 0.5755, "lr": 1.54521625163827e-05, "epoch": 0.30930537352555704, "percentage": 3.09, "elapsed_time": "0:01:48", "remaining_time": "0:56:47", "throughput": 2896.56, "total_tokens": 315040}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 38150, "loss": 0.9387, "lr": 1.5517693315858454e-05, "epoch": 0.3106159895150721, "percentage": 3.11, "elapsed_time": "0:01:49", "remaining_time": "0:56:46", "throughput": 2896.88, "total_tokens": 316352}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 38150, "loss": 0.6202, "lr": 1.5583224115334208e-05, "epoch": 0.3119266055045872, "percentage": 3.12, "elapsed_time": "0:01:49", "remaining_time": "0:56:46", "throughput": 2896.22, "total_tokens": 317616}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 38150, "loss": 0.6555, "lr": 1.564875491480996e-05, "epoch": 0.3132372214941022, "percentage": 3.13, "elapsed_time": "0:01:50", "remaining_time": "0:56:46", "throughput": 2897.97, "total_tokens": 319184}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 38150, "loss": 0.5981, "lr": 1.5714285714285715e-05, "epoch": 0.3145478374836173, "percentage": 3.15, "elapsed_time": "0:01:50", "remaining_time": "0:56:46", "throughput": 2899.28, "total_tokens": 320752}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 38150, "loss": 0.4747, "lr": 1.577981651376147e-05, "epoch": 0.31585845347313235, "percentage": 3.16, "elapsed_time": "0:01:51", "remaining_time": "0:56:45", "throughput": 2899.19, "total_tokens": 322032}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 38150, "loss": 0.5116, "lr": 1.5845347313237223e-05, "epoch": 0.31716906946264745, "percentage": 3.17, "elapsed_time": "0:01:51", "remaining_time": "0:56:44", "throughput": 2899.5, "total_tokens": 323360}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 38150, "loss": 0.473, "lr": 1.5910878112712977e-05, "epoch": 0.31847968545216254, "percentage": 3.18, "elapsed_time": "0:01:51", "remaining_time": "0:56:43", "throughput": 2898.67, "total_tokens": 324528}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 38150, "loss": 0.5086, "lr": 1.5976408912188728e-05, "epoch": 0.3197903014416776, "percentage": 3.2, "elapsed_time": "0:01:52", "remaining_time": "0:56:47", "throughput": 2904.1, "total_tokens": 326928}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 38150, "loss": 0.4242, "lr": 1.604193971166448e-05, "epoch": 0.3211009174311927, "percentage": 3.21, "elapsed_time": "0:01:53", "remaining_time": "0:56:47", "throughput": 2905.01, "total_tokens": 328432}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 38150, "loss": 0.5819, "lr": 1.610747051114024e-05, "epoch": 0.3224115334207077, "percentage": 3.22, "elapsed_time": "0:01:53", "remaining_time": "0:56:46", "throughput": 2902.95, "total_tokens": 329440}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 38150, "loss": 0.3952, "lr": 1.617300131061599e-05, "epoch": 0.3237221494102228, "percentage": 3.24, "elapsed_time": "0:01:53", "remaining_time": "0:56:46", "throughput": 2903.82, "total_tokens": 330912}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 38150, "loss": 0.5953, "lr": 1.6238532110091743e-05, "epoch": 0.32503276539973786, "percentage": 3.25, "elapsed_time": "0:01:54", "remaining_time": "0:56:45", "throughput": 2904.0, "total_tokens": 332288}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 38150, "loss": 0.5915, "lr": 1.6304062909567497e-05, "epoch": 0.32634338138925295, "percentage": 3.26, "elapsed_time": "0:01:54", "remaining_time": "0:56:44", "throughput": 2904.31, "total_tokens": 333584}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 38150, "loss": 0.5593, "lr": 1.636959370904325e-05, "epoch": 0.32765399737876805, "percentage": 3.28, "elapsed_time": "0:01:55", "remaining_time": "0:56:47", "throughput": 2905.88, "total_tokens": 335392}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 38150, "loss": 0.6625, "lr": 1.6435124508519005e-05, "epoch": 0.3289646133682831, "percentage": 3.29, "elapsed_time": "0:01:55", "remaining_time": "0:56:45", "throughput": 2905.17, "total_tokens": 336560}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 38150, "loss": 0.634, "lr": 1.650065530799476e-05, "epoch": 0.3302752293577982, "percentage": 3.3, "elapsed_time": "0:01:56", "remaining_time": "0:56:45", "throughput": 2907.23, "total_tokens": 338192}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 38150, "loss": 0.6497, "lr": 1.6566186107470513e-05, "epoch": 0.3315858453473132, "percentage": 3.32, "elapsed_time": "0:01:56", "remaining_time": "0:56:45", "throughput": 2907.59, "total_tokens": 339568}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 38150, "loss": 0.4776, "lr": 1.6631716906946267e-05, "epoch": 0.3328964613368283, "percentage": 3.33, "elapsed_time": "0:01:57", "remaining_time": "0:56:43", "throughput": 2906.93, "total_tokens": 340736}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 38150, "loss": 1.1958, "lr": 1.669724770642202e-05, "epoch": 0.33420707732634336, "percentage": 