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 +56 -0
- trainer_log.jsonl +386 -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 |
+
"exclude_modules": null,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"modules_to_save": null,
|
| 7 |
+
"peft_type": "LN_TUNING",
|
| 8 |
+
"revision": null,
|
| 9 |
+
"target_modules": [
|
| 10 |
+
"input_layernorm",
|
| 11 |
+
"post_attention_layernorm",
|
| 12 |
+
"norm"
|
| 13 |
+
],
|
| 14 |
+
"task_type": "CAUSAL_LM"
|
| 15 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6605758a75bb363d3039b214e44ecb02cf15950dfbffa8b8893a34dcf812cf73
|
| 3 |
+
size 1074144
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
seed: 42
|
| 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: lntuning
|
| 13 |
+
task_type: CAUSAL_LM
|
| 14 |
+
|
| 15 |
+
### dataset
|
| 16 |
+
dataset: codealpacapy
|
| 17 |
+
template: llama3
|
| 18 |
+
cutoff_len: 2048
|
| 19 |
+
overwrite_cache: true
|
| 20 |
+
preprocessing_num_workers: 8
|
| 21 |
+
dataloader_num_workers: 2
|
| 22 |
+
packing: false
|
| 23 |
+
|
| 24 |
+
### output
|
| 25 |
+
output_dir: saves_multiple/lntuning/llama-3-8b-instruct/train_codealpacapy_42_1760719585
|
| 26 |
+
logging_steps: 5
|
| 27 |
+
save_steps: 0.05
|
| 28 |
+
overwrite_output_dir: true
|
| 29 |
+
save_only_model: false
|
| 30 |
+
plot_loss: true
|
| 31 |
+
include_num_input_tokens_seen: true
|
| 32 |
+
push_to_hub: true
|
| 33 |
+
push_to_hub_organization: rbelanec
|
| 34 |
+
load_best_model_at_end: true
|
| 35 |
+
save_total_limit: 1
|
| 36 |
+
|
| 37 |
+
### train
|
| 38 |
+
per_device_train_batch_size: 4
|
| 39 |
+
learning_rate: 5.0e-5
|
| 40 |
+
num_train_epochs: 20
|
| 41 |
+
weight_decay: 1.0e-5
|
| 42 |
+
lr_scheduler_type: cosine
|
| 43 |
+
bf16: true
|
| 44 |
+
ddp_timeout: 180000000
|
| 45 |
+
resume_from_checkpoint: null
|
| 46 |
+
warmup_ratio: 0.1
|
| 47 |
+
optim: adamw_torch
|
| 48 |
+
report_to:
|
| 49 |
+
- wandb
|
| 50 |
+
run_name: lntuning_llama-3-8b-instruct_train_codealpacapy_42_1760719585
|
| 51 |
+
|
| 52 |
+
### eval
|
| 53 |
+
per_device_eval_batch_size: 4
|
| 54 |
+
eval_strategy: steps
|
| 55 |
+
eval_steps: 0.05
|
| 56 |
+
val_size: 0.1
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 38160, "loss": 1.1831, "lr": 5.241090146750525e-08, "epoch": 0.002620545073375262, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "3:14:45", "throughput": 2131.46, "total_tokens": 3264}
|
| 2 |
+
{"current_steps": 10, "total_steps": 38160, "loss": 1.2437, "lr": 1.1792452830188679e-07, "epoch": 0.005241090146750524, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "2:24:35", "throughput": 2589.19, "total_tokens": 5888}
|
| 3 |
+
{"current_steps": 15, "total_steps": 38160, "loss": 1.348, "lr": 1.8343815513626837e-07, "epoch": 0.007861635220125786, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "2:06:06", "throughput": 2849.93, "total_tokens": 8480}
|
| 4 |
+
{"current_steps": 20, "total_steps": 38160, "loss": 1.4211, "lr": 2.489517819706499e-07, "epoch": 0.010482180293501049, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "1:59:42", "throughput": 3049.93, "total_tokens": 11488}
|
| 5 |
+
{"current_steps": 25, "total_steps": 38160, "loss": 1.1751, "lr": 3.144654088050315e-07, "epoch": 0.01310272536687631, "percentage": 0.07, "elapsed_time": "0:00:04", "remaining_time": "1:56:02", "throughput": 3259.89, "total_tokens": 14880}
|
| 6 |
+
{"current_steps": 30, "total_steps": 38160, "loss": 1.0908, "lr": 3.79979035639413e-07, "epoch": 0.015723270440251572, "percentage": 0.08, "elapsed_time": "0:00:05", "remaining_time": "1:54:48", "throughput": 3430.45, "total_tokens": 18592}
|
| 7 |
+
{"current_steps": 35, "total_steps": 38160, "loss": 1.2527, "lr": 4.454926624737945e-07, "epoch": 0.018343815513626835, "percentage": 0.09, "elapsed_time": "0:00:06", "remaining_time": "1:51:24", "throughput": 3514.87, "total_tokens": 21568}
|
| 8 |
+
{"current_steps": 40, "total_steps": 38160, "loss": 1.5206, "lr": 5.110062893081761e-07, "epoch": 0.020964360587002098, "percentage": 0.1, "elapsed_time": "0:00:06", "remaining_time": "1:48:55", "throughput": 3523.03, "total_tokens": 24160}
|
| 9 |
+
{"current_steps": 45, "total_steps": 38160, "loss": 1.4199, "lr": 5.765199161425577e-07, "epoch": 0.02358490566037736, "percentage": 0.12, "elapsed_time": "0:00:07", "remaining_time": "1:47:11", "throughput": 3578.02, "total_tokens": 27168}
|
| 10 |
+
{"current_steps": 50, "total_steps": 38160, "loss": 1.1084, "lr": 6.420335429769392e-07, "epoch": 0.02620545073375262, "percentage": 0.13, "elapsed_time": "0:00:08", "remaining_time": "1:45:16", "throughput": 3629.64, "total_tokens": 30080}
|
| 11 |
+
{"current_steps": 55, "total_steps": 38160, "loss": 1.4812, "lr": 7.075471698113208e-07, "epoch": 0.028825995807127882, "percentage": 0.14, "elapsed_time": "0:00:09", "remaining_time": "1:44:10", "throughput": 3614.19, "total_tokens": 32608}
|
| 12 |
+
{"current_steps": 60, "total_steps": 38160, "loss": 1.1647, "lr": 7.730607966457024e-07, "epoch": 0.031446540880503145, "percentage": 0.16, "elapsed_time": "0:00:09", "remaining_time": "1:44:30", "throughput": 3691.17, "total_tokens": 36448}
|
| 13 |
+
{"current_steps": 65, "total_steps": 38160, "loss": 1.0807, "lr": 8.38574423480084e-07, "epoch": 0.034067085953878404, "percentage": 0.17, "elapsed_time": "0:00:10", "remaining_time": "1:43:01", "throughput": 3692.15, "total_tokens": 38944}
|
| 14 |
+
{"current_steps": 70, "total_steps": 38160, "loss": 1.4659, "lr": 9.040880503144654e-07, "epoch": 0.03668763102725367, "percentage": 0.18, "elapsed_time": "0:00:11", "remaining_time": "1:42:55", "throughput": 3685.21, "total_tokens": 41824}
|
| 15 |
+
{"current_steps": 75, "total_steps": 38160, "loss": 1.1347, "lr": 9.69601677148847e-07, "epoch": 0.03930817610062893, "percentage": 0.2, "elapsed_time": "0:00:12", "remaining_time": "1:42:54", "throughput": 3692.2, "total_tokens": 44896}
|
| 16 |
+
{"current_steps": 80, "total_steps": 38160, "loss": 1.1628, "lr": 1.0351153039832286e-06, "epoch": 0.041928721174004195, "percentage": 0.21, "elapsed_time": "0:00:12", "remaining_time": "1:42:30", "throughput": 3684.84, "total_tokens": 47616}
|
| 17 |
+
{"current_steps": 85, "total_steps": 38160, "loss": 1.3055, "lr": 1.10062893081761e-06, "epoch": 0.044549266247379454, "percentage": 0.22, "elapsed_time": "0:00:13", "remaining_time": "1:42:22", "throughput": 3673.29, "total_tokens": 50368}
|
| 18 |
+
{"current_steps": 90, "total_steps": 38160, "loss": 1.1198, "lr": 1.1661425576519918e-06, "epoch": 0.04716981132075472, "percentage": 0.24, "elapsed_time": "0:00:14", "remaining_time": "1:42:24", "throughput": 3718.74, "total_tokens": 54016}
|
| 19 |
+
{"current_steps": 95, "total_steps": 38160, "loss": 0.8774, "lr": 1.2316561844863732e-06, "epoch": 0.04979035639412998, "percentage": 0.25, "elapsed_time": "0:00:15", "remaining_time": "1:42:40", "throughput": 3765.12, "total_tokens": 57888}
|
| 20 |
+
{"current_steps": 100, "total_steps": 38160, "loss": 1.3878, "lr": 1.2971698113207548e-06, "epoch": 0.05241090146750524, "percentage": 0.26, "elapsed_time": "0:00:16", "remaining_time": "1:42:13", "throughput": 3786.92, "total_tokens": 61024}
|
| 21 |
+
{"current_steps": 105, "total_steps": 38160, "loss": 1.126, "lr": 1.3626834381551364e-06, "epoch": 0.055031446540880505, "percentage": 0.28, "elapsed_time": "0:00:16", "remaining_time": "1:42:09", "throughput": 3824.27, "total_tokens": 64672}
|
| 22 |
+
{"current_steps": 110, "total_steps": 38160, "loss": 1.0558, "lr": 1.4281970649895177e-06, "epoch": 0.057651991614255764, "percentage": 0.29, "elapsed_time": "0:00:17", "remaining_time": "1:41:27", "throughput": 3841.89, "total_tokens": 67616}
|
| 23 |
+
{"current_steps": 115, "total_steps": 38160, "loss": 1.0369, "lr": 1.4937106918238995e-06, "epoch": 0.06027253668763103, "percentage": 0.3, "elapsed_time": "0:00:18", "remaining_time": "1:42:00", "throughput": 3850.5, "total_tokens": 71232}
|
| 24 |
+
{"current_steps": 120, "total_steps": 38160, "loss": 0.8856, "lr": 1.559224318658281e-06, "epoch": 0.06289308176100629, "percentage": 0.31, "elapsed_time": "0:00:19", "remaining_time": "1:42:13", "throughput": 3870.18, "total_tokens": 74880}
|
| 25 |
+
{"current_steps": 125, "total_steps": 38160, "loss": 1.2109, "lr": 1.6247379454926625e-06, "epoch": 0.06551362683438156, "percentage": 0.33, "elapsed_time": "0:00:20", "remaining_time": "1:42:27", "throughput": 3882.23, "total_tokens": 78432}
|
| 26 |
+
{"current_steps": 130, "total_steps": 38160, "loss": 1.0909, "lr": 1.690251572327044e-06, "epoch": 0.06813417190775681, "percentage": 0.34, "elapsed_time": "0:00:20", "remaining_time": "1:41:51", "throughput": 3881.41, "total_tokens": 81088}
|
| 27 |
+
{"current_steps": 135, "total_steps": 38160, "loss": 1.0198, "lr": 1.7557651991614257e-06, "epoch": 0.07075471698113207, "percentage": 0.35, "elapsed_time": "0:00:21", "remaining_time": "1:41:58", "throughput": 3908.49, "total_tokens": 84896}
|
| 28 |
+
{"current_steps": 140, "total_steps": 38160, "loss": 1.2627, "lr": 1.821278825995807e-06, "epoch": 0.07337526205450734, "percentage": 0.37, "elapsed_time": "0:00:22", "remaining_time": "1:42:32", "throughput": 3917.03, "total_tokens": 88736}
|
| 29 |
+
{"current_steps": 145, "total_steps": 38160, "loss": 1.5872, "lr": 1.8867924528301887e-06, "epoch": 0.0759958071278826, "percentage": 0.38, "elapsed_time": "0:00:23", "remaining_time": "1:42:42", "throughput": 3923.51, "total_tokens": 92224}
|
| 30 |
+
{"current_steps": 150, "total_steps": 38160, "loss": 1.3305, "lr": 1.9523060796645703e-06, "epoch": 0.07861635220125786, "percentage": 0.39, "elapsed_time": "0:00:24", "remaining_time": "1:42:23", "throughput": 3925.22, "total_tokens": 95168}
|
| 31 |
+
{"current_steps": 155, "total_steps": 38160, "loss": 0.9558, "lr": 2.017819706498952e-06, "epoch": 0.08123689727463312, "percentage": 0.41, "elapsed_time": "0:00:25", "remaining_time": "1:42:26", "throughput": 3948.09, "total_tokens": 98976}
|
| 32 |
+
{"current_steps": 160, "total_steps": 38160, "loss": 0.9743, "lr": 2.0833333333333334e-06, "epoch": 0.08385744234800839, "percentage": 0.42, "elapsed_time": "0:00:25", "remaining_time": "1:42:08", "throughput": 3959.78, "total_tokens": 102176}
|
| 33 |
+
{"current_steps": 165, "total_steps": 38160, "loss": 0.949, "lr": 2.148846960167715e-06, "epoch": 0.08647798742138364, "percentage": 0.43, "elapsed_time": "0:00:26", "remaining_time": "1:42:04", "throughput": 3979.02, "total_tokens": 105824}
|
| 34 |
+
{"current_steps": 170, "total_steps": 38160, "loss": 1.1178, "lr": 2.2143605870020966e-06, "epoch": 0.08909853249475891, "percentage": 0.45, "elapsed_time": "0:00:27", "remaining_time": "1:41:37", "throughput": 3976.71, "total_tokens": 108512}
|
| 35 |
+
{"current_steps": 175, "total_steps": 38160, "loss": 0.9909, "lr": 2.279874213836478e-06, "epoch": 0.09171907756813417, "percentage": 0.46, "elapsed_time": "0:00:28", "remaining_time": "1:41:27", "throughput": 3988.71, "total_tokens": 111872}
|
| 36 |
+
{"current_steps": 180, "total_steps": 38160, "loss": 1.0426, "lr": 2.34538784067086e-06, "epoch": 0.09433962264150944, "percentage": 0.47, "elapsed_time": "0:00:28", "remaining_time": "1:41:32", "throughput": 4001.64, "total_tokens": 115552}
|
| 37 |
+
{"current_steps": 185, "total_steps": 38160, "loss": 1.239, "lr": 2.410901467505241e-06, "epoch": 0.09696016771488469, "percentage": 0.48, "elapsed_time": "0:00:29", "remaining_time": "1:41:23", "throughput": 4008.3, "total_tokens": 118784}
|
| 38 |
+
{"current_steps": 190, "total_steps": 38160, "loss": 1.0246, "lr": 2.476415094339623e-06, "epoch": 0.09958071278825996, "percentage": 0.5, "elapsed_time": "0:00:30", "remaining_time": "1:41:35", "throughput": 4017.33, "total_tokens": 122528}
|
| 39 |
+
{"current_steps": 195, "total_steps": 38160, "loss": 1.3984, "lr": 2.5419287211740044e-06, "epoch": 0.10220125786163523, "percentage": 0.51, "elapsed_time": "0:00:31", "remaining_time": "1:41:15", "throughput": 4006.68, "total_tokens": 125024}
|
| 40 |
+
{"current_steps": 200, "total_steps": 38160, "loss": 1.2403, "lr": 2.6074423480083857e-06, "epoch": 0.10482180293501048, "percentage": 0.52, "elapsed_time": "0:00:31", "remaining_time": "1:40:56", "throughput": 4014.29, "total_tokens": 128096}
|
| 41 |
+
{"current_steps": 205, "total_steps": 38160, "loss": 1.5496, "lr": 2.6729559748427675e-06, "epoch": 0.10744234800838574, "percentage": 0.54, "elapsed_time": "0:00:32", "remaining_time": "1:40:32", "throughput": 4005.18, "total_tokens": 130496}
|
| 42 |
+