3.34, "elapsed_time": "0:01:57", "remaining_time": "0:56:42", "throughput": 2904.38, "total_tokens": 341680}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 38150, "loss": 0.6276, "lr": 1.676277850589777e-05, "epoch": 0.33551769331585846, "percentage": 3.36, "elapsed_time": "0:01:58", "remaining_time": "0:56:40", "throughput": 2903.62, "total_tokens": 342800}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 38150, "loss": 0.6474, "lr": 1.682830930537353e-05, "epoch": 0.33682830930537355, "percentage": 3.37, "elapsed_time": "0:01:58", "remaining_time": "0:56:39", "throughput": 2903.33, "total_tokens": 344000}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 38150, "loss": 0.5122, "lr": 1.689384010484928e-05, "epoch": 0.3381389252948886, "percentage": 3.38, "elapsed_time": "0:01:59", "remaining_time": "0:56:41", "throughput": 2906.42, "total_tokens": 345968}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 38150, "loss": 0.4873, "lr": 1.6959370904325033e-05, "epoch": 0.3394495412844037, "percentage": 3.39, "elapsed_time": "0:01:59", "remaining_time": "0:56:41", "throughput": 2905.42, "total_tokens": 347264}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 38150, "loss": 0.5323, "lr": 1.702490170380079e-05, "epoch": 0.34076015727391873, "percentage": 3.41, "elapsed_time": "0:02:00", "remaining_time": "0:56:41", "throughput": 2905.87, "total_tokens": 348720}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 38150, "loss": 0.43, "lr": 1.709043250327654e-05, "epoch": 0.3420707732634338, "percentage": 3.42, "elapsed_time": "0:02:00", "remaining_time": "0:56:40", "throughput": 2906.12, "total_tokens": 350032}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 38150, "loss": 0.5165, "lr": 1.7155963302752295e-05, "epoch": 0.34338138925294887, "percentage": 3.43, "elapsed_time": "0:02:00", "remaining_time": "0:56:40", "throughput": 2906.4, "total_tokens": 351408}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 38150, "loss": 0.4325, "lr": 1.722149410222805e-05, "epoch": 0.34469200524246396, "percentage": 3.45, "elapsed_time": "0:02:01", "remaining_time": "0:56:38", "throughput": 2905.51, "total_tokens": 352560}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 38150, "loss": 0.5998, "lr": 1.7287024901703802e-05, "epoch": 0.34600262123197906, "percentage": 3.46, "elapsed_time": "0:02:01", "remaining_time": "0:56:38", "throughput": 2905.14, "total_tokens": 353824}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 38150, "loss": 0.4273, "lr": 1.7352555701179553e-05, "epoch": 0.3473132372214941, "percentage": 3.47, "elapsed_time": "0:02:02", "remaining_time": "0:56:38", "throughput": 2906.59, "total_tokens": 355456}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 38150, "loss": 0.4973, "lr": 1.741808650065531e-05, "epoch": 0.3486238532110092, "percentage": 3.49, "elapsed_time": "0:02:02", "remaining_time": "0:56:37", "throughput": 2904.9, "total_tokens": 356528}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 38150, "loss": 0.3728, "lr": 1.7483617300131064e-05, "epoch": 0.34993446920052423, "percentage": 3.5, "elapsed_time": "0:02:03", "remaining_time": "0:56:36", "throughput": 2904.17, "total_tokens": 357664}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 38150, "loss": 0.6563, "lr": 1.7549148099606815e-05, "epoch": 0.35124508519003933, "percentage": 3.51, "elapsed_time": "0:02:03", "remaining_time": "0:56:36", "throughput": 2904.83, "total_tokens": 359136}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 38150, "loss": 0.3813, "lr": 1.7614678899082572e-05, "epoch": 0.35255570117955437, "percentage": 3.53, "elapsed_time": "0:02:04", "remaining_time": "0:56:35", "throughput": 2905.9, "total_tokens": 360560}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 38150, "loss": 0.6403, "lr": 1.7680209698558323e-05, "epoch": 0.35386631716906947, "percentage": 3.54, "elapsed_time": "0:02:04", "remaining_time": "0:56:34", "throughput": 2906.65, "total_tokens": 361952}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 38150, "loss": 0.5332, "lr": 1.7745740498034076e-05, "epoch": 0.35517693315858456, "percentage": 3.55, "elapsed_time": "0:02:05", "remaining_time": "0:56:34", "throughput": 2906.61, "total_tokens": 363360}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 38150, "loss": 0.6022, "lr": 1.781127129750983e-05, "epoch": 0.3564875491480996, "percentage": 3.56, "elapsed_time": "0:02:05", "remaining_time": "0:56:33", "throughput": 2905.7, "total_tokens": 364480}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 38150, "loss": 0.7471, "lr": 1.7876802096985584e-05, "epoch": 0.3577981651376147, "percentage": 3.58, "elapsed_time": "0:02:05", "remaining_time": "0:56:31", "throughput": 2904.58, "total_tokens": 365584}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 38150, "loss": 0.7135, "lr": 1.7942332896461335e-05, "epoch": 0.35910878112712974, "percentage": 3.59, "elapsed_time": "0:02:06", "remaining_time": "0:56:30", "throughput": 2903.67, "total_tokens": 366704}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 38150, "loss": 0.7771, "lr": 1.8007863695937092e-05, "epoch": 0.36041939711664484, "percentage": 3.6, "elapsed_time": "0:02:06", "remaining_time": "0:56:29", "throughput": 2903.81, "total_tokens": 368000}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 38150, "loss": 0.4134, "lr": 1.8073394495412846e-05, "epoch": 0.3617300131061599, "percentage": 3.62, "elapsed_time": "0:02:07", "remaining_time": "0:56:29", "throughput": 2903.67, "total_tokens": 369360}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 38150, "loss": 0.53, "lr": 1.8138925294888597e-05, "epoch": 0.36304062909567497, "percentage": 3.63, "elapsed_time": "0:02:07", "remaining_time": "0:56:29", "throughput": 2904.71, "total_tokens": 370864}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 38150, "loss": 0.3567, "lr": 1.8204456094364354e-05, "epoch": 0.36435124508519, "percentage": 3.64, "elapsed_time": "0:02:08", "remaining_time": "0:56:27", "throughput": 2903.96, "total_tokens": 372000}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 38150, "loss": 0.9822, "lr": 1.8269986893840104e-05, "epoch": 0.3656618610747051, "percentage": 3.66, "elapsed_time": "0:02:08", "remaining_time": "0:56:26", "throughput": 2903.39, "total_tokens": 373168}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 38150, "loss": 0.64, "lr": 1.833551769331586e-05, "epoch": 0.3669724770642202, "percentage": 3.67, "elapsed_time": "0:02:08", "remaining_time": "0:56:25", "throughput": 2902.38, "total_tokens": 374304}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 38150, "loss": 0.3163, "lr": 1.8401048492791612e-05, "epoch": 0.36828309305373524, "percentage": 3.68, "elapsed_time": "0:02:09", "remaining_time": "0:56:25", "throughput": 2904.03, "total_tokens": 375888}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 38150, "loss": 0.5838, "lr": 1.8466579292267366e-05, "epoch": 0.36959370904325034, "percentage": 3.7, "elapsed_time": "0:02:09", "remaining_time": "0:56:24", "throughput": 2904.56, "total_tokens": 377296}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 38150, "loss": 0.4152, "lr": 1.853211009174312e-05, "epoch": 0.3709043250327654, "percentage": 3.71, "elapsed_time": "0:02:10", "remaining_time": "0:56:24", "throughput": 2904.43, "total_tokens": 378608}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 38150, "loss": 0.4893, "lr": 1.8597640891218874e-05, "epoch": 0.3722149410222805, "percentage": 3.72, "elapsed_time": "0:02:10", "remaining_time": "0:56:24", "throughput": 2905.51, "total_tokens": 380192}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 38150, "loss": 0.5901, "lr": 1.8663171690694628e-05, "epoch": 0.3735255570117955, "percentage": 3.74, "elapsed_time": "0:02:11", "remaining_time": "0:56:23", "throughput": 2906.53, "total_tokens": 381616}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 38150, "loss": 0.505, "lr": 1.872870249017038e-05, "epoch": 0.3748361730013106, "percentage": 3.75, "elapsed_time": "0:02:11", "remaining_time": "0:56:22", "throughput": 2905.19, "total_tokens": 382672}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 38150, "loss": 0.5805, "lr": 1.8794233289646136e-05, "epoch": 0.3761467889908257, "percentage": 3.76, "elapsed_time": "0:02:12", "remaining_time": "0:56:21", "throughput": 2906.58, "total_tokens": 384176}
|
| 288 |
+
{"current_steps": 1440, "total_steps": 38150, "loss": 0.7246, "lr": 1.8859764089121886e-05, "epoch": 0.37745740498034075, "percentage": 3.77, "elapsed_time": "0:02:12", "remaining_time": "0:56:21", "throughput": 2907.07, "total_tokens": 385584}
|
| 289 |
+
{"current_steps": 1445, "total_steps": 38150, "loss": 0.4377, "lr": 1.892529488859764e-05, "epoch": 0.37876802096985585, "percentage": 3.79, "elapsed_time": "0:02:13", "remaining_time": "0:56:20", "throughput": 2906.59, "total_tokens": 386832}
|
| 290 |
+
{"current_steps": 1450, "total_steps": 38150, "loss": 0.4578, "lr": 1.8990825688073397e-05, "epoch": 0.3800786369593709, "percentage": 3.8, "elapsed_time": "0:02:13", "remaining_time": "0:56:21", "throughput": 2907.44, "total_tokens": 388416}
|
| 291 |
+
{"current_steps": 1455, "total_steps": 38150, "loss": 0.3723, "lr": 1.9056356487549148e-05, "epoch": 0.381389252948886, "percentage": 3.81, "elapsed_time": "0:02:14", "remaining_time": "0:56:20", "throughput": 2907.2, "total_tokens": 389648}
|
| 292 |
+
{"current_steps": 1460, "total_steps": 38150, "loss": 0.3484, "lr": 1.9121887287024902e-05, "epoch": 0.382699868938401, "percentage": 3.83, "elapsed_time": "0:02:14", "remaining_time": "0:56:19", "throughput": 2906.82, "total_tokens": 390864}
|
| 293 |
+
{"current_steps": 1465, "total_steps": 38150, "loss": 0.5137, "lr": 1.9187418086500656e-05, "epoch": 0.3840104849279161, "percentage": 3.84, "elapsed_time": "0:02:14", "remaining_time": "0:56:18", "throughput": 2906.82, "total_tokens": 392128}
|
| 294 |
+
{"current_steps": 1470, "total_steps": 38150, "loss": 0.6429, "lr": 1.925294888597641e-05, "epoch": 0.3853211009174312, "percentage": 3.85, "elapsed_time": "0:02:15", "remaining_time": "0:56:24", "throughput": 2911.06, "total_tokens": 394864}