{"current_steps": 210, "total_steps": 38160, "loss": 1.2499, "lr": 2.738469601677149e-06, "epoch": 0.11006289308176101, "percentage": 0.55, "elapsed_time": "0:00:33", "remaining_time": "1:40:15", "throughput": 3999.84, "total_tokens": 133152}
|
| 43 |
+
{"current_steps": 215, "total_steps": 38160, "loss": 1.4203, "lr": 2.8039832285115303e-06, "epoch": 0.11268343815513626, "percentage": 0.56, "elapsed_time": "0:00:34", "remaining_time": "1:40:06", "throughput": 4007.43, "total_tokens": 136384}
|
| 44 |
+
{"current_steps": 220, "total_steps": 38160, "loss": 1.2109, "lr": 2.869496855345912e-06, "epoch": 0.11530398322851153, "percentage": 0.58, "elapsed_time": "0:00:34", "remaining_time": "1:39:55", "throughput": 4011.13, "total_tokens": 139456}
|
| 45 |
+
{"current_steps": 225, "total_steps": 38160, "loss": 1.4333, "lr": 2.935010482180294e-06, "epoch": 0.1179245283018868, "percentage": 0.59, "elapsed_time": "0:00:35", "remaining_time": "1:39:52", "throughput": 4018.2, "total_tokens": 142816}
|
| 46 |
+
{"current_steps": 230, "total_steps": 38160, "loss": 1.2697, "lr": 3.0005241090146753e-06, "epoch": 0.12054507337526206, "percentage": 0.6, "elapsed_time": "0:00:36", "remaining_time": "1:39:38", "throughput": 4018.98, "total_tokens": 145696}
|
| 47 |
+
{"current_steps": 235, "total_steps": 38160, "loss": 1.2018, "lr": 3.0660377358490567e-06, "epoch": 0.12316561844863731, "percentage": 0.62, "elapsed_time": "0:00:37", "remaining_time": "1:39:35", "throughput": 4025.05, "total_tokens": 149024}
|
| 48 |
+
{"current_steps": 240, "total_steps": 38160, "loss": 1.3744, "lr": 3.131551362683438e-06, "epoch": 0.12578616352201258, "percentage": 0.63, "elapsed_time": "0:00:37", "remaining_time": "1:39:24", "throughput": 4021.97, "total_tokens": 151840}
|
| 49 |
+
{"current_steps": 245, "total_steps": 38160, "loss": 1.1831, "lr": 3.1970649895178203e-06, "epoch": 0.12840670859538783, "percentage": 0.64, "elapsed_time": "0:00:38", "remaining_time": "1:39:26", "throughput": 4032.09, "total_tokens": 155456}
|
| 50 |
+
{"current_steps": 250, "total_steps": 38160, "loss": 1.2365, "lr": 3.2625786163522012e-06, "epoch": 0.1310272536687631, "percentage": 0.66, "elapsed_time": "0:00:39", "remaining_time": "1:39:20", "throughput": 4033.4, "total_tokens": 158528}
|
| 51 |
+
{"current_steps": 255, "total_steps": 38160, "loss": 0.9354, "lr": 3.3280922431865826e-06, "epoch": 0.13364779874213836, "percentage": 0.67, "elapsed_time": "0:00:41", "remaining_time": "1:41:37", "throughput": 4059.08, "total_tokens": 166496}
|
| 52 |
+
{"current_steps": 260, "total_steps": 38160, "loss": 1.0281, "lr": 3.393605870020965e-06, "epoch": 0.13626834381551362, "percentage": 0.68, "elapsed_time": "0:00:41", "remaining_time": "1:41:32", "throughput": 4057.11, "total_tokens": 169568}
|
| 53 |
+
{"current_steps": 265, "total_steps": 38160, "loss": 1.1861, "lr": 3.459119496855346e-06, "epoch": 0.1388888888888889, "percentage": 0.69, "elapsed_time": "0:00:42", "remaining_time": "1:41:22", "throughput": 4060.23, "total_tokens": 172704}
|
| 54 |
+
{"current_steps": 270, "total_steps": 38160, "loss": 1.2347, "lr": 3.524633123689727e-06, "epoch": 0.14150943396226415, "percentage": 0.71, "elapsed_time": "0:00:43", "remaining_time": "1:41:28", "throughput": 4067.68, "total_tokens": 176480}
|
| 55 |
+
{"current_steps": 275, "total_steps": 38160, "loss": 1.0775, "lr": 3.5901467505241094e-06, "epoch": 0.1441299790356394, "percentage": 0.72, "elapsed_time": "0:00:44", "remaining_time": "1:42:03", "throughput": 4081.01, "total_tokens": 181408}
|
| 56 |
+
{"current_steps": 280, "total_steps": 38160, "loss": 1.2125, "lr": 3.6556603773584908e-06, "epoch": 0.14675052410901468, "percentage": 0.73, "elapsed_time": "0:00:45", "remaining_time": "1:41:55", "throughput": 4086.71, "total_tokens": 184736}
|
| 57 |
+
{"current_steps": 285, "total_steps": 38160, "loss": 1.1424, "lr": 3.7211740041928726e-06, "epoch": 0.14937106918238993, "percentage": 0.75, "elapsed_time": "0:00:46", "remaining_time": "1:41:54", "throughput": 4094.04, "total_tokens": 188352}
|
| 58 |
+
{"current_steps": 290, "total_steps": 38160, "loss": 1.0782, "lr": 3.786687631027254e-06, "epoch": 0.1519916142557652, "percentage": 0.76, "elapsed_time": "0:00:47", "remaining_time": "1:42:38", "throughput": 4100.82, "total_tokens": 193408}
|
| 59 |
+
{"current_steps": 295, "total_steps": 38160, "loss": 1.0261, "lr": 3.852201257861635e-06, "epoch": 0.15461215932914046, "percentage": 0.77, "elapsed_time": "0:00:47", "remaining_time": "1:42:27", "throughput": 4100.35, "total_tokens": 196384}
|
| 60 |
+
{"current_steps": 300, "total_steps": 38160, "loss": 1.2104, "lr": 3.917714884696017e-06, "epoch": 0.15723270440251572, "percentage": 0.79, "elapsed_time": "0:00:48", "remaining_time": "1:42:16", "throughput": 4100.02, "total_tokens": 199360}
|
| 61 |
+
{"current_steps": 305, "total_steps": 38160, "loss": 1.087, "lr": 3.9832285115303985e-06, "epoch": 0.159853249475891, "percentage": 0.8, "elapsed_time": "0:00:49", "remaining_time": "1:42:19", "throughput": 4100.71, "total_tokens": 202848}
|
| 62 |
+
{"current_steps": 310, "total_steps": 38160, "loss": 0.9271, "lr": 4.04874213836478e-06, "epoch": 0.16247379454926625, "percentage": 0.81, "elapsed_time": "0:00:50", "remaining_time": "1:42:30", "throughput": 4111.41, "total_tokens": 207104}
|
| 63 |
+
{"current_steps": 315, "total_steps": 38160, "loss": 1.3985, "lr": 4.114255765199162e-06, "epoch": 0.1650943396226415, "percentage": 0.83, "elapsed_time": "0:00:51", "remaining_time": "1:42:12", "throughput": 4106.11, "total_tokens": 209600}
|
| 64 |
+
{"current_steps": 320, "total_steps": 38160, "loss": 1.2418, "lr": 4.1797693920335435e-06, "epoch": 0.16771488469601678, "percentage": 0.84, "elapsed_time": "0:00:51", "remaining_time": "1:42:17", "throughput": 4106.59, "total_tokens": 213152}
|
| 65 |
+
{"current_steps": 325, "total_steps": 38160, "loss": 1.4177, "lr": 4.245283018867925e-06, "epoch": 0.17033542976939203, "percentage": 0.85, "elapsed_time": "0:00:52", "remaining_time": "1:42:01", "throughput": 4100.2, "total_tokens": 215616}
|
| 66 |
+
{"current_steps": 330, "total_steps": 38160, "loss": 1.1862, "lr": 4.310796645702306e-06, "epoch": 0.17295597484276728, "percentage": 0.86, "elapsed_time": "0:00:53", "remaining_time": "1:42:01", "throughput": 4092.65, "total_tokens": 218528}
|
| 67 |
+
{"current_steps": 335, "total_steps": 38160, "loss": 1.0566, "lr": 4.376310272536688e-06, "epoch": 0.17557651991614256, "percentage": 0.88, "elapsed_time": "0:00:54", "remaining_time": "1:41:56", "throughput": 4095.07, "total_tokens": 221824}
|
| 68 |
+
{"current_steps": 340, "total_steps": 38160, "loss": 1.0487, "lr": 4.441823899371069e-06, "epoch": 0.17819706498951782, "percentage": 0.89, "elapsed_time": "0:00:54", "remaining_time": "1:41:56", "throughput": 4097.08, "total_tokens": 225280}
|
| 69 |
+
{"current_steps": 345, "total_steps": 38160, "loss": 0.987, "lr": 4.507337526205451e-06, "epoch": 0.18081761006289307, "percentage": 0.9, "elapsed_time": "0:00:56", "remaining_time": "1:42:44", "throughput": 4105.75, "total_tokens": 230912}
|
| 70 |
+
{"current_steps": 350, "total_steps": 38160, "loss": 1.146, "lr": 4.572851153039833e-06, "epoch": 0.18343815513626835, "percentage": 0.92, "elapsed_time": "0:00:57", "remaining_time": "1:42:45", "throughput": 4110.61, "total_tokens": 234592}
|
| 71 |
+
{"current_steps": 355, "total_steps": 38160, "loss": 0.9917, "lr": 4.638364779874214e-06, "epoch": 0.1860587002096436, "percentage": 0.93, "elapsed_time": "0:00:57", "remaining_time": "1:42:37", "throughput": 4109.07, "total_tokens": 237600}
|
| 72 |
+
{"current_steps": 360, "total_steps": 38160, "loss": 1.1355, "lr": 4.703878406708595e-06, "epoch": 0.18867924528301888, "percentage": 0.94, "elapsed_time": "0:00:58", "remaining_time": "1:42:30", "throughput": 4116.03, "total_tokens": 241088}
|
| 73 |
+
{"current_steps": 365, "total_steps": 38160, "loss": 1.2241, "lr": 4.769392033542977e-06, "epoch": 0.19129979035639413, "percentage": 0.96, "elapsed_time": "0:00:59", "remaining_time": "1:42:15", "throughput": 4109.57, "total_tokens": 243520}
|
| 74 |
+
{"current_steps": 370, "total_steps": 38160, "loss": 1.3376, "lr": 4.834905660377359e-06, "epoch": 0.19392033542976939, "percentage": 0.97, "elapsed_time": "0:01:00", "remaining_time": "1:42:20", "throughput": 4115.92, "total_tokens": 247456}
|
| 75 |
+
{"current_steps": 375, "total_steps": 38160, "loss": 1.1097, "lr": 4.90041928721174e-06, "epoch": 0.19654088050314467, "percentage": 0.98, "elapsed_time": "0:01:00", "remaining_time": "1:42:16", "throughput": 4117.91, "total_tokens": 250784}
|
| 76 |
+
{"current_steps": 380, "total_steps": 38160, "loss": 1.0079, "lr": 4.965932914046122e-06, "epoch": 0.19916142557651992, "percentage": 1.0, "elapsed_time": "0:01:01", "remaining_time": "1:42:25", "throughput": 4126.26, "total_tokens": 255040}
|
| 77 |
+
{"current_steps": 385, "total_steps": 38160, "loss": 1.181, "lr": 5.031446540880504e-06, "epoch": 0.20178197064989517, "percentage": 1.01, "elapsed_time": "0:01:02", "remaining_time": "1:42:20", "throughput": 4126.27, "total_tokens": 258240}
|
| 78 |
+
{"current_steps": 390, "total_steps": 38160, "loss": 1.016, "lr": 5.096960167714885e-06, "epoch": 0.20440251572327045, "percentage": 1.02, "elapsed_time": "0:01:03", "remaining_time": "1:42:12", "throughput": 4123.94, "total_tokens": 261152}
|
| 79 |
+
{"current_steps": 395, "total_steps": 38160, "loss": 1.346, "lr": 5.162473794549266e-06, "epoch": 0.2070230607966457, "percentage": 1.04, "elapsed_time": "0:01:04", "remaining_time": "1:42:10", "throughput": 4125.82, "total_tokens": 264544}
|
| 80 |
+
{"current_steps": 400, "total_steps": 38160, "loss": 1.2918, "lr": 5.227987421383648e-06, "epoch": 0.20964360587002095, "percentage": 1.05, "elapsed_time": "0:01:04", "remaining_time": "1:41:56", "throughput": 4122.92, "total_tokens": 267136}
|
| 81 |
+
{"current_steps": 405, "total_steps": 38160, "loss": 1.2002, "lr": 5.2935010482180295e-06, "epoch": 0.21226415094339623, "percentage": 1.06, "elapsed_time": "0:01:05", "remaining_time": "1:41:57", "throughput": 4121.45, "total_tokens": 270464}
|
| 82 |
+
{"current_steps": 410, "total_steps": 38160, "loss": 0.9004, "lr": 5.359014675052411e-06, "epoch": 0.2148846960167715, "percentage": 1.07, "elapsed_time": "0:01:06", "remaining_time": "1:42:02", "throughput": 4128.21, "total_tokens": 274528}
|
| 83 |
+
{"current_steps": 415, "total_steps": 38160, "loss": 1.0571, "lr": 5.424528301886793e-06, "epoch": 0.21750524109014674, "percentage": 1.09, "elapsed_time": "0:01:07", "remaining_time": "1:41:52", "throughput": 4127.04, "total_tokens": 277376}
|
| 84 |
+
{"current_steps": 420, "total_steps": 38160, "loss": 1.2608, "lr": 5.4900419287211744e-06, "epoch": 0.22012578616352202, "percentage": 1.1, "elapsed_time": "0:01:07", "remaining_time": "1:41:44", "throughput": 4115.99, "total_tokens": 279616}
|
| 85 |
+
{"current_steps": 425, "total_steps": 38160, "loss": 1.1058, "lr": 5.555555555555556e-06, "epoch": 0.22274633123689727, "percentage": 1.11, "elapsed_time": "0:01:08", "remaining_time": "1:41:37", "throughput": 4115.72, "total_tokens": 282656}
|
| 86 |
+
{"current_steps": 430, "total_steps": 38160, "loss": 1.089, "lr": 5.621069182389937e-06, "epoch": 0.22536687631027252, "percentage": 1.13, "elapsed_time": "0:01:09", "remaining_time": "1:41:26", "throughput": 4117.35, "total_tokens": 285600}
|
| 87 |
+
{"current_steps": 435, "total_steps": 38160, "loss": 0.8637, "lr": 5.686582809224319e-06, "epoch": 0.2279874213836478, "percentage": 1.14, "elapsed_time": "0:01:10", "remaining_time": "1:41:33", "throughput": 4121.09, "total_tokens": 289568}
|
| 88 |
+
{"current_steps": 440, "total_steps": 38160, "loss": 1.1407, "lr": 5.752096436058701e-06, "epoch": 0.23060796645702306, "percentage": 1.15, "elapsed_time": "0:01:11", "remaining_time": "1:41:28", "throughput": 4122.35, "total_tokens": 292768}
|
| 89 |
+
{"current_steps": 445, "total_steps": 38160, "loss": 1.2331, "lr": 5.817610062893082e-06, "epoch": 0.23322851153039834, "percentage": 1.17, "elapsed_time": "0:01:11", "remaining_time": "1:41:15", "throughput": 4121.29, "total_tokens": 295456}
|
| 90 |
+
{"current_steps": 450, "total_steps": 38160, "loss": 1.1639, "lr": 5.8831236897274636e-06, "epoch": 0.2358490566037736, "percentage": 1.18, "elapsed_time": "0:01:12", "remaining_time": "1:41:24", "throughput": 4124.79, "total_tokens": 299488}
|
| 91 |
+
{"current_steps": 455, "total_steps": 38160, "loss": 1.1761, "lr": 5.948637316561846e-06, "epoch": 0.23846960167714884, "percentage": 1.19, "elapsed_time": "0:01:13", "remaining_time": "1:41:21", "throughput": 4128.28, "total_tokens": 302976}
|
| 92 |
+
{"current_steps": 460, "total_steps": 38160, "loss": 1.0252, "lr": 6.014150943396227e-06, "epoch": 0.24109014675052412, "percentage": 1.21, "elapsed_time": "0:01:14", "remaining_time": "1:41:18", "throughput": 4133.28, "total_tokens": 306560}
|
| 93 |
+
{"current_steps": 465, "total_steps": 38160, "loss": 1.049, "lr": 6.079664570230608e-06, "epoch": 0.24371069182389937, "percentage": 1.22, "elapsed_time": "0:01:14", "remaining_time": "1:41:10", "throughput": 4133.26, "total_tokens": 309536}
|
| 94 |
+
{"current_steps": 470, "total_steps": 38160, "loss": 0.9718, "lr": 6.14517819706499e-06, "epoch": 0.24633123689727462, "percentage": 1.23, "elapsed_time": "0:01:15", "remaining_time": "1:41:01", "throughput": 4134.99, "total_tokens": 312576}
|
| 95 |
+
{"current_steps": 475, "total_steps": 38160, "loss": 1.0296, "lr": 6.210691823899371e-06, "epoch": 0.2489517819706499, "percentage": 1.24, "elapsed_time": "0:01:16", "remaining_time": "1:40:52", "throughput": 4136.97, "total_tokens": 315616}
|
| 96 |
+
{"current_steps": 480, "total_steps": 38160, "loss": 0.9917, "lr": 6.2762054507337535e-06, "epoch": 0.25157232704402516, "percentage": 1.26, "elapsed_time": "0:01:17", "remaining_time": "1:40:48", "throughput": 4141.77, "total_tokens": 319136}
|
| 97 |
+
{"current_steps": 485, "total_steps": 38160, "loss": 1.7992, "lr": 6.341719077568134e-06, "epoch": 0.25419287211740044, "percentage": 1.27, "elapsed_time": "0:01:17", "remaining_time": "1:40:37", "throughput": 4134.68, "total_tokens": 321376}
|
| 98 |
+
{"current_steps": 490, "total_steps": 38160, "loss": 1.0498, "lr": 6.407232704402516e-06, "epoch": 0.25681341719077566, "percentage": 1.28, "elapsed_time": "0:01:18", "remaining_time": "1:40:35", "throughput": 4138.89, "total_tokens": 324928}
|
| 99 |
+
{"current_steps": 495, "total_steps": 38160, "loss": 1.1065, "lr": 6.472746331236898e-06, "epoch": 0.25943396226415094, "percentage": 1.3, "elapsed_time": "0:01:19", "remaining_time": "1:40:43", "throughput": 4145.26, "total_tokens": 329248}
|
| 100 |
+
{"current_steps": 500, "total_steps": 38160, "loss": 1.1709, "lr": 6.538259958071278e-06, "epoch": 0.2620545073375262, "percentage": 1.31, "elapsed_time": "0:01:20", "remaining_time": "1:40:38", "throughput": 4144.62, "total_tokens": 332288}
|
| 101 |
+
{"current_steps": 505, "total_steps": 38160, "loss": 1.2378, "lr": 6.60377358490566e-06, "epoch": 0.26467505241090145, "percentage": 1.32, "elapsed_time": "0:01:20", "remaining_time": "1:40:30", "throughput": 4138.91, "total_tokens": 334752}
|
| 102 |
+
{"current_steps": 510, "total_steps": 38160, "loss": 1.1834, "lr": 6.669287211740043e-06, "epoch": 0.2672955974842767, "percentage": 1.34, "elapsed_time": "0:01:21", "remaining_time": "1:40:28", "throughput": 4137.04, "total_tokens": 337856}
|
| 103 |
+
{"current_steps": 515, "total_steps": 38160, "loss": 1.0229, "lr": 6.734800838574423e-06, "epoch": 0.269916142557652, "percentage": 1.35, "elapsed_time": "0:01:22", "remaining_time": "1:40:31", "throughput": 4142.3, "total_tokens": 341792}
|
| 104 |
+
{"current_steps": 520, "total_steps": 38160, "loss": 1.246, "lr": 6.800314465408805e-06, "epoch": 0.27253668763102723, "percentage": 1.36, "elapsed_time": "0:01:23", "remaining_time": "1:40:28", "throughput": 4139.86, "total_tokens": 344768}
|
| 105 |
+
{"current_steps": 525, "total_steps": 38160, "loss": 1.0913, "lr": 6.865828092243188e-06, "epoch": 0.2751572327044025, "percentage": 1.38, "elapsed_time": "0:01:23", "remaining_time": "1:40:19", "throughput": 4136.41, "total_tokens": 347360}
|
| 106 |
+
{"current_steps": 530, "total_steps": 38160, "loss": 1.1348, "lr": 6.931341719077568e-06, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:01:24", "remaining_time": "1:40:15", "throughput": 4138.13, "total_tokens": 350592}
|
| 107 |
+
{"current_steps": 535, "total_steps": 38160, "loss": 1.0046, "lr": 6.9968553459119495e-06, "epoch": 0.280398322851153, "percentage": 1.4, "elapsed_time": "0:01:25", "remaining_time": "1:40:11", "throughput": 4136.14, "total_tokens": 353568}
|
| 108 |
+
{"current_steps": 540, "total_steps": 38160, "loss": 1.2658, "lr": 7.062368972746332e-06, "epoch": 0.2830188679245283, "percentage": 1.42, "elapsed_time": "0:01:26", "remaining_time": "1:40:06", "throughput": 4132.93, "total_tokens": 356320}
|
| 109 |
+
{"current_steps": 545, "total_steps": 38160, "loss": 0.8918, "lr": 7.127882599580712e-06, "epoch": 0.2856394129979036, "percentage": 1.43, "elapsed_time": "0:01:27", "remaining_time": "1:40:06", "throughput": 4136.2, "total_tokens": 359968}
|
| 110 |
+
{"current_steps": 550, "total_steps": 38160, "loss": 0.9517, "lr": 7.1933962264150945e-06, "epoch": 0.2882599580712788, "percentage": 1.44, "elapsed_time": "0:01:27", "remaining_time": "1:40:03", "throughput": 4132.12, "total_tokens": 362752}
|
| 111 |
+
{"current_steps": 555, "total_steps": 38160, "loss": 1.0871, "lr": 7.258909853249477e-06, "epoch": 0.2908805031446541, "percentage": 1.45, "elapsed_time": "0:01:28", "remaining_time": "1:39:54", "throughput": 4129.39, "total_tokens": 365312}
|
| 112 |
+
{"current_steps": 560, "total_steps": 38160, "loss": 0.9237, "lr": 7.324423480083858e-06, "epoch": 0.29350104821802936, "percentage": 1.47, "elapsed_time": "0:01:29", "remaining_time": "1:39:55", "throughput": 4131.39, "total_tokens": 368896}
|
| 113 |
+
{"current_steps": 565, "total_steps": 38160, "loss": 1.0478, "lr": 7.3899371069182395e-06, "epoch": 0.29612159329140464, "percentage": 1.48, "elapsed_time": "0:01:29", "remaining_time": "1:39:45", "throughput": 4131.52, "total_tokens": 371648}
|
| 114 |
+
{"current_steps": 570, "total_steps": 38160, "loss": 1.0252, "lr": 7.455450733752621e-06, "epoch": 0.29874213836477986, "percentage": 1.49, "elapsed_time": "0:01:30", "remaining_time": "1:39:39", "throughput": 4133.95, "total_tokens": 374848}
|
| 115 |
+
{"current_steps": 575, "total_steps": 38160, "loss": 1.2862, "lr": 7.520964360587003e-06, "epoch": 0.30136268343815514, "percentage": 1.51, "elapsed_time": "0:01:31", "remaining_time": "1:39:31", "throughput": 4128.57, "total_tokens": 377184}
|
| 116 |
+
{"current_steps": 580, "total_steps": 38160, "loss": 0.9097, "lr": 7.586477987421384e-06, "epoch": 0.3039832285115304, "percentage": 1.52, "elapsed_time": "0:01:32", "remaining_time": "1:39:37", "throughput": 4135.26, "total_tokens": 381504}
|
| 117 |
+
{"current_steps": 585, "total_steps": 38160, "loss": 0.9704, "lr": 7.651991614255765e-06, "epoch": 0.30660377358490565, "percentage": 1.53, "elapsed_time": "0:01:32", "remaining_time": "1:39:32", "throughput": 4136.67, "total_tokens": 384672}
|
| 118 |
+
{"current_steps": 590, "total_steps": 38160, "loss": 0.9229, "lr": 7.717505241090148e-06, "epoch": 0.30922431865828093, "percentage": 1.55, "elapsed_time": "0:01:34", "remaining_time": "1:39:46", "throughput": 4141.58, "total_tokens": 389376}
|
| 119 |
+
{"current_steps": 595, "total_steps": 38160, "loss": 0.9882, "lr": 7.783018867924528e-06, "epoch": 0.3118448637316562, "percentage": 1.56, "elapsed_time": "0:01:34", "remaining_time": "1:39:42", "throughput": 4142.47, "total_tokens": 392512}
|
| 120 |
+
{"current_steps": 600, "total_steps": 38160, "loss": 0.9624, "lr": 7.848532494758911e-06, "epoch": 0.31446540880503143, "percentage": 1.57, "elapsed_time": "0:01:35", "remaining_time": "1:39:51", "throughput": 4146.82, "total_tokens": 396864}
|
| 121 |
+
{"current_steps": 605, "total_steps": 38160, "loss": 1.0595, "lr": 7.914046121593292e-06, "epoch": 0.3170859538784067, "percentage": 1.59, "elapsed_time": "0:01:36", "remaining_time": "1:39:42", "throughput": 4145.3, "total_tokens": 399520}
|
| 122 |
+
{"current_steps": 610, "total_steps": 38160, "loss": 1.1716, "lr": 7.979559748427674e-06, "epoch": 0.319706498951782, "percentage": 1.6, "elapsed_time": "0:01:37", "remaining_time": "1:39:39", "throughput": 4144.14, "total_tokens": 402560}
|
| 123 |
+
{"current_steps": 615, "total_steps": 38160, "loss": 1.0467, "lr": 8.045073375262055e-06, "epoch": 0.3223270440251572, "percentage": 1.61, "elapsed_time": "0:01:37", "remaining_time": "1:39:38", "throughput": 4148.35, "total_tokens": 406240}
|
| 124 |
+
{"current_steps": 620, "total_steps": 38160, "loss": 1.0783, "lr": 8.110587002096436e-06, "epoch": 0.3249475890985325, "percentage": 1.62, "elapsed_time": "0:01:38", "remaining_time": "1:39:31", "throughput": 4146.77, "total_tokens": 408960}
|
| 125 |
+
{"current_steps": 625, "total_steps": 38160, "loss": 1.1026, "lr": 8.176100628930818e-06, "epoch": 0.3275681341719078, "percentage": 1.64, "elapsed_time": "0:01:39", "remaining_time": "1:39:28", "throughput": 4147.58, "total_tokens": 412224}
|
| 126 |
+
{"current_steps": 630, "total_steps": 38160, "loss": 0.8968, "lr": 8.241614255765199e-06, "epoch": 0.330188679245283, "percentage": 1.65, "elapsed_time": "0:01:40", "remaining_time": "1:39:25", "throughput": 4147.39, "total_tokens": 415296}
|
| 127 |
+
{"current_steps": 635, "total_steps": 38160, "loss": 1.1176, "lr": 8.307127882599582e-06, "epoch": 0.3328092243186583, "percentage": 1.66, "elapsed_time": "0:01:40", "remaining_time": "1:39:16", "throughput": 4141.96, "total_tokens": 417504}
|
| 128 |
+
{"current_steps": 640, "total_steps": 38160, "loss": 0.9334, "lr": 8.372641509433962e-06, "epoch": 0.33542976939203356, "percentage": 1.68, "elapsed_time": "0:01:41", "remaining_time": "1:39:12", "throughput": 4139.54, "total_tokens": 420288}
|
| 129 |
+
{"current_steps": 645, "total_steps": 38160, "loss": 1.1693, "lr": 8.438155136268345e-06, "epoch": 0.3380503144654088, "percentage": 1.69, "elapsed_time": "0:01:42", "remaining_time": "1:39:04", "throughput": 4134.39, "total_tokens": 422560}
|
| 130 |
+
{"current_steps": 650, "total_steps": 38160, "loss": 1.1429, "lr": 8.503668763102726e-06, "epoch": 0.34067085953878407, "percentage": 1.7, "elapsed_time": "0:01:42", "remaining_time": "1:38:59", "throughput": 4133.79, "total_tokens": 425472}
|
| 131 |
+
{"current_steps": 655, "total_steps": 38160, "loss": 0.9116, "lr": 8.569182389937106e-06, "epoch": 0.34329140461215935, "percentage": 1.72, "elapsed_time": "0:01:43", "remaining_time": "1:38:56", "throughput": 4138.09, "total_tokens": 429056}
|
| 132 |
+
{"current_steps": 660, "total_steps": 38160, "loss": 0.8381, "lr": 8.634696016771489e-06, "epoch": 0.34591194968553457, "percentage": 1.73, "elapsed_time": "0:01:44", "remaining_time": "1:38:59", "throughput": 4142.45, "total_tokens": 433024}
|
| 133 |
+
{"current_steps": 665, "total_steps": 38160, "loss": 0.9827, "lr": 8.70020964360587e-06, "epoch": 0.34853249475890985, "percentage": 1.74, "elapsed_time": "0:01:45", "remaining_time": "1:38:51", "throughput": 4142.21, "total_tokens": 435776}
|
| 134 |
+
{"current_steps": 670, "total_steps": 38160, "loss": 1.0833, "lr": 8.765723270440252e-06, "epoch": 0.35115303983228513, "percentage": 1.76, "elapsed_time": "0:01:45", "remaining_time": "1:38:46", "throughput": 4139.2, "total_tokens": 438432}
|
| 135 |
+
{"current_steps": 675, "total_steps": 38160, "loss": 0.8643, "lr": 8.831236897274633e-06, "epoch": 0.35377358490566035, "percentage": 1.77, "elapsed_time": "0:01:46", "remaining_time": "1:38:49", "throughput": 4143.55, "total_tokens": 442400}
|
| 136 |
+
{"current_steps": 680, "total_steps": 38160, "loss": 0.998, "lr": 8.896750524109015e-06, "epoch": 0.35639412997903563, "percentage": 1.78, "elapsed_time": "0:01:47", "remaining_time": "1:38:49", "throughput": 4144.77, "total_tokens": 445888}
|
| 137 |
+
{"current_steps": 685, "total_steps": 38160, "loss": 0.9173, "lr": 8.962264150943396e-06, "epoch": 0.3590146750524109, "percentage": 1.8, "elapsed_time": "0:01:48", "remaining_time": "1:38:46", "throughput": 4143.54, "total_tokens": 448864}
|
| 138 |
+
{"current_steps": 690, "total_steps": 38160, "loss": 1.0871, "lr": 9.027777777777777e-06, "epoch": 0.36163522012578614, "percentage": 1.81, "elapsed_time": "0:01:49", "remaining_time": "1:38:47", "throughput": 4146.79, "total_tokens": 452640}
|
| 139 |
+
{"current_steps": 695, "total_steps": 38160, "loss": 1.0848, "lr": 9.09329140461216e-06, "epoch": 0.3642557651991614, "percentage": 1.82, "elapsed_time": "0:01:49", "remaining_time": "1:38:43", "throughput": 4143.12, "total_tokens": 455296}
|
| 140 |
+
{"current_steps": 700, "total_steps": 38160, "loss": 1.0012, "lr": 9.15880503144654e-06, "epoch": 0.3668763102725367, "percentage": 1.83, "elapsed_time": "0:01:50", "remaining_time": "1:38:42", "throughput": 4137.24, "total_tokens": 457888}
|
| 141 |
+
{"current_steps": 705, "total_steps": 38160, "loss": 0.888, "lr": 9.224318658280923e-06, "epoch": 0.3694968553459119, "percentage": 1.85, "elapsed_time": "0:01:51", "remaining_time": "1:38:43", "throughput": 4140.86, "total_tokens": 461664}