|
| 295 |
+
{"current_steps": 1475, "total_steps": 38150, "loss": 0.4161, "lr": 1.9318479685452164e-05, "epoch": 0.38663171690694625, "percentage": 3.87, "elapsed_time": "0:02:16", "remaining_time": "0:56:23", "throughput": 2908.85, "total_tokens": 395776}
|
| 296 |
+
{"current_steps": 1480, "total_steps": 38150, "loss": 0.7234, "lr": 1.9384010484927918e-05, "epoch": 0.38794233289646135, "percentage": 3.88, "elapsed_time": "0:02:16", "remaining_time": "0:56:21", "throughput": 2907.8, "total_tokens": 396880}
|
| 297 |
+
{"current_steps": 1485, "total_steps": 38150, "loss": 0.4897, "lr": 1.944954128440367e-05, "epoch": 0.3892529488859764, "percentage": 3.89, "elapsed_time": "0:02:16", "remaining_time": "0:56:22", "throughput": 2909.11, "total_tokens": 398512}
|
| 298 |
+
{"current_steps": 1490, "total_steps": 38150, "loss": 0.7631, "lr": 1.9515072083879425e-05, "epoch": 0.3905635648754915, "percentage": 3.91, "elapsed_time": "0:02:17", "remaining_time": "0:56:20", "throughput": 2908.42, "total_tokens": 399664}
|
| 299 |
+
{"current_steps": 1495, "total_steps": 38150, "loss": 0.3469, "lr": 1.958060288335518e-05, "epoch": 0.3918741808650065, "percentage": 3.92, "elapsed_time": "0:02:17", "remaining_time": "0:56:19", "throughput": 2907.92, "total_tokens": 400864}
|
| 300 |
+
{"current_steps": 1500, "total_steps": 38150, "loss": 0.5932, "lr": 1.964613368283093e-05, "epoch": 0.3931847968545216, "percentage": 3.93, "elapsed_time": "0:02:18", "remaining_time": "0:56:19", "throughput": 2908.69, "total_tokens": 402352}
|
| 301 |
+
{"current_steps": 1505, "total_steps": 38150, "loss": 0.5632, "lr": 1.9711664482306684e-05, "epoch": 0.3944954128440367, "percentage": 3.94, "elapsed_time": "0:02:18", "remaining_time": "0:56:19", "throughput": 2908.93, "total_tokens": 403744}
|
| 302 |
+
{"current_steps": 1510, "total_steps": 38150, "loss": 0.5145, "lr": 1.9777195281782438e-05, "epoch": 0.39580602883355176, "percentage": 3.96, "elapsed_time": "0:02:19", "remaining_time": "0:56:18", "throughput": 2909.51, "total_tokens": 405104}
|
| 303 |
+
{"current_steps": 1515, "total_steps": 38150, "loss": 0.7461, "lr": 1.984272608125819e-05, "epoch": 0.39711664482306686, "percentage": 3.97, "elapsed_time": "0:02:19", "remaining_time": "0:56:16", "throughput": 2908.73, "total_tokens": 406208}
|
| 304 |
+
{"current_steps": 1520, "total_steps": 38150, "loss": 0.5303, "lr": 1.9908256880733945e-05, "epoch": 0.3984272608125819, "percentage": 3.98, "elapsed_time": "0:02:20", "remaining_time": "0:56:15", "throughput": 2906.4, "total_tokens": 407120}
|
| 305 |
+
{"current_steps": 1525, "total_steps": 38150, "loss": 0.5914, "lr": 1.99737876802097e-05, "epoch": 0.399737876802097, "percentage": 4.0, "elapsed_time": "0:02:20", "remaining_time": "0:56:14", "throughput": 2904.63, "total_tokens": 408080}
|
| 306 |
+
{"current_steps": 1530, "total_steps": 38150, "loss": 0.5925, "lr": 2.0039318479685453e-05, "epoch": 0.40104849279161203, "percentage": 4.01, "elapsed_time": "0:02:20", "remaining_time": "0:56:13", "throughput": 2904.35, "total_tokens": 409360}
|
| 307 |
+
{"current_steps": 1535, "total_steps": 38150, "loss": 0.4984, "lr": 2.0104849279161207e-05, "epoch": 0.40235910878112713, "percentage": 4.02, "elapsed_time": "0:02:21", "remaining_time": "0:56:12", "throughput": 2904.81, "total_tokens": 410720}
|
| 308 |
+
{"current_steps": 1540, "total_steps": 38150, "loss": 0.5547, "lr": 2.017038007863696e-05, "epoch": 0.4036697247706422, "percentage": 4.04, "elapsed_time": "0:02:21", "remaining_time": "0:56:11", "throughput": 2904.45, "total_tokens": 411904}
|
| 309 |
+
{"current_steps": 1545, "total_steps": 38150, "loss": 0.574, "lr": 2.023591087811271e-05, "epoch": 0.40498034076015726, "percentage": 4.05, "elapsed_time": "0:02:22", "remaining_time": "0:56:09", "throughput": 2903.33, "total_tokens": 412960}
|
| 310 |
+
{"current_steps": 1550, "total_steps": 38150, "loss": 0.5387, "lr": 2.030144167758847e-05, "epoch": 0.40629095674967236, "percentage": 4.06, "elapsed_time": "0:02:22", "remaining_time": "0:56:11", "throughput": 2905.26, "total_tokens": 414784}
|
| 311 |
+
{"current_steps": 1555, "total_steps": 38150, "loss": 0.5704, "lr": 2.0366972477064223e-05, "epoch": 0.4076015727391874, "percentage": 4.08, "elapsed_time": "0:02:23", "remaining_time": "0:56:10", "throughput": 2906.11, "total_tokens": 416208}
|
| 312 |
+
{"current_steps": 1560, "total_steps": 38150, "loss": 0.4686, "lr": 2.0432503276539973e-05, "epoch": 0.4089121887287025, "percentage": 4.09, "elapsed_time": "0:02:23", "remaining_time": "0:56:09", "throughput": 2905.93, "total_tokens": 417440}
|
| 313 |
+
{"current_steps": 1565, "total_steps": 38150, "loss": 0.5881, "lr": 2.049803407601573e-05, "epoch": 0.41022280471821754, "percentage": 4.1, "elapsed_time": "0:02:24", "remaining_time": "0:56:09", "throughput": 2906.68, "total_tokens": 419008}
|
| 314 |
+
{"current_steps": 1570, "total_steps": 38150, "loss": 0.5021, "lr": 2.056356487549148e-05, "epoch": 0.41153342070773263, "percentage": 4.12, "elapsed_time": "0:02:24", "remaining_time": "0:56:08", "throughput": 2907.41, "total_tokens": 420384}
|
| 315 |
+
{"current_steps": 1575, "total_steps": 38150, "loss": 0.5988, "lr": 2.0629095674967235e-05, "epoch": 0.41284403669724773, "percentage": 4.13, "elapsed_time": "0:02:25", "remaining_time": "0:56:07", "throughput": 2906.18, "total_tokens": 421440}
|
| 316 |
+
{"current_steps": 1580, "total_steps": 38150, "loss": 0.5494, "lr": 2.069462647444299e-05, "epoch": 0.41415465268676277, "percentage": 4.14, "elapsed_time": "0:02:25", "remaining_time": "0:56:06", "throughput": 2905.68, "total_tokens": 422608}
|
| 317 |
+
{"current_steps": 1585, "total_steps": 38150, "loss": 0.527, "lr": 2.0760157273918743e-05, "epoch": 0.41546526867627787, "percentage": 4.15, "elapsed_time": "0:02:25", "remaining_time": "0:56:05", "throughput": 2906.17, "total_tokens": 423952}
|
| 318 |
+
{"current_steps": 1590, "total_steps": 38150, "loss": 0.5064, "lr": 2.0825688073394497e-05, "epoch": 0.4167758846657929, "percentage": 4.17, "elapsed_time": "0:02:26", "remaining_time": "0:56:05", "throughput": 2907.53, "total_tokens": 425552}
|
| 319 |
+
{"current_steps": 1595, "total_steps": 38150, "loss": 0.6502, "lr": 2.089121887287025e-05, "epoch": 0.418086500655308, "percentage": 4.18, "elapsed_time": "0:02:26", "remaining_time": "0:56:04", "throughput": 2906.51, "total_tokens": 426656}
|
| 320 |
+
{"current_steps": 1600, "total_steps": 38150, "loss": 0.7287, "lr": 2.0956749672346005e-05, "epoch": 0.41939711664482304, "percentage": 4.19, "elapsed_time": "0:02:27", "remaining_time": "0:56:03", "throughput": 2905.06, "total_tokens": 427696}
|
| 321 |
+
{"current_steps": 1605, "total_steps": 38150, "loss": 0.5959, "lr": 2.1022280471821755e-05, "epoch": 0.42070773263433814, "percentage": 4.21, "elapsed_time": "0:02:27", "remaining_time": "0:56:01", "throughput": 2903.38, "total_tokens": 428656}
|
| 322 |
+
{"current_steps": 1610, "total_steps": 38150, "loss": 0.6838, "lr": 2.1087811271297513e-05, "epoch": 0.42201834862385323, "percentage": 4.22, "elapsed_time": "0:02:28", "remaining_time": "0:56:01", "throughput": 2904.09, "total_tokens": 430128}
|
| 323 |
+
{"current_steps": 1615, "total_steps": 38150, "loss": 0.3815, "lr": 2.1153342070773263e-05, "epoch": 0.4233289646133683, "percentage": 4.23, "elapsed_time": "0:02:28", "remaining_time": "0:56:01", "throughput": 2905.46, "total_tokens": 431792}
|
| 324 |
+
{"current_steps": 1620, "total_steps": 38150, "loss": 0.4181, "lr": 2.1218872870249017e-05, "epoch": 0.42463958060288337, "percentage": 4.25, "elapsed_time": "0:02:29", "remaining_time": "0:56:01", "throughput": 2906.28, "total_tokens": 433200}
|
| 325 |
+
{"current_steps": 1625, "total_steps": 38150, "loss": 0.4455, "lr": 2.1284403669724774e-05, "epoch": 0.4259501965923984, "percentage": 4.26, "elapsed_time": "0:02:29", "remaining_time": "0:56:00", "throughput": 2907.35, "total_tokens": 434688}
|
| 326 |
+
{"current_steps": 1630, "total_steps": 38150, "loss": 0.7561, "lr": 2.1349934469200525e-05, "epoch": 0.4272608125819135, "percentage": 4.27, "elapsed_time": "0:02:29", "remaining_time": "0:55:59", "throughput": 2907.2, "total_tokens": 435920}
|
| 327 |
+
{"current_steps": 1635, "total_steps": 38150, "loss": 0.5686, "lr": 2.141546526867628e-05, "epoch": 0.42857142857142855, "percentage": 4.29, "elapsed_time": "0:02:30", "remaining_time": "0:56:01", "throughput": 2909.97, "total_tokens": 438000}
|
| 328 |
+
{"current_steps": 1640, "total_steps": 38150, "loss": 0.5332, "lr": 2.1480996068152033e-05, "epoch": 0.42988204456094364, "percentage": 4.3, "elapsed_time": "0:02:30", "remaining_time": "0:56:00", "throughput": 2909.11, "total_tokens": 439104}
|
| 329 |
+
{"current_steps": 1645, "total_steps": 38150, "loss": 0.5709, "lr": 2.1546526867627787e-05, "epoch": 0.43119266055045874, "percentage": 4.31, "elapsed_time": "0:02:31", "remaining_time": "0:55:59", "throughput": 2909.33, "total_tokens": 440400}
|
| 330 |
+
{"current_steps": 1650, "total_steps": 38150, "loss": 0.5826, "lr": 2.1612057667103537e-05, "epoch": 0.4325032765399738, "percentage": 4.33, "elapsed_time": "0:02:31", "remaining_time": "0:56:01", "throughput": 2912.18, "total_tokens": 442592}
|
| 331 |
+
{"current_steps": 1655, "total_steps": 38150, "loss": 0.6349, "lr": 2.1677588466579294e-05, "epoch": 0.4338138925294889, "percentage": 4.34, "elapsed_time": "0:02:32", "remaining_time": "0:56:01", "throughput": 2912.61, "total_tokens": 444016}
|
| 332 |
+
{"current_steps": 1660, "total_steps": 38150, "loss": 0.5075, "lr": 2.1743119266055048e-05, "epoch": 0.4351245085190039, "percentage": 4.35, "elapsed_time": "0:02:32", "remaining_time": "0:56:01", "throughput": 2912.74, "total_tokens": 445424}
|
| 333 |
+
{"current_steps": 1665, "total_steps": 38150, "loss": 0.4579, "lr": 2.18086500655308e-05, "epoch": 0.436435124508519, "percentage": 4.36, "elapsed_time": "0:02:33", "remaining_time": "0:56:00", "throughput": 2913.09, "total_tokens": 446768}