|
| 142 |
+
{"current_steps": 710, "total_steps": 38160, "loss": 0.9659, "lr": 9.289832285115305e-06, "epoch": 0.3721174004192872, "percentage": 1.86, "elapsed_time": "0:01:52", "remaining_time": "1:38:36", "throughput": 4140.07, "total_tokens": 464352}
|
| 143 |
+
{"current_steps": 715, "total_steps": 38160, "loss": 0.9356, "lr": 9.355345911949686e-06, "epoch": 0.3747379454926625, "percentage": 1.87, "elapsed_time": "0:01:53", "remaining_time": "1:38:40", "throughput": 4142.28, "total_tokens": 468256}
|
| 144 |
+
{"current_steps": 720, "total_steps": 38160, "loss": 1.0206, "lr": 9.420859538784067e-06, "epoch": 0.37735849056603776, "percentage": 1.89, "elapsed_time": "0:01:53", "remaining_time": "1:38:37", "throughput": 4139.82, "total_tokens": 471104}
|
| 145 |
+
{"current_steps": 725, "total_steps": 38160, "loss": 1.1537, "lr": 9.486373165618449e-06, "epoch": 0.379979035639413, "percentage": 1.9, "elapsed_time": "0:01:54", "remaining_time": "1:38:34", "throughput": 4135.66, "total_tokens": 473696}
|
| 146 |
+
{"current_steps": 730, "total_steps": 38160, "loss": 0.8547, "lr": 9.551886792452832e-06, "epoch": 0.38259958071278827, "percentage": 1.91, "elapsed_time": "0:01:55", "remaining_time": "1:38:32", "throughput": 4132.49, "total_tokens": 476512}
|
| 147 |
+
{"current_steps": 735, "total_steps": 38160, "loss": 0.8992, "lr": 9.617400419287211e-06, "epoch": 0.38522012578616355, "percentage": 1.93, "elapsed_time": "0:01:56", "remaining_time": "1:38:32", "throughput": 4134.99, "total_tokens": 480128}
|
| 148 |
+
{"current_steps": 740, "total_steps": 38160, "loss": 0.9139, "lr": 9.682914046121595e-06, "epoch": 0.38784067085953877, "percentage": 1.94, "elapsed_time": "0:01:56", "remaining_time": "1:38:34", "throughput": 4136.43, "total_tokens": 483808}
|
| 149 |
+
{"current_steps": 745, "total_steps": 38160, "loss": 1.1133, "lr": 9.748427672955976e-06, "epoch": 0.39046121593291405, "percentage": 1.95, "elapsed_time": "0:01:57", "remaining_time": "1:38:34", "throughput": 4128.88, "total_tokens": 486240}
|
| 150 |
+
{"current_steps": 750, "total_steps": 38160, "loss": 1.1958, "lr": 9.813941299790357e-06, "epoch": 0.39308176100628933, "percentage": 1.97, "elapsed_time": "0:01:58", "remaining_time": "1:38:32", "throughput": 4120.9, "total_tokens": 488448}
|
| 151 |
+
{"current_steps": 755, "total_steps": 38160, "loss": 0.9657, "lr": 9.879454926624739e-06, "epoch": 0.39570230607966456, "percentage": 1.98, "elapsed_time": "0:01:59", "remaining_time": "1:38:31", "throughput": 4118.53, "total_tokens": 491392}
|
| 152 |
+
{"current_steps": 760, "total_steps": 38160, "loss": 0.8531, "lr": 9.94496855345912e-06, "epoch": 0.39832285115303984, "percentage": 1.99, "elapsed_time": "0:02:00", "remaining_time": "1:38:33", "throughput": 4120.88, "total_tokens": 495232}
|
| 153 |
+
{"current_steps": 765, "total_steps": 38160, "loss": 0.8805, "lr": 1.0010482180293501e-05, "epoch": 0.4009433962264151, "percentage": 2.0, "elapsed_time": "0:02:01", "remaining_time": "1:38:35", "throughput": 4115.63, "total_tokens": 498016}
|
| 154 |
+
{"current_steps": 770, "total_steps": 38160, "loss": 0.8561, "lr": 1.0075995807127883e-05, "epoch": 0.40356394129979034, "percentage": 2.02, "elapsed_time": "0:02:01", "remaining_time": "1:38:32", "throughput": 4115.73, "total_tokens": 501152}
|
| 155 |
+
{"current_steps": 775, "total_steps": 38160, "loss": 0.9297, "lr": 1.0141509433962266e-05, "epoch": 0.4061844863731656, "percentage": 2.03, "elapsed_time": "0:02:02", "remaining_time": "1:38:27", "throughput": 4114.36, "total_tokens": 503872}
|
| 156 |
+
{"current_steps": 780, "total_steps": 38160, "loss": 0.8837, "lr": 1.0207023060796646e-05, "epoch": 0.4088050314465409, "percentage": 2.04, "elapsed_time": "0:02:03", "remaining_time": "1:38:31", "throughput": 4113.06, "total_tokens": 507328}
|
| 157 |
+
{"current_steps": 785, "total_steps": 38160, "loss": 0.7091, "lr": 1.0272536687631027e-05, "epoch": 0.4114255765199161, "percentage": 2.06, "elapsed_time": "0:02:04", "remaining_time": "1:38:30", "throughput": 4115.55, "total_tokens": 510912}
|
| 158 |
+
{"current_steps": 790, "total_steps": 38160, "loss": 0.8577, "lr": 1.033805031446541e-05, "epoch": 0.4140461215932914, "percentage": 2.07, "elapsed_time": "0:02:04", "remaining_time": "1:38:32", "throughput": 4114.56, "total_tokens": 514304}
|
| 159 |
+
{"current_steps": 795, "total_steps": 38160, "loss": 0.874, "lr": 1.040356394129979e-05, "epoch": 0.4166666666666667, "percentage": 2.08, "elapsed_time": "0:02:05", "remaining_time": "1:38:35", "throughput": 4111.39, "total_tokens": 517440}
|
| 160 |
+
{"current_steps": 800, "total_steps": 38160, "loss": 1.1037, "lr": 1.0469077568134173e-05, "epoch": 0.4192872117400419, "percentage": 2.1, "elapsed_time": "0:02:06", "remaining_time": "1:38:32", "throughput": 4110.74, "total_tokens": 520416}
|
| 161 |
+
{"current_steps": 805, "total_steps": 38160, "loss": 1.0693, "lr": 1.0534591194968554e-05, "epoch": 0.4219077568134172, "percentage": 2.11, "elapsed_time": "0:02:07", "remaining_time": "1:38:29", "throughput": 4110.32, "total_tokens": 523456}
|
| 162 |
+
{"current_steps": 810, "total_steps": 38160, "loss": 0.7801, "lr": 1.0600104821802936e-05, "epoch": 0.42452830188679247, "percentage": 2.12, "elapsed_time": "0:02:08", "remaining_time": "1:38:28", "throughput": 4110.96, "total_tokens": 526720}
|
| 163 |
+
{"current_steps": 815, "total_steps": 38160, "loss": 0.7334, "lr": 1.0665618448637317e-05, "epoch": 0.4271488469601677, "percentage": 2.14, "elapsed_time": "0:02:08", "remaining_time": "1:38:30", "throughput": 4111.31, "total_tokens": 530272}
|
| 164 |
+
{"current_steps": 820, "total_steps": 38160, "loss": 0.9566, "lr": 1.0731132075471698e-05, "epoch": 0.429769392033543, "percentage": 2.15, "elapsed_time": "0:02:09", "remaining_time": "1:38:32", "throughput": 4108.34, "total_tokens": 533408}
|
| 165 |
+
{"current_steps": 825, "total_steps": 38160, "loss": 1.0542, "lr": 1.079664570230608e-05, "epoch": 0.43238993710691825, "percentage": 2.16, "elapsed_time": "0:02:10", "remaining_time": "1:38:31", "throughput": 4109.07, "total_tokens": 536768}
|
| 166 |
+
{"current_steps": 830, "total_steps": 38160, "loss": 0.8357, "lr": 1.0862159329140461e-05, "epoch": 0.4350104821802935, "percentage": 2.18, "elapsed_time": "0:02:11", "remaining_time": "1:38:39", "throughput": 4111.53, "total_tokens": 541184}
|
| 167 |
+
{"current_steps": 835, "total_steps": 38160, "loss": 0.7165, "lr": 1.0927672955974844e-05, "epoch": 0.43763102725366876, "percentage": 2.19, "elapsed_time": "0:02:12", "remaining_time": "1:38:38", "throughput": 4113.24, "total_tokens": 544576}
|
| 168 |
+
{"current_steps": 840, "total_steps": 38160, "loss": 0.8549, "lr": 1.0993186582809224e-05, "epoch": 0.44025157232704404, "percentage": 2.2, "elapsed_time": "0:02:13", "remaining_time": "1:38:49", "throughput": 4116.76, "total_tokens": 549408}
|
| 169 |
+
{"current_steps": 845, "total_steps": 38160, "loss": 0.8129, "lr": 1.1058700209643607e-05, "epoch": 0.44287211740041926, "percentage": 2.21, "elapsed_time": "0:02:14", "remaining_time": "1:38:44", "throughput": 4114.57, "total_tokens": 552032}
|
| 170 |
+
{"current_steps": 850, "total_steps": 38160, "loss": 0.7198, "lr": 1.1124213836477988e-05, "epoch": 0.44549266247379454, "percentage": 2.23, "elapsed_time": "0:02:14", "remaining_time": "1:38:45", "throughput": 4117.82, "total_tokens": 555872}
|
| 171 |
+
{"current_steps": 855, "total_steps": 38160, "loss": 0.923, "lr": 1.118972746331237e-05, "epoch": 0.4481132075471698, "percentage": 2.24, "elapsed_time": "0:02:15", "remaining_time": "1:38:43", "throughput": 4118.38, "total_tokens": 559136}
|
| 172 |
+
{"current_steps": 860, "total_steps": 38160, "loss": 0.7993, "lr": 1.1255241090146751e-05, "epoch": 0.45073375262054505, "percentage": 2.25, "elapsed_time": "0:02:16", "remaining_time": "1:38:43", "throughput": 4114.73, "total_tokens": 561984}
|
| 173 |
+
{"current_steps": 865, "total_steps": 38160, "loss": 0.7921, "lr": 1.1320754716981132e-05, "epoch": 0.4533542976939203, "percentage": 2.27, "elapsed_time": "0:02:17", "remaining_time": "1:38:40", "throughput": 4110.41, "total_tokens": 564448}
|
| 174 |
+
{"current_steps": 870, "total_steps": 38160, "loss": 1.0655, "lr": 1.1386268343815514e-05, "epoch": 0.4559748427672956, "percentage": 2.28, "elapsed_time": "0:02:18", "remaining_time": "1:38:37", "throughput": 4104.97, "total_tokens": 566752}
|
| 175 |
+
{"current_steps": 875, "total_steps": 38160, "loss": 0.774, "lr": 1.1451781970649895e-05, "epoch": 0.4585953878406709, "percentage": 2.29, "elapsed_time": "0:02:18", "remaining_time": "1:38:34", "throughput": 4105.51, "total_tokens": 569856}
|
| 176 |
+
{"current_steps": 880, "total_steps": 38160, "loss": 0.7655, "lr": 1.1517295597484278e-05, "epoch": 0.4612159329140461, "percentage": 2.31, "elapsed_time": "0:02:19", "remaining_time": "1:38:34", "throughput": 4104.49, "total_tokens": 573056}
|
| 177 |
+
{"current_steps": 885, "total_steps": 38160, "loss": 0.8161, "lr": 1.158280922431866e-05, "epoch": 0.4638364779874214, "percentage": 2.32, "elapsed_time": "0:02:20", "remaining_time": "1:38:30", "throughput": 4102.25, "total_tokens": 575712}
|
| 178 |
+
{"current_steps": 890, "total_steps": 38160, "loss": 0.7528, "lr": 1.164832285115304e-05, "epoch": 0.46645702306079667, "percentage": 2.33, "elapsed_time": "0:02:21", "remaining_time": "1:38:28", "throughput": 4102.61, "total_tokens": 578880}
|
| 179 |
+
{"current_steps": 895, "total_steps": 38160, "loss": 0.7216, "lr": 1.1713836477987422e-05, "epoch": 0.4690775681341719, "percentage": 2.35, "elapsed_time": "0:02:21", "remaining_time": "1:38:27", "throughput": 4101.32, "total_tokens": 581920}
|
| 180 |
+
{"current_steps": 900, "total_steps": 38160, "loss": 0.8706, "lr": 1.1779350104821804e-05, "epoch": 0.4716981132075472, "percentage": 2.36, "elapsed_time": "0:02:22", "remaining_time": "1:38:27", "throughput": 4097.7, "total_tokens": 584672}
|
| 181 |
+
{"current_steps": 905, "total_steps": 38160, "loss": 0.7196, "lr": 1.1844863731656185e-05, "epoch": 0.47431865828092246, "percentage": 2.37, "elapsed_time": "0:02:23", "remaining_time": "1:38:31", "throughput": 4099.68, "total_tokens": 588704}
|
| 182 |
+
{"current_steps": 910, "total_steps": 38160, "loss": 0.7647, "lr": 1.1910377358490566e-05, "epoch": 0.4769392033542977, "percentage": 2.38, "elapsed_time": "0:02:24", "remaining_time": "1:38:28", "throughput": 4099.51, "total_tokens": 591712}
|
| 183 |
+
{"current_steps": 915, "total_steps": 38160, "loss": 0.7805, "lr": 1.197589098532495e-05, "epoch": 0.47955974842767296, "percentage": 2.4, "elapsed_time": "0:02:25", "remaining_time": "1:38:26", "throughput": 4101.21, "total_tokens": 595104}
|
| 184 |
+
{"current_steps": 920, "total_steps": 38160, "loss": 0.698, "lr": 1.204140461215933e-05, "epoch": 0.48218029350104824, "percentage": 2.41, "elapsed_time": "0:02:26", "remaining_time": "1:38:33", "throughput": 4105.54, "total_tokens": 599808}
|
| 185 |
+
{"current_steps": 925, "total_steps": 38160, "loss": 0.6407, "lr": 1.210691823899371e-05, "epoch": 0.48480083857442346, "percentage": 2.42, "elapsed_time": "0:02:26", "remaining_time": "1:38:30", "throughput": 4105.18, "total_tokens": 602720}
|
| 186 |
+
{"current_steps": 930, "total_steps": 38160, "loss": 0.6805, "lr": 1.2172431865828094e-05, "epoch": 0.48742138364779874, "percentage": 2.44, "elapsed_time": "0:02:27", "remaining_time": "1:38:29", "throughput": 4106.07, "total_tokens": 606176}
|
| 187 |
+
{"current_steps": 935, "total_steps": 38160, "loss": 0.718, "lr": 1.2237945492662473e-05, "epoch": 0.490041928721174, "percentage": 2.45, "elapsed_time": "0:02:28", "remaining_time": "1:38:25", "throughput": 4104.87, "total_tokens": 608864}
|
| 188 |
+
{"current_steps": 940, "total_steps": 38160, "loss": 0.6831, "lr": 1.2303459119496856e-05, "epoch": 0.49266247379454925, "percentage": 2.46, "elapsed_time": "0:02:29", "remaining_time": "1:38:21", "throughput": 4105.82, "total_tokens": 611968}
|
| 189 |
+
{"current_steps": 945, "total_steps": 38160, "loss": 0.8422, "lr": 1.2368972746331238e-05, "epoch": 0.49528301886792453, "percentage": 2.48, "elapsed_time": "0:02:29", "remaining_time": "1:38:17", "throughput": 4105.67, "total_tokens": 614848}
|
| 190 |
+
{"current_steps": 950, "total_steps": 38160, "loss": 0.9827, "lr": 1.243448637316562e-05, "epoch": 0.4979035639412998, "percentage": 2.49, "elapsed_time": "0:02:30", "remaining_time": "1:38:15", "throughput": 4106.32, "total_tokens": 618080}