|
| 334 |
+
{"current_steps": 1670, "total_steps": 38150, "loss": 0.7532, "lr": 2.1874180865006556e-05, "epoch": 0.43774574049803405, "percentage": 4.38, "elapsed_time": "0:02:33", "remaining_time": "0:56:00", "throughput": 2914.06, "total_tokens": 448288}
|
| 335 |
+
{"current_steps": 1675, "total_steps": 38150, "loss": 0.7297, "lr": 2.1939711664482307e-05, "epoch": 0.43905635648754915, "percentage": 4.39, "elapsed_time": "0:02:34", "remaining_time": "0:55:59", "throughput": 2913.31, "total_tokens": 449440}
|
| 336 |
+
{"current_steps": 1680, "total_steps": 38150, "loss": 0.4648, "lr": 2.200524246395806e-05, "epoch": 0.44036697247706424, "percentage": 4.4, "elapsed_time": "0:02:34", "remaining_time": "0:55:59", "throughput": 2913.58, "total_tokens": 450832}
|
| 337 |
+
{"current_steps": 1685, "total_steps": 38150, "loss": 0.6376, "lr": 2.2070773263433814e-05, "epoch": 0.4416775884665793, "percentage": 4.42, "elapsed_time": "0:02:35", "remaining_time": "0:55:57", "throughput": 2913.04, "total_tokens": 451984}
|
| 338 |
+
{"current_steps": 1690, "total_steps": 38150, "loss": 0.5312, "lr": 2.213630406290957e-05, "epoch": 0.4429882044560944, "percentage": 4.43, "elapsed_time": "0:02:35", "remaining_time": "0:55:56", "throughput": 2913.71, "total_tokens": 453376}
|
| 339 |
+
{"current_steps": 1695, "total_steps": 38150, "loss": 0.424, "lr": 2.2201834862385322e-05, "epoch": 0.4442988204456094, "percentage": 4.44, "elapsed_time": "0:02:36", "remaining_time": "0:55:56", "throughput": 2913.77, "total_tokens": 454672}
|
| 340 |
+
{"current_steps": 1700, "total_steps": 38150, "loss": 0.4403, "lr": 2.2267365661861076e-05, "epoch": 0.4456094364351245, "percentage": 4.46, "elapsed_time": "0:02:36", "remaining_time": "0:55:56", "throughput": 2914.74, "total_tokens": 456240}
|
| 341 |
+
{"current_steps": 1705, "total_steps": 38150, "loss": 0.4756, "lr": 2.233289646133683e-05, "epoch": 0.44692005242463956, "percentage": 4.47, "elapsed_time": "0:02:36", "remaining_time": "0:55:55", "throughput": 2915.02, "total_tokens": 457632}
|
| 342 |
+
{"current_steps": 1710, "total_steps": 38150, "loss": 0.3792, "lr": 2.239842726081258e-05, "epoch": 0.44823066841415465, "percentage": 4.48, "elapsed_time": "0:02:37", "remaining_time": "0:55:56", "throughput": 2915.62, "total_tokens": 459200}
|
| 343 |
+
{"current_steps": 1715, "total_steps": 38150, "loss": 0.5779, "lr": 2.2463958060288338e-05, "epoch": 0.44954128440366975, "percentage": 4.5, "elapsed_time": "0:02:37", "remaining_time": "0:55:55", "throughput": 2915.16, "total_tokens": 460384}
|
| 344 |
+
{"current_steps": 1720, "total_steps": 38150, "loss": 0.5067, "lr": 2.252948885976409e-05, "epoch": 0.4508519003931848, "percentage": 4.51, "elapsed_time": "0:02:38", "remaining_time": "0:55:54", "throughput": 2915.38, "total_tokens": 461712}
|
| 345 |
+
{"current_steps": 1725, "total_steps": 38150, "loss": 0.3813, "lr": 2.2595019659239842e-05, "epoch": 0.4521625163826999, "percentage": 4.52, "elapsed_time": "0:02:38", "remaining_time": "0:55:52", "throughput": 2914.79, "total_tokens": 462832}
|
| 346 |
+
{"current_steps": 1730, "total_steps": 38150, "loss": 0.4115, "lr": 2.26605504587156e-05, "epoch": 0.4534731323722149, "percentage": 4.53, "elapsed_time": "0:02:39", "remaining_time": "0:55:52", "throughput": 2914.91, "total_tokens": 464224}
|
| 347 |
+
{"current_steps": 1735, "total_steps": 38150, "loss": 0.4886, "lr": 2.272608125819135e-05, "epoch": 0.45478374836173, "percentage": 4.55, "elapsed_time": "0:02:39", "remaining_time": "0:55:52", "throughput": 2915.56, "total_tokens": 465696}
|
| 348 |
+
{"current_steps": 1740, "total_steps": 38150, "loss": 0.542, "lr": 2.2791612057667104e-05, "epoch": 0.45609436435124506, "percentage": 4.56, "elapsed_time": "0:02:40", "remaining_time": "0:55:52", "throughput": 2914.9, "total_tokens": 466944}
|
| 349 |
+
{"current_steps": 1745, "total_steps": 38150, "loss": 0.5699, "lr": 2.2857142857142858e-05, "epoch": 0.45740498034076016, "percentage": 4.57, "elapsed_time": "0:02:40", "remaining_time": "0:55:51", "throughput": 2915.18, "total_tokens": 468256}
|
| 350 |
+
{"current_steps": 1750, "total_steps": 38150, "loss": 0.5485, "lr": 2.2922673656618612e-05, "epoch": 0.45871559633027525, "percentage": 4.59, "elapsed_time": "0:02:41", "remaining_time": "0:55:49", "throughput": 2914.43, "total_tokens": 469376}
|
| 351 |
+
{"current_steps": 1755, "total_steps": 38150, "loss": 0.6248, "lr": 2.2988204456094366e-05, "epoch": 0.4600262123197903, "percentage": 4.6, "elapsed_time": "0:02:41", "remaining_time": "0:55:48", "throughput": 2912.64, "total_tokens": 470336}
|
| 352 |
+
{"current_steps": 1760, "total_steps": 38150, "loss": 0.6179, "lr": 2.305373525557012e-05, "epoch": 0.4613368283093054, "percentage": 4.61, "elapsed_time": "0:02:41", "remaining_time": "0:55:47", "throughput": 2911.32, "total_tokens": 471360}
|
| 353 |
+
{"current_steps": 1765, "total_steps": 38150, "loss": 0.6513, "lr": 2.3119266055045874e-05, "epoch": 0.46264744429882043, "percentage": 4.63, "elapsed_time": "0:02:42", "remaining_time": "0:55:46", "throughput": 2911.0, "total_tokens": 472576}
|
| 354 |
+
{"current_steps": 1770, "total_steps": 38150, "loss": 0.6138, "lr": 2.3184796854521628e-05, "epoch": 0.4639580602883355, "percentage": 4.64, "elapsed_time": "0:02:42", "remaining_time": "0:55:46", "throughput": 2912.32, "total_tokens": 474224}
|
| 355 |
+
{"current_steps": 1775, "total_steps": 38150, "loss": 0.5069, "lr": 2.325032765399738e-05, "epoch": 0.46526867627785057, "percentage": 4.65, "elapsed_time": "0:02:43", "remaining_time": "0:55:45", "throughput": 2911.84, "total_tokens": 475376}
|
| 356 |
+
{"current_steps": 1780, "total_steps": 38150, "loss": 0.681, "lr": 2.3315858453473132e-05, "epoch": 0.46657929226736566, "percentage": 4.67, "elapsed_time": "0:02:43", "remaining_time": "0:55:44", "throughput": 2911.23, "total_tokens": 476592}
|
| 357 |
+
{"current_steps": 1785, "total_steps": 38150, "loss": 0.6823, "lr": 2.3381389252948886e-05, "epoch": 0.46788990825688076, "percentage": 4.68, "elapsed_time": "0:02:44", "remaining_time": "0:55:43", "throughput": 2909.42, "total_tokens": 477504}
|
| 358 |
+
{"current_steps": 1790, "total_steps": 38150, "loss": 0.5181, "lr": 2.344692005242464e-05, "epoch": 0.4692005242463958, "percentage": 4.69, "elapsed_time": "0:02:44", "remaining_time": "0:55:42", "throughput": 2908.21, "total_tokens": 478560}
|
| 359 |
+
{"current_steps": 1795, "total_steps": 38150, "loss": 0.4554, "lr": 2.3512450851900394e-05, "epoch": 0.4705111402359109, "percentage": 4.71, "elapsed_time": "0:02:44", "remaining_time": "0:55:41", "throughput": 2908.61, "total_tokens": 479920}
|
| 360 |
+
{"current_steps": 1800, "total_steps": 38150, "loss": 0.3995, "lr": 2.3577981651376148e-05, "epoch": 0.47182175622542594, "percentage": 4.72, "elapsed_time": "0:02:45", "remaining_time": "0:55:40", "throughput": 2908.98, "total_tokens": 481264}
|
| 361 |
+
{"current_steps": 1805, "total_steps": 38150, "loss": 0.9633, "lr": 2.36435124508519e-05, "epoch": 0.47313237221494103, "percentage": 4.73, "elapsed_time": "0:02:45", "remaining_time": "0:55:40", "throughput": 2908.97, "total_tokens": 482608}
|
| 362 |
+
{"current_steps": 1810, "total_steps": 38150, "loss": 0.4989, "lr": 2.3709043250327656e-05, "epoch": 0.4744429882044561, "percentage": 4.74, "elapsed_time": "0:02:46", "remaining_time": "0:55:40", "throughput": 2909.65, "total_tokens": 484096}
|
| 363 |
+
{"current_steps": 1815, "total_steps": 38150, "loss": 0.5268, "lr": 2.377457404980341e-05, "epoch": 0.47575360419397117, "percentage": 4.76, "elapsed_time": "0:02:46", "remaining_time": "0:55:39", "throughput": 2908.53, "total_tokens": 485120}
|
| 364 |
+
{"current_steps": 1820, "total_steps": 38150, "loss": 0.3852, "lr": 2.3840104849279163e-05, "epoch": 0.47706422018348627, "percentage": 4.77, "elapsed_time": "0:02:47", "remaining_time": "0:55:37", "throughput": 2907.01, "total_tokens": 486080}
|
| 365 |
+
{"current_steps": 1825, "total_steps": 38150, "loss": 0.5655, "lr": 2.3905635648754914e-05, "epoch": 0.4783748361730013, "percentage": 4.78, "elapsed_time": "0:02:47", "remaining_time": "0:55:36", "throughput": 2907.06, "total_tokens": 487344}
|
| 366 |
+
{"current_steps": 1830, "total_steps": 38150, "loss": 0.4897, "lr": 2.397116644823067e-05, "epoch": 0.4796854521625164, "percentage": 4.8, "elapsed_time": "0:02:48", "remaining_time": "0:55:35", "throughput": 2907.0, "total_tokens": 488608}
|
| 367 |
+
{"current_steps": 1835, "total_steps": 38150, "loss": 0.5226, "lr": 2.4036697247706425e-05, "epoch": 0.48099606815203144, "percentage": 4.81, "elapsed_time": "0:02:48", "remaining_time": "0:55:34", "throughput": 2905.84, "total_tokens": 489664}
|
| 368 |
+
{"current_steps": 1840, "total_steps": 38150, "loss": 0.4796, "lr": 2.4102228047182176e-05, "epoch": 0.48230668414154654, "percentage": 4.82, "elapsed_time": "0:02:48", "remaining_time": "0:55:34", "throughput": 2906.46, "total_tokens": 491120}
|
| 369 |
+
{"current_steps": 1845, "total_steps": 38150, "loss": 0.4987, "lr": 2.4167758846657933e-05, "epoch": 0.4836173001310616, "percentage": 4.84, "elapsed_time": "0:02:49", "remaining_time": "0:55:34", "throughput": 2906.51, "total_tokens": 492464}
|
| 370 |
+
{"current_steps": 1850, "total_steps": 38150, "loss": 0.5534, "lr": 2.4233289646133683e-05, "epoch": 0.4849279161205767, "percentage": 4.85, "elapsed_time": "0:02:49", "remaining_time": "0:55:33", "throughput": 2906.41, "total_tokens": 493712}
|
| 371 |
+
{"current_steps": 1855, "total_steps": 38150, "loss": 0.4145, "lr": 2.4298820445609437e-05, "epoch": 0.48623853211009177, "percentage": 4.86, "elapsed_time": "0:02:50", "remaining_time": "0:55:31", "throughput": 2905.76, "total_tokens": 494816}
|
| 372 |
+
{"current_steps": 1860, "total_steps": 38150, "loss": 0.4663, "lr": 2.436435124508519e-05, "epoch": 0.4875491480996068, "percentage": 4.88, "elapsed_time": "0:02:50", "remaining_time": "0:55:31", "throughput": 2906.23, "total_tokens": 496256}