|
| 191 |
+
{"current_steps": 955, "total_steps": 38160, "loss": 0.5562, "lr": 1.25e-05, "epoch": 0.500524109014675, "percentage": 2.5, "elapsed_time": "0:02:31", "remaining_time": "1:38:12", "throughput": 4103.74, "total_tokens": 620736}
|
| 192 |
+
{"current_steps": 960, "total_steps": 38160, "loss": 0.6546, "lr": 1.2565513626834382e-05, "epoch": 0.5031446540880503, "percentage": 2.52, "elapsed_time": "0:02:32", "remaining_time": "1:38:14", "throughput": 4105.31, "total_tokens": 624480}
|
| 193 |
+
{"current_steps": 965, "total_steps": 38160, "loss": 0.6289, "lr": 1.2631027253668765e-05, "epoch": 0.5057651991614256, "percentage": 2.53, "elapsed_time": "0:02:32", "remaining_time": "1:38:16", "throughput": 4107.91, "total_tokens": 628448}
|
| 194 |
+
{"current_steps": 970, "total_steps": 38160, "loss": 0.8385, "lr": 1.2696540880503146e-05, "epoch": 0.5083857442348009, "percentage": 2.54, "elapsed_time": "0:02:33", "remaining_time": "1:38:18", "throughput": 4107.68, "total_tokens": 632000}
|
| 195 |
+
{"current_steps": 975, "total_steps": 38160, "loss": 0.8011, "lr": 1.2762054507337526e-05, "epoch": 0.5110062893081762, "percentage": 2.56, "elapsed_time": "0:02:34", "remaining_time": "1:38:19", "throughput": 4109.59, "total_tokens": 635680}
|
| 196 |
+
{"current_steps": 980, "total_steps": 38160, "loss": 1.0264, "lr": 1.2827568134171907e-05, "epoch": 0.5136268343815513, "percentage": 2.57, "elapsed_time": "0:02:35", "remaining_time": "1:38:14", "throughput": 4109.51, "total_tokens": 638496}
|
| 197 |
+
{"current_steps": 985, "total_steps": 38160, "loss": 0.652, "lr": 1.289308176100629e-05, "epoch": 0.5162473794549266, "percentage": 2.58, "elapsed_time": "0:02:36", "remaining_time": "1:38:16", "throughput": 4111.17, "total_tokens": 642272}
|
| 198 |
+
{"current_steps": 990, "total_steps": 38160, "loss": 0.8193, "lr": 1.2958595387840672e-05, "epoch": 0.5188679245283019, "percentage": 2.59, "elapsed_time": "0:02:37", "remaining_time": "1:38:19", "throughput": 4110.72, "total_tokens": 645888}
|
| 199 |
+
{"current_steps": 995, "total_steps": 38160, "loss": 0.526, "lr": 1.3024109014675053e-05, "epoch": 0.5214884696016772, "percentage": 2.61, "elapsed_time": "0:02:38", "remaining_time": "1:38:40", "throughput": 4112.41, "total_tokens": 651808}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 38160, "loss": 0.7769, "lr": 1.3089622641509436e-05, "epoch": 0.5241090146750524, "percentage": 2.62, "elapsed_time": "0:02:39", "remaining_time": "1:38:41", "throughput": 4113.35, "total_tokens": 655488}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 38160, "loss": 0.6392, "lr": 1.3155136268343814e-05, "epoch": 0.5267295597484277, "percentage": 2.63, "elapsed_time": "0:02:40", "remaining_time": "1:38:40", "throughput": 4114.98, "total_tokens": 658976}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 38160, "loss": 0.6963, "lr": 1.3220649895178197e-05, "epoch": 0.5293501048218029, "percentage": 2.65, "elapsed_time": "0:02:40", "remaining_time": "1:38:37", "throughput": 4114.85, "total_tokens": 662048}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 38160, "loss": 0.7808, "lr": 1.3286163522012579e-05, "epoch": 0.5319706498951782, "percentage": 2.66, "elapsed_time": "0:02:41", "remaining_time": "1:38:34", "throughput": 4112.7, "total_tokens": 664640}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 38160, "loss": 0.6198, "lr": 1.3351677148846962e-05, "epoch": 0.5345911949685535, "percentage": 2.67, "elapsed_time": "0:02:42", "remaining_time": "1:38:39", "throughput": 4115.38, "total_tokens": 669056}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 38160, "loss": 0.6533, "lr": 1.3417190775681343e-05, "epoch": 0.5372117400419287, "percentage": 2.69, "elapsed_time": "0:02:43", "remaining_time": "1:38:37", "throughput": 4115.14, "total_tokens": 672128}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 38160, "loss": 0.6627, "lr": 1.3482704402515725e-05, "epoch": 0.539832285115304, "percentage": 2.7, "elapsed_time": "0:02:44", "remaining_time": "1:38:34", "throughput": 4114.97, "total_tokens": 675136}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 38160, "loss": 0.7828, "lr": 1.3548218029350104e-05, "epoch": 0.5424528301886793, "percentage": 2.71, "elapsed_time": "0:02:44", "remaining_time": "1:38:36", "throughput": 4116.53, "total_tokens": 678976}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 38160, "loss": 0.9475, "lr": 1.3613731656184486e-05, "epoch": 0.5450733752620545, "percentage": 2.73, "elapsed_time": "0:02:45", "remaining_time": "1:38:35", "throughput": 4115.86, "total_tokens": 682176}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 38160, "loss": 0.7612, "lr": 1.3679245283018869e-05, "epoch": 0.5476939203354297, "percentage": 2.74, "elapsed_time": "0:02:46", "remaining_time": "1:38:30", "throughput": 4114.72, "total_tokens": 684768}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 38160, "loss": 0.7655, "lr": 1.374475890985325e-05, "epoch": 0.550314465408805, "percentage": 2.75, "elapsed_time": "0:02:47", "remaining_time": "1:38:28", "throughput": 4111.77, "total_tokens": 687392}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 38160, "loss": 0.6834, "lr": 1.3810272536687632e-05, "epoch": 0.5529350104821803, "percentage": 2.76, "elapsed_time": "0:02:47", "remaining_time": "1:38:26", "throughput": 4111.77, "total_tokens": 690496}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 38160, "loss": 0.9208, "lr": 1.3875786163522015e-05, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:02:48", "remaining_time": "1:38:26", "throughput": 4108.46, "total_tokens": 693376}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 38160, "loss": 0.7404, "lr": 1.3941299790356394e-05, "epoch": 0.5581761006289309, "percentage": 2.79, "elapsed_time": "0:02:49", "remaining_time": "1:38:25", "throughput": 4103.81, "total_tokens": 695808}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 38160, "loss": 0.5877, "lr": 1.4006813417190776e-05, "epoch": 0.560796645702306, "percentage": 2.8, "elapsed_time": "0:02:50", "remaining_time": "1:38:25", "throughput": 4105.2, "total_tokens": 699424}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 38160, "loss": 0.6302, "lr": 1.4072327044025157e-05, "epoch": 0.5634171907756813, "percentage": 2.82, "elapsed_time": "0:02:51", "remaining_time": "1:38:28", "throughput": 4108.25, "total_tokens": 703584}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 38160, "loss": 0.7182, "lr": 1.413784067085954e-05, "epoch": 0.5660377358490566, "percentage": 2.83, "elapsed_time": "0:02:51", "remaining_time": "1:38:23", "throughput": 4106.89, "total_tokens": 706144}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 38160, "loss": 0.7308, "lr": 1.4203354297693922e-05, "epoch": 0.5686582809224319, "percentage": 2.84, "elapsed_time": "0:02:52", "remaining_time": "1:38:19", "throughput": 4105.84, "total_tokens": 708864}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 38160, "loss": 0.7117, "lr": 1.4268867924528303e-05, "epoch": 0.5712788259958071, "percentage": 2.86, "elapsed_time": "0:02:53", "remaining_time": "1:38:19", "throughput": 4106.25, "total_tokens": 712352}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 38160, "loss": 0.8671, "lr": 1.4334381551362683e-05, "epoch": 0.5738993710691824, "percentage": 2.87, "elapsed_time": "0:02:54", "remaining_time": "1:38:16", "throughput": 4106.44, "total_tokens": 715296}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 38160, "loss": 0.6207, "lr": 1.4399895178197064e-05, "epoch": 0.5765199161425576, "percentage": 2.88, "elapsed_time": "0:02:54", "remaining_time": "1:38:15", "throughput": 4106.07, "total_tokens": 718528}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 38160, "loss": 0.6151, "lr": 1.4465408805031447e-05, "epoch": 0.5791404612159329, "percentage": 2.9, "elapsed_time": "0:02:55", "remaining_time": "1:38:18", "throughput": 4109.2, "total_tokens": 722752}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 38160, "loss": 0.689, "lr": 1.4530922431865828e-05, "epoch": 0.5817610062893082, "percentage": 2.91, "elapsed_time": "0:02:56", "remaining_time": "1:38:15", "throughput": 4109.68, "total_tokens": 725824}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 38160, "loss": 0.7411, "lr": 1.4596436058700211e-05, "epoch": 0.5843815513626834, "percentage": 2.92, "elapsed_time": "0:02:57", "remaining_time": "1:38:17", "throughput": 4112.73, "total_tokens": 730080}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 38160, "loss": 0.5858, "lr": 1.4661949685534593e-05, "epoch": 0.5870020964360587, "percentage": 2.94, "elapsed_time": "0:02:58", "remaining_time": "1:38:14", "throughput": 4113.55, "total_tokens": 733216}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 38160, "loss": 0.7963, "lr": 1.4727463312368974e-05, "epoch": 0.589622641509434, "percentage": 2.95, "elapsed_time": "0:02:59", "remaining_time": "1:38:14", "throughput": 4113.13, "total_tokens": 736416}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 38160, "loss": 0.6192, "lr": 1.4792976939203354e-05, "epoch": 0.5922431865828093, "percentage": 2.96, "elapsed_time": "0:02:59", "remaining_time": "1:38:11", "throughput": 4114.74, "total_tokens": 739808}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 38160, "loss": 0.7157, "lr": 1.4858490566037735e-05, "epoch": 0.5948637316561844, "percentage": 2.97, "elapsed_time": "0:03:00", "remaining_time": "1:38:10", "throughput": 4111.28, "total_tokens": 742400}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 38160, "loss": 0.5183, "lr": 1.4924004192872118e-05, "epoch": 0.5974842767295597, "percentage": 2.99, "elapsed_time": "0:03:01", "remaining_time": "1:38:10", "throughput": 4111.06, "total_tokens": 745760}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 38160, "loss": 0.746, "lr": 1.49895178197065e-05, "epoch": 0.600104821802935, "percentage": 3.0, "elapsed_time": "0:03:02", "remaining_time": "1:38:10", "throughput": 4109.41, "total_tokens": 748736}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 38160, "loss": 0.6771, "lr": 1.5055031446540883e-05, "epoch": 0.6027253668763103, "percentage": 3.01, "elapsed_time": "0:03:02", "remaining_time": "1:38:07", "throughput": 4110.46, "total_tokens": 752032}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 38160, "loss": 0.5946, "lr": 1.5120545073375264e-05, "epoch": 0.6053459119496856, "percentage": 3.03, "elapsed_time": "0:03:03", "remaining_time": "1:38:14", "throughput": 4113.37, "total_tokens": 756736}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 38160, "loss": 0.617, "lr": 1.5186058700209644e-05, "epoch": 0.6079664570230608, "percentage": 3.04, "elapsed_time": "0:03:04", "remaining_time": "1:38:11", "throughput": 4113.19, "total_tokens": 759680}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 38160, "loss": 0.783, "lr": 1.5251572327044025e-05, "epoch": 0.610587002096436, "percentage": 3.05, "elapsed_time": "0:03:05", "remaining_time": "1:38:08", "throughput": 4112.16, "total_tokens": 762560}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 38160, "loss": 0.5559, "lr": 1.5317085953878407e-05, "epoch": 0.6132075471698113, "percentage": 3.07, "elapsed_time": "0:03:06", "remaining_time": "1:38:06", "throughput": 4111.73, "total_tokens": 765600}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 38160, "loss": 0.4896, "lr": 1.538259958071279e-05, "epoch": 0.6158280922431866, "percentage": 3.08, "elapsed_time": "0:03:06", "remaining_time": "1:38:04", "throughput": 4111.94, "total_tokens": 768736}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 38160, "loss": 0.7999, "lr": 1.5448113207547173e-05, "epoch": 0.6184486373165619, "percentage": 3.09, "elapsed_time": "0:03:07", "remaining_time": "1:38:02", "throughput": 4112.22, "total_tokens": 771872}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 38160, "loss": 0.7693, "lr": 1.5513626834381552e-05, "epoch": 0.6210691823899371, "percentage": 3.11, "elapsed_time": "0:03:08", "remaining_time": "1:37:59", "throughput": 4112.65, "total_tokens": 775008}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 38160, "loss": 0.5689, "lr": 1.5579140461215932e-05, "epoch": 0.6236897274633124, "percentage": 3.12, "elapsed_time": "0:03:09", "remaining_time": "1:37:56", "throughput": 4112.34, "total_tokens": 777920}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 38160, "loss": 0.6846, "lr": 1.5644654088050315e-05, "epoch": 0.6263102725366876, "percentage": 3.13, "elapsed_time": "0:03:09", "remaining_time": "1:37:55", "throughput": 4112.3, "total_tokens": 781056}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 38160, "loss": 0.6956, "lr": 1.5710167714884695e-05, "epoch": 0.6289308176100629, "percentage": 3.14, "elapsed_time": "0:03:10", "remaining_time": "1:37:53", "throughput": 4112.14, "total_tokens": 784128}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 38160, "loss": 0.7071, "lr": 1.5775681341719078e-05, "epoch": 0.6315513626834381, "percentage": 3.16, "elapsed_time": "0:03:11", "remaining_time": "1:37:49", "throughput": 4109.87, "total_tokens": 786624}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 38160, "loss": 0.6347, "lr": 1.584119496855346e-05, "epoch": 0.6341719077568134, "percentage": 3.17, "elapsed_time": "0:03:12", "remaining_time": "1:37:47", "throughput": 4109.58, "total_tokens": 789664}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 38160, "loss": 0.5269, "lr": 1.5906708595387844e-05, "epoch": 0.6367924528301887, "percentage": 3.18, "elapsed_time": "0:03:13", "remaining_time": "1:37:49", "throughput": 4112.23, "total_tokens": 793824}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 38160, "loss": 0.8113, "lr": 1.597222222222222e-05, "epoch": 0.639412997903564, "percentage": 3.2, "elapsed_time": "0:03:13", "remaining_time": "1:37:45", "throughput": 4111.64, "total_tokens": 796544}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 38160, "loss": 0.515, "lr": 1.6037735849056604e-05, "epoch": 0.6420335429769392, "percentage": 3.21, "elapsed_time": "0:03:14", "remaining_time": "1:37:43", "throughput": 4111.27, "total_tokens": 799520}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 38160, "loss": 0.4912, "lr": 1.6103249475890987e-05, "epoch": 0.6446540880503144, "percentage": 3.22, "elapsed_time": "0:03:15", "remaining_time": "1:37:41", "throughput": 4110.34, "total_tokens": 802464}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 38160, "loss": 0.7404, "lr": 1.6168763102725366e-05, "epoch": 0.6472746331236897, "percentage": 3.24, "elapsed_time": "0:03:16", "remaining_time": "1:37:40", "throughput": 4109.3, "total_tokens": 805536}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 38160, "loss": 0.5321, "lr": 1.623427672955975e-05, "epoch": 0.649895178197065, "percentage": 3.25, "elapsed_time": "0:03:16", "remaining_time": "1:37:38", "throughput": 4108.78, "total_tokens": 808448}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 38160, "loss": 0.5692, "lr": 1.6299790356394132e-05, "epoch": 0.6525157232704403, "percentage": 3.26, "elapsed_time": "0:03:17", "remaining_time": "1:37:39", "throughput": 4109.88, "total_tokens": 812160}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 38160, "loss": 0.8446, "lr": 1.6365303983228512e-05, "epoch": 0.6551362683438156, "percentage": 3.28, "elapsed_time": "0:03:18", "remaining_time": "1:37:34", "throughput": 4108.97, "total_tokens": 814752}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 38160, "loss": 0.529, "lr": 1.6430817610062892e-05, "epoch": 0.6577568134171907, "percentage": 3.29, "elapsed_time": "0:03:19", "remaining_time": "1:37:32", "throughput": 4108.28, "total_tokens": 817568}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 38160, "loss": 0.618, "lr": 1.6496331236897275e-05, "epoch": 0.660377358490566, "percentage": 3.3, "elapsed_time": "0:03:19", "remaining_time": "1:37:28", "throughput": 4107.93, "total_tokens": 820384}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 38160, "loss": 0.4065, "lr": 1.6561844863731658e-05, "epoch": 0.6629979035639413, "percentage": 3.31, "elapsed_time": "0:03:20", "remaining_time": "1:37:25", "throughput": 4106.59, "total_tokens": 823040}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 38160, "loss": 0.7655, "lr": 1.6627358490566038e-05, "epoch": 0.6656184486373166, "percentage": 3.33, "elapsed_time": "0:03:21", "remaining_time": "1:37:22", "throughput": 4104.6, "total_tokens": 825600}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 38160, "loss": 0.6828, "lr": 1.669287211740042e-05, "epoch": 0.6682389937106918, "percentage": 3.34, "elapsed_time": "0:03:21", "remaining_time": "1:37:18", "throughput": 4102.84, "total_tokens": 828032}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 38160, "loss": 0.598, "lr": 1.6758385744234804e-05, "epoch": 0.6708595387840671, "percentage": 3.35, "elapsed_time": "0:03:22", "remaining_time": "1:37:18", "throughput": 4102.61, "total_tokens": 831296}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 38160, "loss": 0.7169, "lr": 1.6823899371069183e-05, "epoch": 0.6734800838574424, "percentage": 3.37, "elapsed_time": "0:03:23", "remaining_time": "1:37:15", "throughput": 4102.15, "total_tokens": 834208}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 38160, "loss": 0.5976, "lr": 1.6889412997903563e-05, "epoch": 0.6761006289308176, "percentage": 3.38, "elapsed_time": "0:03:24", "remaining_time": "1:37:17", "throughput": 4103.3, "total_tokens": 838048}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 38160, "loss": 0.6662, "lr": 1.6954926624737946e-05, "epoch": 0.6787211740041929, "percentage": 3.39, "elapsed_time": "0:03:25", "remaining_time": "1:37:17", "throughput": 4104.18, "total_tokens": 841536}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 38160, "loss": 0.5336, "lr": 1.702044025157233e-05, "epoch": 0.6813417190775681, "percentage": 3.41, "elapsed_time": "0:03:25", "remaining_time": "1:37:17", "throughput": 4105.16, "total_tokens": 845184}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 38160, "loss": 0.5071, "lr": 1.708595387840671e-05, "epoch": 0.6839622641509434, "percentage": 3.42, "elapsed_time": "0:03:26", "remaining_time": "1:37:13", "throughput": 4105.05, "total_tokens": 848000}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 38160, "loss": 0.6809, "lr": 1.7151467505241092e-05, "epoch": 0.6865828092243187, "percentage": 3.43, "elapsed_time": "0:03:27", "remaining_time": "1:37:11", "throughput": 4105.15, "total_tokens": 851040}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 38160, "loss": 0.69, "lr": 1.7216981132075472e-05, "epoch": 0.689203354297694, "percentage": 3.45, "elapsed_time": "0:03:28", "remaining_time": "1:37:09", "throughput": 4104.55, "total_tokens": 853920}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 38160, "loss": 0.6153, "lr": 1.7282494758909855e-05, "epoch": 0.6918238993710691, "percentage": 3.46, "elapsed_time": "0:03:28", "remaining_time": "1:37:07", "throughput": 4105.57, "total_tokens": 857312}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 38160, "loss": 0.5198, "lr": 1.7348008385744234e-05, "epoch": 0.6944444444444444, "percentage": 3.47, "elapsed_time": "0:03:29", "remaining_time": "1:37:04", "throughput": 4103.94, "total_tokens": 859904}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 38160, "loss": 0.6601, "lr": 1.7413522012578618e-05, "epoch": 0.6970649895178197, "percentage": 3.49, "elapsed_time": "0:03:30", "remaining_time": "1:37:05", "throughput": 4105.49, "total_tokens": 863680}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 38160, "loss": 0.7199, "lr": 1.7479035639413e-05, "epoch": 0.699685534591195, "percentage": 3.5, "elapsed_time": "0:03:31", "remaining_time": "1:37:03", "throughput": 4105.81, "total_tokens": 866880}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 38160, "loss": 0.4921, "lr": 1.754454926624738e-05, "epoch": 0.7023060796645703, "percentage": 3.51, "elapsed_time": "0:03:31", "remaining_time": "1:37:03", "throughput": 4104.21, "total_tokens": 869856}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 38160, "loss": 0.6852, "lr": 1.761006289308176e-05, "epoch": 0.7049266247379455, "percentage": 3.52, "elapsed_time": "0:03:32", "remaining_time": "1:37:04", "throughput": 4104.86, "total_tokens": 873472}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 38160, "loss": 0.5787, "lr": 1.7675576519916143e-05, "epoch": 0.7075471698113207, "percentage": 3.54, "elapsed_time": "0:03:33", "remaining_time": "1:37:03", "throughput": 4105.03, "total_tokens": 876704}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 38160, "loss": 0.5533, "lr": 1.7741090146750526e-05, "epoch": 0.710167714884696, "percentage": 3.55, "elapsed_time": "0:03:34", "remaining_time": "1:37:03", "throughput": 4106.91, "total_tokens": 880576}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 38160, "loss": 0.5917, "lr": 1.7806603773584906e-05, "epoch": 0.7127882599580713, "percentage": 3.56, "elapsed_time": "0:03:35", "remaining_time": "1:37:02", "throughput": 4106.7, "total_tokens": 883680}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 38160, "loss": 0.73, "lr": 1.787211740041929e-05, "epoch": 0.7154088050314465, "percentage": 3.58, "elapsed_time": "0:03:35", "remaining_time": "1:36:59", "throughput": 4105.91, "total_tokens": 886464}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 38160, "loss": 0.6766, "lr": 1.7937631027253672e-05, "epoch": 0.7180293501048218, "percentage": 3.59, "elapsed_time": "0:03:36", "remaining_time": "1:36:58", "throughput": 4105.56, "total_tokens": 889536}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 38160, "loss": 0.6193, "lr": 1.8003144654088048e-05, "epoch": 0.7206498951781971, "percentage": 3.6, "elapsed_time": "0:03:37", "remaining_time": "1:37:04", "throughput": 4107.62, "total_tokens": 894272}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 38160, "loss": 0.5334, "lr": 1.806865828092243e-05, "epoch": 0.7232704402515723, "percentage": 3.62, "elapsed_time": "0:03:38", "remaining_time": "1:37:01", "throughput": 4107.39, "total_tokens": 897120}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 38160, "loss": 0.5893, "lr": 1.8134171907756814e-05, "epoch": 0.7258909853249476, "percentage": 3.63, "elapsed_time": "0:03:39", "remaining_time": "1:36:58", "throughput": 4106.19, "total_tokens": 899808}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 38160, "loss": 0.6111, "lr": 1.8199685534591197e-05, "epoch": 0.7285115303983228, "percentage": 3.64, "elapsed_time": "0:03:39", "remaining_time": "1:36:59", "throughput": 4107.13, "total_tokens": 903520}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 38160, "loss": 0.6196, "lr": 1.8265199161425577e-05, "epoch": 0.7311320754716981, "percentage": 3.66, "elapsed_time": "0:03:40", "remaining_time": "1:37:00", "throughput": 4108.07, "total_tokens": 907200}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 38160, "loss": 0.5963, "lr": 1.833071278825996e-05, "epoch": 0.7337526205450734, "percentage": 3.67, "elapsed_time": "0:03:41", "remaining_time": "1:37:03", "throughput": 4109.49, "total_tokens": 911392}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 38160, "loss": 0.7127, "lr": 1.839622641509434e-05, "epoch": 0.7363731656184487, "percentage": 3.68, "elapsed_time": "0:03:42", "remaining_time": "1:36:59", "throughput": 4106.18, "total_tokens": 913440}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 38160, "loss": 0.5527, "lr": 1.846174004192872e-05, "epoch": 0.7389937106918238, "percentage": 3.69, "elapsed_time": "0:03:43", "remaining_time": "1:37:04", "throughput": 4107.57, "total_tokens": 917888}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 38160, "loss": 0.6356, "lr": 1.8527253668763103e-05, "epoch": 0.7416142557651991, "percentage": 3.71, "elapsed_time": "0:03:44", "remaining_time": "1:37:04", "throughput": 4107.75, "total_tokens": 921376}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 38160, "loss": 0.6561, "lr": 1.8592767295597486e-05, "epoch": 0.7442348008385744, "percentage": 3.72, "elapsed_time": "0:03:45", "remaining_time": "1:37:04", "throughput": 4107.98, "total_tokens": 924800}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 38160, "loss": 0.7697, "lr": 1.865828092243187e-05, "epoch": 0.7468553459119497, "percentage": 3.73, "elapsed_time": "0:03:45", "remaining_time": "1:37:02", "throughput": 4107.02, "total_tokens": 927648}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 38160, "loss": 0.4955, "lr": 1.872379454926625e-05, "epoch": 0.749475890985325, "percentage": 3.75, "elapsed_time": "0:03:46", "remaining_time": "1:36:59", "throughput": 4105.62, "total_tokens": 930144}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 38160, "loss": 0.4879, "lr": 1.878930817610063e-05, "epoch": 0.7520964360587002, "percentage": 3.76, "elapsed_time": "0:03:47", "remaining_time": "1:36:57", "throughput": 4105.2, "total_tokens": 933184}
|
| 288 |
+
{"current_steps": 1440, "total_steps": 38160, "loss": 0.6451, "lr": 1.885482180293501e-05, "epoch": 0.7547169811320755, "percentage": 3.77, "elapsed_time": "0:03:48", "remaining_time": "1:36:59", "throughput": 4107.71, "total_tokens": 937376}
|
| 289 |
+