|
| 373 |
+
{"current_steps": 1865, "total_steps": 38150, "loss": 0.5588, "lr": 2.4429882044560945e-05, "epoch": 0.4888597640891219, "percentage": 4.89, "elapsed_time": "0:02:51", "remaining_time": "0:55:30", "throughput": 2905.16, "total_tokens": 497280}
|
| 374 |
+
{"current_steps": 1870, "total_steps": 38150, "loss": 0.6248, "lr": 2.44954128440367e-05, "epoch": 0.49017038007863695, "percentage": 4.9, "elapsed_time": "0:02:51", "remaining_time": "0:55:29", "throughput": 2903.11, "total_tokens": 498144}
|
| 375 |
+
{"current_steps": 1875, "total_steps": 38150, "loss": 0.5519, "lr": 2.4560943643512453e-05, "epoch": 0.49148099606815204, "percentage": 4.91, "elapsed_time": "0:02:52", "remaining_time": "0:55:29", "throughput": 2903.65, "total_tokens": 499648}
|
| 376 |
+
{"current_steps": 1880, "total_steps": 38150, "loss": 0.4062, "lr": 2.4626474442988207e-05, "epoch": 0.4927916120576671, "percentage": 4.93, "elapsed_time": "0:02:52", "remaining_time": "0:55:29", "throughput": 2905.46, "total_tokens": 501488}
|
| 377 |
+
{"current_steps": 1885, "total_steps": 38150, "loss": 0.6932, "lr": 2.4692005242463957e-05, "epoch": 0.4941022280471822, "percentage": 4.94, "elapsed_time": "0:02:53", "remaining_time": "0:55:30", "throughput": 2907.92, "total_tokens": 503456}
|
| 378 |
+
{"current_steps": 1890, "total_steps": 38150, "loss": 0.3835, "lr": 2.4757536041939715e-05, "epoch": 0.4954128440366973, "percentage": 4.95, "elapsed_time": "0:02:53", "remaining_time": "0:55:29", "throughput": 2907.1, "total_tokens": 504544}
|
| 379 |
+
{"current_steps": 1895, "total_steps": 38150, "loss": 0.5434, "lr": 2.4823066841415465e-05, "epoch": 0.4967234600262123, "percentage": 4.97, "elapsed_time": "0:02:53", "remaining_time": "0:55:28", "throughput": 2906.66, "total_tokens": 505728}
|
| 380 |
+
{"current_steps": 1900, "total_steps": 38150, "loss": 0.6397, "lr": 2.488859764089122e-05, "epoch": 0.4980340760157274, "percentage": 4.98, "elapsed_time": "0:02:54", "remaining_time": "0:55:27", "throughput": 2904.97, "total_tokens": 506640}
|
| 381 |
+
{"current_steps": 1905, "total_steps": 38150, "loss": 0.4217, "lr": 2.4954128440366977e-05, "epoch": 0.49934469200524245, "percentage": 4.99, "elapsed_time": "0:02:54", "remaining_time": "0:55:26", "throughput": 2905.11, "total_tokens": 507904}
|
| 382 |
+
{"current_steps": 1908, "total_steps": 38150, "eval_loss": 0.5446770191192627, "epoch": 0.5001310615989515, "percentage": 5.0, "elapsed_time": "0:03:11", "remaining_time": "1:00:46", "throughput": 2649.37, "total_tokens": 508608}
|
| 383 |
+
{"current_steps": 1910, "total_steps": 38150, "loss": 0.5547, "lr": 2.501965923984273e-05, "epoch": 0.5006553079947575, "percentage": 5.01, "elapsed_time": "0:03:14", "remaining_time": "1:01:26", "throughput": 2619.46, "total_tokens": 508992}
|
| 384 |
+
{"current_steps": 1915, "total_steps": 38150, "loss": 0.3163, "lr": 2.5085190039318478e-05, "epoch": 0.5019659239842726, "percentage": 5.02, "elapsed_time": "0:03:14", "remaining_time": "1:01:25", "throughput": 2619.72, "total_tokens": 510256}
|
| 385 |
+
{"current_steps": 1920, "total_steps": 38150, "loss": 0.5593, "lr": 2.5150720838794235e-05, "epoch": 0.5032765399737876, "percentage": 5.03, "elapsed_time": "0:03:15", "remaining_time": "1:01:23", "throughput": 2620.4, "total_tokens": 511536}
|
| 386 |
+
{"current_steps": 1925, "total_steps": 38150, "loss": 0.6053, "lr": 2.521625163826999e-05, "epoch": 0.5045871559633027, "percentage": 5.05, "elapsed_time": "0:03:15", "remaining_time": "1:01:22", "throughput": 2621.49, "total_tokens": 512992}
|
| 387 |
+
{"current_steps": 1930, "total_steps": 38150, "loss": 0.4414, "lr": 2.5281782437745743e-05, "epoch": 0.5058977719528178, "percentage": 5.06, "elapsed_time": "0:03:16", "remaining_time": "1:01:20", "throughput": 2621.71, "total_tokens": 514208}
|
| 388 |
+
{"current_steps": 1935, "total_steps": 38150, "loss": 0.7122, "lr": 2.5347313237221493e-05, "epoch": 0.5072083879423329, "percentage": 5.07, "elapsed_time": "0:03:16", "remaining_time": "1:01:19", "throughput": 2622.16, "total_tokens": 515536}
|
| 389 |
+
{"current_steps": 1940, "total_steps": 38150, "loss": 0.6212, "lr": 2.5412844036697247e-05, "epoch": 0.508519003931848, "percentage": 5.09, "elapsed_time": "0:03:17", "remaining_time": "1:01:17", "throughput": 2622.27, "total_tokens": 516720}
|
| 390 |
+
{"current_steps": 1945, "total_steps": 38150, "loss": 0.4091, "lr": 2.5478374836173e-05, "epoch": 0.509829619921363, "percentage": 5.1, "elapsed_time": "0:03:17", "remaining_time": "1:01:15", "throughput": 2622.08, "total_tokens": 517808}
|
| 391 |
+
{"current_steps": 1950, "total_steps": 38150, "loss": 0.4856, "lr": 2.554390563564876e-05, "epoch": 0.5111402359108781, "percentage": 5.11, "elapsed_time": "0:03:17", "remaining_time": "1:01:14", "throughput": 2623.31, "total_tokens": 519312}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54099557616fe844926e35cc6b005a0472c7128dd67ca373ee8a428ddb059ad3
|
| 3 |
+
size 6225
|