{"current_steps": 1445, "total_steps": 38160, "loss": 0.6051, "lr": 1.892033542976939e-05, "epoch": 0.7573375262054507, "percentage": 3.79, "elapsed_time": "0:03:48", "remaining_time": "1:36:57", "throughput": 4106.51, "total_tokens": 940160}
|
| 290 |
+
{"current_steps": 1450, "total_steps": 38160, "loss": 0.6754, "lr": 1.8985849056603774e-05, "epoch": 0.759958071278826, "percentage": 3.8, "elapsed_time": "0:03:49", "remaining_time": "1:36:54", "throughput": 4105.1, "total_tokens": 942816}
|
| 291 |
+
{"current_steps": 1455, "total_steps": 38160, "loss": 0.653, "lr": 1.9051362683438157e-05, "epoch": 0.7625786163522013, "percentage": 3.81, "elapsed_time": "0:03:50", "remaining_time": "1:36:52", "throughput": 4105.42, "total_tokens": 945952}
|
| 292 |
+
{"current_steps": 1460, "total_steps": 38160, "loss": 0.4929, "lr": 1.9116876310272537e-05, "epoch": 0.7651991614255765, "percentage": 3.83, "elapsed_time": "0:03:51", "remaining_time": "1:36:52", "throughput": 4105.84, "total_tokens": 949472}
|
| 293 |
+
{"current_steps": 1465, "total_steps": 38160, "loss": 0.6275, "lr": 1.918238993710692e-05, "epoch": 0.7678197064989518, "percentage": 3.84, "elapsed_time": "0:03:51", "remaining_time": "1:36:50", "throughput": 4106.48, "total_tokens": 952672}
|
| 294 |
+
{"current_steps": 1470, "total_steps": 38160, "loss": 0.7223, "lr": 1.92479035639413e-05, "epoch": 0.7704402515723271, "percentage": 3.85, "elapsed_time": "0:03:52", "remaining_time": "1:36:52", "throughput": 4103.17, "total_tokens": 955520}
|
| 295 |
+
{"current_steps": 1475, "total_steps": 38160, "loss": 0.6358, "lr": 1.9313417190775683e-05, "epoch": 0.7730607966457023, "percentage": 3.87, "elapsed_time": "0:03:53", "remaining_time": "1:36:54", "throughput": 4099.8, "total_tokens": 958464}
|
| 296 |
+
{"current_steps": 1480, "total_steps": 38160, "loss": 0.5915, "lr": 1.9378930817610062e-05, "epoch": 0.7756813417190775, "percentage": 3.88, "elapsed_time": "0:03:54", "remaining_time": "1:36:55", "throughput": 4094.14, "total_tokens": 960768}
|
| 297 |
+
{"current_steps": 1485, "total_steps": 38160, "loss": 0.8072, "lr": 1.9444444444444445e-05, "epoch": 0.7783018867924528, "percentage": 3.89, "elapsed_time": "0:03:55", "remaining_time": "1:36:57", "throughput": 4090.74, "total_tokens": 963616}
|
| 298 |
+
{"current_steps": 1490, "total_steps": 38160, "loss": 0.7734, "lr": 1.950995807127883e-05, "epoch": 0.7809224318658281, "percentage": 3.9, "elapsed_time": "0:03:56", "remaining_time": "1:37:02", "throughput": 4091.06, "total_tokens": 967936}
|
| 299 |
+
{"current_steps": 1495, "total_steps": 38160, "loss": 0.5603, "lr": 1.9575471698113208e-05, "epoch": 0.7835429769392034, "percentage": 3.92, "elapsed_time": "0:03:57", "remaining_time": "1:37:08", "throughput": 4089.16, "total_tokens": 971744}
|
| 300 |
+
{"current_steps": 1500, "total_steps": 38160, "loss": 0.6896, "lr": 1.9640985324947588e-05, "epoch": 0.7861635220125787, "percentage": 3.93, "elapsed_time": "0:03:58", "remaining_time": "1:37:09", "throughput": 4083.61, "total_tokens": 974080}
|
| 301 |
+
{"current_steps": 1505, "total_steps": 38160, "loss": 0.5451, "lr": 1.970649895178197e-05, "epoch": 0.7887840670859538, "percentage": 3.94, "elapsed_time": "0:03:59", "remaining_time": "1:37:11", "throughput": 4080.48, "total_tokens": 976992}
|
| 302 |
+
{"current_steps": 1510, "total_steps": 38160, "loss": 0.5976, "lr": 1.9772012578616354e-05, "epoch": 0.7914046121593291, "percentage": 3.96, "elapsed_time": "0:04:00", "remaining_time": "1:37:12", "throughput": 4076.59, "total_tokens": 979648}
|
| 303 |
+
{"current_steps": 1515, "total_steps": 38160, "loss": 0.6765, "lr": 1.9837526205450734e-05, "epoch": 0.7940251572327044, "percentage": 3.97, "elapsed_time": "0:04:01", "remaining_time": "1:37:15", "throughput": 4075.2, "total_tokens": 983136}
|
| 304 |
+
{"current_steps": 1520, "total_steps": 38160, "loss": 0.6083, "lr": 1.9903039832285117e-05, "epoch": 0.7966457023060797, "percentage": 3.98, "elapsed_time": "0:04:02", "remaining_time": "1:37:20", "throughput": 4073.31, "total_tokens": 986976}
|
| 305 |
+
{"current_steps": 1525, "total_steps": 38160, "loss": 0.5482, "lr": 1.99685534591195e-05, "epoch": 0.799266247379455, "percentage": 4.0, "elapsed_time": "0:04:03", "remaining_time": "1:37:23", "throughput": 4071.18, "total_tokens": 990272}
|
| 306 |
+
{"current_steps": 1530, "total_steps": 38160, "loss": 0.5687, "lr": 2.003406708595388e-05, "epoch": 0.8018867924528302, "percentage": 4.01, "elapsed_time": "0:04:04", "remaining_time": "1:37:30", "throughput": 4069.1, "total_tokens": 994368}
|
| 307 |
+
{"current_steps": 1535, "total_steps": 38160, "loss": 0.5074, "lr": 2.009958071278826e-05, "epoch": 0.8045073375262054, "percentage": 4.02, "elapsed_time": "0:04:05", "remaining_time": "1:37:32", "throughput": 4066.93, "total_tokens": 997504}
|
| 308 |
+
{"current_steps": 1540, "total_steps": 38160, "loss": 0.6636, "lr": 2.0165094339622642e-05, "epoch": 0.8071278825995807, "percentage": 4.04, "elapsed_time": "0:04:06", "remaining_time": "1:37:32", "throughput": 4064.78, "total_tokens": 1000352}
|
| 309 |
+
{"current_steps": 1545, "total_steps": 38160, "loss": 0.6473, "lr": 2.0230607966457025e-05, "epoch": 0.809748427672956, "percentage": 4.05, "elapsed_time": "0:04:06", "remaining_time": "1:37:33", "throughput": 4063.63, "total_tokens": 1003616}
|
| 310 |
+
{"current_steps": 1550, "total_steps": 38160, "loss": 0.7402, "lr": 2.0296121593291405e-05, "epoch": 0.8123689727463312, "percentage": 4.06, "elapsed_time": "0:04:07", "remaining_time": "1:37:32", "throughput": 4060.86, "total_tokens": 1006240}
|
| 311 |
+
{"current_steps": 1555, "total_steps": 38160, "loss": 0.647, "lr": 2.0361635220125788e-05, "epoch": 0.8149895178197065, "percentage": 4.07, "elapsed_time": "0:04:08", "remaining_time": "1:37:32", "throughput": 4060.24, "total_tokens": 1009440}
|
| 312 |
+
{"current_steps": 1560, "total_steps": 38160, "loss": 0.7354, "lr": 2.0427148846960168e-05, "epoch": 0.8176100628930818, "percentage": 4.09, "elapsed_time": "0:04:09", "remaining_time": "1:37:32", "throughput": 4056.92, "total_tokens": 1011936}
|
| 313 |
+
{"current_steps": 1565, "total_steps": 38160, "loss": 0.5667, "lr": 2.049266247379455e-05, "epoch": 0.820230607966457, "percentage": 4.1, "elapsed_time": "0:04:10", "remaining_time": "1:37:32", "throughput": 4055.21, "total_tokens": 1015040}
|
| 314 |
+
{"current_steps": 1570, "total_steps": 38160, "loss": 0.698, "lr": 2.055817610062893e-05, "epoch": 0.8228511530398323, "percentage": 4.11, "elapsed_time": "0:04:11", "remaining_time": "1:37:33", "throughput": 4054.39, "total_tokens": 1018240}
|
| 315 |
+
{"current_steps": 1575, "total_steps": 38160, "loss": 0.5864, "lr": 2.0623689727463314e-05, "epoch": 0.8254716981132075, "percentage": 4.13, "elapsed_time": "0:04:12", "remaining_time": "1:37:36", "throughput": 4055.04, "total_tokens": 1022336}
|
| 316 |
+
{"current_steps": 1580, "total_steps": 38160, "loss": 0.6134, "lr": 2.0689203354297697e-05, "epoch": 0.8280922431865828, "percentage": 4.14, "elapsed_time": "0:04:12", "remaining_time": "1:37:36", "throughput": 4052.86, "total_tokens": 1025184}
|
| 317 |
+
{"current_steps": 1585, "total_steps": 38160, "loss": 0.6512, "lr": 2.0754716981132076e-05, "epoch": 0.8307127882599581, "percentage": 4.15, "elapsed_time": "0:04:13", "remaining_time": "1:37:39", "throughput": 4050.34, "total_tokens": 1028448}
|
| 318 |
+
{"current_steps": 1590, "total_steps": 38160, "loss": 0.6254, "lr": 2.0820230607966456e-05, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:04:14", "remaining_time": "1:37:40", "throughput": 4046.55, "total_tokens": 1031072}
|
| 319 |
+
{"current_steps": 1595, "total_steps": 38160, "loss": 0.6073, "lr": 2.088574423480084e-05, "epoch": 0.8359538784067087, "percentage": 4.18, "elapsed_time": "0:04:15", "remaining_time": "1:37:43", "throughput": 4043.42, "total_tokens": 1034208}
|
| 320 |
+
{"current_steps": 1600, "total_steps": 38160, "loss": 0.5577, "lr": 2.0951257861635222e-05, "epoch": 0.8385744234800838, "percentage": 4.19, "elapsed_time": "0:04:16", "remaining_time": "1:37:47", "throughput": 4044.63, "total_tokens": 1038624}
|
| 321 |
+
{"current_steps": 1605, "total_steps": 38160, "loss": 0.6905, "lr": 2.1016771488469602e-05, "epoch": 0.8411949685534591, "percentage": 4.21, "elapsed_time": "0:04:17", "remaining_time": "1:37:50", "throughput": 4039.47, "total_tokens": 1041152}
|
| 322 |
+
{"current_steps": 1610, "total_steps": 38160, "loss": 0.4755, "lr": 2.1082285115303985e-05, "epoch": 0.8438155136268344, "percentage": 4.22, "elapsed_time": "0:04:18", "remaining_time": "1:37:51", "throughput": 4036.41, "total_tokens": 1043904}
|
| 323 |
+
{"current_steps": 1615, "total_steps": 38160, "loss": 0.578, "lr": 2.1147798742138368e-05, "epoch": 0.8464360587002097, "percentage": 4.23, "elapsed_time": "0:04:19", "remaining_time": "1:37:52", "throughput": 4036.2, "total_tokens": 1047456}
|
| 324 |
+
{"current_steps": 1620, "total_steps": 38160, "loss": 0.6271, "lr": 2.1213312368972748e-05, "epoch": 0.8490566037735849, "percentage": 4.25, "elapsed_time": "0:04:20", "remaining_time": "1:37:55", "throughput": 4031.98, "total_tokens": 1050304}
|
| 325 |
+
{"current_steps": 1625, "total_steps": 38160, "loss": 0.6134, "lr": 2.1278825995807127e-05, "epoch": 0.8516771488469602, "percentage": 4.26, "elapsed_time": "0:04:21", "remaining_time": "1:37:57", "throughput": 4030.31, "total_tokens": 1053600}
|
| 326 |
+
{"current_steps": 1630, "total_steps": 38160, "loss": 0.4403, "lr": 2.134433962264151e-05, "epoch": 0.8542976939203354, "percentage": 4.27, "elapsed_time": "0:04:22", "remaining_time": "1:37:59", "throughput": 4028.04, "total_tokens": 1056672}
|
| 327 |
+
{"current_steps": 1635, "total_steps": 38160, "loss": 0.4695, "lr": 2.1409853249475894e-05, "epoch": 0.8569182389937107, "percentage": 4.28, "elapsed_time": "0:04:23", "remaining_time": "1:38:02", "throughput": 4025.11, "total_tokens": 1059904}
|
| 328 |
+
{"current_steps": 1640, "total_steps": 38160, "loss": 0.5861, "lr": 2.1475366876310273e-05, "epoch": 0.859538784067086, "percentage": 4.3, "elapsed_time": "0:04:24", "remaining_time": "1:38:03", "throughput": 4024.7, "total_tokens": 1063360}
|
| 329 |
+
{"current_steps": 1645, "total_steps": 38160, "loss": 0.605, "lr": 2.1540880503144656e-05, "epoch": 0.8621593291404612, "percentage": 4.31, "elapsed_time": "0:04:25", "remaining_time": "1:38:06", "throughput": 4018.83, "total_tokens": 1065728}
|
| 330 |
+
{"current_steps": 1650, "total_steps": 38160, "loss": 0.5751, "lr": 2.160639412997904e-05, "epoch": 0.8647798742138365, "percentage": 4.32, "elapsed_time": "0:04:26", "remaining_time": "1:38:07", "throughput": 4015.87, "total_tokens": 1068448}
|
| 331 |
+
{"current_steps": 1655, "total_steps": 38160, "loss": 0.6013, "lr": 2.1671907756813416e-05, "epoch": 0.8674004192872118, "percentage": 4.34, "elapsed_time": "0:04:26", "remaining_time": "1:38:08", "throughput": 4012.34, "total_tokens": 1071104}
|
| 332 |
+
{"current_steps": 1660, "total_steps": 38160, "loss": 0.5121, "lr": 2.17374213836478e-05, "epoch": 0.870020964360587, "percentage": 4.35, "elapsed_time": "0:04:27", "remaining_time": "1:38:11", "throughput": 4012.11, "total_tokens": 1075072}
|
| 333 |
+
{"current_steps": 1665, "total_steps": 38160, "loss": 0.5984, "lr": 2.1802935010482182e-05, "epoch": 0.8726415094339622, "percentage": 4.36, "elapsed_time": "0:04:28", "remaining_time": "1:38:11", "throughput": 4009.69, "total_tokens": 1077824}
|
| 334 |
+
{"current_steps": 1670, "total_steps": 38160, "loss": 0.5406, "lr": 2.186844863731656e-05, "epoch": 0.8752620545073375, "percentage": 4.38, "elapsed_time": "0:04:29", "remaining_time": "1:38:13", "throughput": 4007.22, "total_tokens": 1080832}
|
| 335 |
+
{"current_steps": 1675, "total_steps": 38160, "loss": 0.6457, "lr": 2.1933962264150945e-05, "epoch": 0.8778825995807128, "percentage": 4.39, "elapsed_time": "0:04:30", "remaining_time": "1:38:13", "throughput": 4006.56, "total_tokens": 1084096}
|
| 336 |
+
{"current_steps": 1680, "total_steps": 38160, "loss": 0.6039, "lr": 2.1999475890985328e-05, "epoch": 0.8805031446540881, "percentage": 4.4, "elapsed_time": "0:04:31", "remaining_time": "1:38:13", "throughput": 4005.5, "total_tokens": 1087104}
|
| 337 |
+
{"current_steps": 1685, "total_steps": 38160, "loss": 0.6796, "lr": 2.2064989517819707e-05, "epoch": 0.8831236897274634, "percentage": 4.42, "elapsed_time": "0:04:32", "remaining_time": "1:38:15", "throughput": 4003.35, "total_tokens": 1090304}
|
| 338 |
+
{"current_steps": 1690, "total_steps": 38160, "loss": 0.8619, "lr": 2.2130503144654087e-05, "epoch": 0.8857442348008385, "percentage": 4.43, "elapsed_time": "0:04:33", "remaining_time": "1:38:16", "throughput": 4003.97, "total_tokens": 1094112}
|
| 339 |
+
{"current_steps": 1695, "total_steps": 38160, "loss": 0.6187, "lr": 2.219601677148847e-05, "epoch": 0.8883647798742138, "percentage": 4.44, "elapsed_time": "0:04:34", "remaining_time": "1:38:22", "throughput": 4003.82, "total_tokens": 1098496}
|
| 340 |
+
{"current_steps": 1700, "total_steps": 38160, "loss": 0.6041, "lr": 2.2261530398322853e-05, "epoch": 0.8909853249475891, "percentage": 4.45, "elapsed_time": "0:04:35", "remaining_time": "1:38:25", "throughput": 3998.3, "total_tokens": 1100992}
|
| 341 |
+
{"current_steps": 1705, "total_steps": 38160, "loss": 0.6141, "lr": 2.2327044025157233e-05, "epoch": 0.8936058700209644, "percentage": 4.47, "elapsed_time": "0:04:36", "remaining_time": "1:38:27", "throughput": 3994.67, "total_tokens": 1103776}
|
| 342 |
+
{"current_steps": 1710, "total_steps": 38160, "loss": 0.5361, "lr": 2.2392557651991616e-05, "epoch": 0.8962264150943396, "percentage": 4.48, "elapsed_time": "0:04:37", "remaining_time": "1:38:29", "throughput": 3990.77, "total_tokens": 1106368}
|
| 343 |
+
{"current_steps": 1715, "total_steps": 38160, "loss": 0.5639, "lr": 2.2458071278825996e-05, "epoch": 0.8988469601677149, "percentage": 4.49, "elapsed_time": "0:04:38", "remaining_time": "1:38:29", "throughput": 3989.39, "total_tokens": 1109376}
|
| 344 |
+
{"current_steps": 1720, "total_steps": 38160, "loss": 0.5239, "lr": 2.252358490566038e-05, "epoch": 0.9014675052410901, "percentage": 4.51, "elapsed_time": "0:04:38", "remaining_time": "1:38:30", "throughput": 3987.55, "total_tokens": 1112448}
|
| 345 |
+
{"current_steps": 1725, "total_steps": 38160, "loss": 0.5674, "lr": 2.258909853249476e-05, "epoch": 0.9040880503144654, "percentage": 4.52, "elapsed_time": "0:04:39", "remaining_time": "1:38:33", "throughput": 3984.33, "total_tokens": 1115520}
|
| 346 |
+
{"current_steps": 1730, "total_steps": 38160, "loss": 0.7186, "lr": 2.265461215932914e-05, "epoch": 0.9067085953878407, "percentage": 4.53, "elapsed_time": "0:04:40", "remaining_time": "1:38:35", "throughput": 3982.77, "total_tokens": 1118784}
|
| 347 |
+
{"current_steps": 1735, "total_steps": 38160, "loss": 0.8266, "lr": 2.2720125786163524e-05, "epoch": 0.9093291404612159, "percentage": 4.55, "elapsed_time": "0:04:41", "remaining_time": "1:38:38", "throughput": 3980.47, "total_tokens": 1122112}
|
| 348 |
+
{"current_steps": 1740, "total_steps": 38160, "loss": 0.5431, "lr": 2.2785639412997904e-05, "epoch": 0.9119496855345912, "percentage": 4.56, "elapsed_time": "0:04:42", "remaining_time": "1:38:39", "throughput": 3980.98, "total_tokens": 1125952}
|
| 349 |
+
{"current_steps": 1745, "total_steps": 38160, "loss": 0.7551, "lr": 2.2851153039832284e-05, "epoch": 0.9145702306079665, "percentage": 4.57, "elapsed_time": "0:04:43", "remaining_time": "1:38:40", "throughput": 3979.2, "total_tokens": 1129024}
|
| 350 |
+
{"current_steps": 1750, "total_steps": 38160, "loss": 0.5506, "lr": 2.2916666666666667e-05, "epoch": 0.9171907756813418, "percentage": 4.59, "elapsed_time": "0:04:44", "remaining_time": "1:38:41", "throughput": 3975.42, "total_tokens": 1131488}
|
| 351 |
+
{"current_steps": 1755, "total_steps": 38160, "loss": 0.535, "lr": 2.298218029350105e-05, "epoch": 0.9198113207547169, "percentage": 4.6, "elapsed_time": "0:04:45", "remaining_time": "1:38:43", "throughput": 3971.53, "total_tokens": 1134176}
|
| 352 |
+
{"current_steps": 1760, "total_steps": 38160, "loss": 0.6003, "lr": 2.304769392033543e-05, "epoch": 0.9224318658280922, "percentage": 4.61, "elapsed_time": "0:04:46", "remaining_time": "1:38:47", "throughput": 3970.56, "total_tokens": 1137888}
|
| 353 |
+
{"current_steps": 1765, "total_steps": 38160, "loss": 0.6974, "lr": 2.3113207547169813e-05, "epoch": 0.9250524109014675, "percentage": 4.63, "elapsed_time": "0:04:47", "remaining_time": "1:38:48", "throughput": 3969.13, "total_tokens": 1141184}
|
| 354 |
+
{"current_steps": 1770, "total_steps": 38160, "loss": 0.6366, "lr": 2.3178721174004196e-05, "epoch": 0.9276729559748428, "percentage": 4.64, "elapsed_time": "0:04:48", "remaining_time": "1:38:49", "throughput": 3966.74, "total_tokens": 1144064}
|
| 355 |
+
{"current_steps": 1775, "total_steps": 38160, "loss": 0.5468, "lr": 2.3244234800838576e-05, "epoch": 0.9302935010482181, "percentage": 4.65, "elapsed_time": "0:04:49", "remaining_time": "1:38:51", "throughput": 3965.94, "total_tokens": 1147584}
|
| 356 |
+
{"current_steps": 1780, "total_steps": 38160, "loss": 0.5392, "lr": 2.3309748427672955e-05, "epoch": 0.9329140461215933, "percentage": 4.66, "elapsed_time": "0:04:51", "remaining_time": "1:39:09", "throughput": 3967.12, "total_tokens": 1154784}
|
| 357 |
+
{"current_steps": 1785, "total_steps": 38160, "loss": 0.6265, "lr": 2.3375262054507338e-05, "epoch": 0.9355345911949685, "percentage": 4.68, "elapsed_time": "0:04:51", "remaining_time": "1:39:09", "throughput": 3964.62, "total_tokens": 1157440}
|
| 358 |
+
{"current_steps": 1790, "total_steps": 38160, "loss": 0.7302, "lr": 2.344077568134172e-05, "epoch": 0.9381551362683438, "percentage": 4.69, "elapsed_time": "0:04:52", "remaining_time": "1:39:09", "throughput": 3962.6, "total_tokens": 1160224}
|
| 359 |
+
{"current_steps": 1795, "total_steps": 38160, "loss": 0.5734, "lr": 2.35062893081761e-05, "epoch": 0.9407756813417191, "percentage": 4.7, "elapsed_time": "0:04:53", "remaining_time": "1:39:12", "throughput": 3963.46, "total_tokens": 1164480}
|
| 360 |
+
{"current_steps": 1800, "total_steps": 38160, "loss": 0.4622, "lr": 2.3571802935010484e-05, "epoch": 0.9433962264150944, "percentage": 4.72, "elapsed_time": "0:04:54", "remaining_time": "1:39:15", "throughput": 3964.17, "total_tokens": 1168704}
|
| 361 |
+
{"current_steps": 1805, "total_steps": 38160, "loss": 0.5044, "lr": 2.3637316561844867e-05, "epoch": 0.9460167714884696, "percentage": 4.73, "elapsed_time": "0:04:55", "remaining_time": "1:39:15", "throughput": 3964.66, "total_tokens": 1172384}
|
| 362 |
+
{"current_steps": 1810, "total_steps": 38160, "loss": 0.5985, "lr": 2.3702830188679247e-05, "epoch": 0.9486373165618449, "percentage": 4.74, "elapsed_time": "0:04:56", "remaining_time": "1:39:15", "throughput": 3963.63, "total_tokens": 1175392}
|
| 363 |
+
{"current_steps": 1815, "total_steps": 38160, "loss": 0.5284, "lr": 2.3768343815513627e-05, "epoch": 0.9512578616352201, "percentage": 4.76, "elapsed_time": "0:04:57", "remaining_time": "1:39:17", "throughput": 3960.55, "total_tokens": 1178368}
|
| 364 |
+
{"current_steps": 1820, "total_steps": 38160, "loss": 0.5446, "lr": 2.383385744234801e-05, "epoch": 0.9538784067085954, "percentage": 4.77, "elapsed_time": "0:04:58", "remaining_time": "1:39:21", "throughput": 3959.82, "total_tokens": 1182240}
|
| 365 |
+
{"current_steps": 1825, "total_steps": 38160, "loss": 0.5348, "lr": 2.3899371069182393e-05, "epoch": 0.9564989517819706, "percentage": 4.78, "elapsed_time": "0:04:59", "remaining_time": "1:39:22", "throughput": 3958.76, "total_tokens": 1185504}
|
| 366 |
+
{"current_steps": 1830, "total_steps": 38160, "loss": 0.5613, "lr": 2.3964884696016772e-05, "epoch": 0.9591194968553459, "percentage": 4.8, "elapsed_time": "0:05:00", "remaining_time": "1:39:23", "throughput": 3955.49, "total_tokens": 1188288}
|
| 367 |
+
{"current_steps": 1835, "total_steps": 38160, "loss": 0.4922, "lr": 2.4030398322851155e-05, "epoch": 0.9617400419287212, "percentage": 4.81, "elapsed_time": "0:05:01", "remaining_time": "1:39:26", "throughput": 3954.79, "total_tokens": 1192064}
|
| 368 |
+
{"current_steps": 1840, "total_steps": 38160, "loss": 0.5507, "lr": 2.4095911949685535e-05, "epoch": 0.9643605870020965, "percentage": 4.82, "elapsed_time": "0:05:02", "remaining_time": "1:39:26", "throughput": 3953.57, "total_tokens": 1195104}
|
| 369 |
+
{"current_steps": 1845, "total_steps": 38160, "loss": 0.7647, "lr": 2.4161425576519918e-05, "epoch": 0.9669811320754716, "percentage": 4.83, "elapsed_time": "0:05:03", "remaining_time": "1:39:29", "throughput": 3949.94, "total_tokens": 1197920}
|
| 370 |
+
{"current_steps": 1850, "total_steps": 38160, "loss": 0.5312, "lr": 2.4226939203354298e-05, "epoch": 0.9696016771488469, "percentage": 4.85, "elapsed_time": "0:05:04", "remaining_time": "1:39:30", "throughput": 3947.7, "total_tokens": 1200896}
|
| 371 |
+
{"current_steps": 1855, "total_steps": 38160, "loss": 0.5635, "lr": 2.429245283018868e-05, "epoch": 0.9722222222222222, "percentage": 4.86, "elapsed_time": "0:05:05", "remaining_time": "1:39:32", "throughput": 3945.61, "total_tokens": 1204032}
|
| 372 |
+
{"current_steps": 1860, "total_steps": 38160, "loss": 0.4591, "lr": 2.4357966457023064e-05, "epoch": 0.9748427672955975, "percentage": 4.87, "elapsed_time": "0:05:06", "remaining_time": "1:39:34", "throughput": 3943.51, "total_tokens": 1207264}
|
| 373 |
+
{"current_steps": 1865, "total_steps": 38160, "loss": 0.6502, "lr": 2.4423480083857444e-05, "epoch": 0.9774633123689728, "percentage": 4.89, "elapsed_time": "0:05:07", "remaining_time": "1:39:35", "throughput": 3940.46, "total_tokens": 1209984}
|
| 374 |
+
{"current_steps": 1870, "total_steps": 38160, "loss": 0.4914, "lr": 2.4488993710691823e-05, "epoch": 0.980083857442348, "percentage": 4.9, "elapsed_time": "0:05:08", "remaining_time": "1:39:39", "throughput": 3939.83, "total_tokens": 1213856}
|
| 375 |
+
{"current_steps": 1875, "total_steps": 38160, "loss": 0.4778, "lr": 2.4554507337526206e-05, "epoch": 0.9827044025157232, "percentage": 4.91, "elapsed_time": "0:05:09", "remaining_time": "1:39:39", "throughput": 3939.75, "total_tokens": 1217408}
|
| 376 |
+
{"current_steps": 1880, "total_steps": 38160, "loss": 0.5747, "lr": 2.4620020964360586e-05, "epoch": 0.9853249475890985, "percentage": 4.93, "elapsed_time": "0:05:09", "remaining_time": "1:39:40", "throughput": 3940.16, "total_tokens": 1221024}
|
| 377 |
+
{"current_steps": 1885, "total_steps": 38160, "loss": 0.4637, "lr": 2.468553459119497e-05, "epoch": 0.9879454926624738, "percentage": 4.94, "elapsed_time": "0:05:10", "remaining_time": "1:39:38", "throughput": 3940.8, "total_tokens": 1224320}
|
| 378 |
+
{"current_steps": 1890, "total_steps": 38160, "loss": 0.4419, "lr": 2.4751048218029352e-05, "epoch": 0.9905660377358491, "percentage": 4.95, "elapsed_time": "0:05:11", "remaining_time": "1:39:40", "throughput": 3940.69, "total_tokens": 1228000}
|
| 379 |
+
{"current_steps": 1895, "total_steps": 38160, "loss": 0.5499, "lr": 2.4816561844863735e-05, "epoch": 0.9931865828092243, "percentage": 4.97, "elapsed_time": "0:05:12", "remaining_time": "1:39:43", "throughput": 3941.21, "total_tokens": 1232320}
|
| 380 |
+
{"current_steps": 1900, "total_steps": 38160, "loss": 0.6565, "lr": 2.488207547169811e-05, "epoch": 0.9958071278825996, "percentage": 4.98, "elapsed_time": "0:05:14", "remaining_time": "1:39:56", "throughput": 3940.84, "total_tokens": 1238272}
|
| 381 |
+
{"current_steps": 1905, "total_steps": 38160, "loss": 0.5784, "lr": 2.4947589098532495e-05, "epoch": 0.9984276729559748, "percentage": 4.99, "elapsed_time": "0:05:15", "remaining_time": "1:39:58", "throughput": 3938.57, "total_tokens": 1241344}
|
| 382 |
+
{"current_steps": 1908, "total_steps": 38160, "eval_loss": 0.5528630614280701, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:05:25", "remaining_time": "1:43:07", "throughput": 3817.01, "total_tokens": 1243048}
|
| 383 |
+
{"current_steps": 1910, "total_steps": 38160, "loss": 0.4905, "lr": 2.5013102725366878e-05, "epoch": 1.00104821802935, "percentage": 5.01, "elapsed_time": "0:05:27", "remaining_time": "1:43:34", "throughput": 3800.91, "total_tokens": 1244520}
|
| 384 |
+
{"current_steps": 1915, "total_steps": 38160, "loss": 0.5776, "lr": 2.507861635220126e-05, "epoch": 1.0036687631027255, "percentage": 5.02, "elapsed_time": "0:05:28", "remaining_time": "1:43:34", "throughput": 3799.34, "total_tokens": 1247528}
|
| 385 |
+
{"current_steps": 1920, "total_steps": 38160, "loss": 0.6784, "lr": 2.514412997903564e-05, "epoch": 1.0062893081761006, "percentage": 5.03, "elapsed_time": "0:05:29", "remaining_time": "1:43:34", "throughput": 3799.05, "total_tokens": 1250824}
|
| 386 |
+
{"current_steps": 1925, "total_steps": 38160, "loss": 0.5598, "lr": 2.520964360587002e-05, "epoch": 1.0089098532494758, "percentage": 5.04, "elapsed_time": "0:05:30", "remaining_time": "1:43:34", "throughput": 3798.17, "total_tokens": 1254024}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7027d103a00865b3a791fc9cb6a8100d7aa0cd9bb003fc1520aad89a83c8555
|
| 3 |
+
size 6353
|