Training in progress, step 1908
Browse files- .gitattributes +1 -0
- adapter_config.json +17 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +26 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2077 -0
- train.yaml +60 -0
- trainer_log.jsonl +387 -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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
| 4 |
+
"encoder_dropout": 0.1,
|
| 5 |
+
"encoder_hidden_size": 768,
|
| 6 |
+
"encoder_num_layers": 2,
|
| 7 |
+
"encoder_reparameterization_type": "MLP",
|
| 8 |
+
"inference_mode": true,
|
| 9 |
+
"num_attention_heads": 32,
|
| 10 |
+
"num_layers": 32,
|
| 11 |
+
"num_transformer_submodules": 1,
|
| 12 |
+
"num_virtual_tokens": 100,
|
| 13 |
+
"peft_type": "P_TUNING",
|
| 14 |
+
"revision": null,
|
| 15 |
+
"task_type": "CAUSAL_LM",
|
| 16 |
+
"token_dim": 4096
|
| 17 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:90d11120862d37e89056d80c0c8c60ddb983f30bb823fa36b59e8f7acc61e20c
|
| 3 |
+
size 1638528
|
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 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
seed: 101112
|
| 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: p-tuning
|
| 13 |
+
task_type: CAUSAL_LM
|
| 14 |
+
num_virtual_tokens: 100
|
| 15 |
+
encoder_reparameterization_type: MLP
|
| 16 |
+
encoder_hidden_size: 768
|
| 17 |
+
encoder_dropout: 0.1
|
| 18 |
+
|
| 19 |
+
### dataset
|
| 20 |
+
dataset: codealpacapy
|
| 21 |
+
template: llama3
|
| 22 |
+
cutoff_len: 2048
|
| 23 |
+
overwrite_cache: true
|
| 24 |
+
preprocessing_num_workers: 8
|
| 25 |
+
dataloader_num_workers: 2
|
| 26 |
+
packing: false
|
| 27 |
+
|
| 28 |
+
### output
|
| 29 |
+
output_dir: saves_multiple/p-tuning/llama-3-8b-instruct/train_codealpacapy_101112_1770438262
|
| 30 |
+
logging_steps: 5
|
| 31 |
+
save_steps: 0.05
|
| 32 |
+
overwrite_output_dir: true
|
| 33 |
+
save_only_model: false
|
| 34 |
+
plot_loss: true
|
| 35 |
+
include_num_input_tokens_seen: true
|
| 36 |
+
push_to_hub: true
|
| 37 |
+
push_to_hub_organization: rbelanec
|
| 38 |
+
load_best_model_at_end: true
|
| 39 |
+
save_total_limit: 1
|
| 40 |
+
|
| 41 |
+
### train
|
| 42 |
+
per_device_train_batch_size: 4
|
| 43 |
+
learning_rate: 1.0e-3
|
| 44 |
+
num_train_epochs: 20
|
| 45 |
+
weight_decay: 1.0e-5
|
| 46 |
+
lr_scheduler_type: cosine
|
| 47 |
+
bf16: true
|
| 48 |
+
ddp_timeout: 180000000
|
| 49 |
+
resume_from_checkpoint: null
|
| 50 |
+
warmup_ratio: 0.1
|
| 51 |
+
optim: adamw_torch
|
| 52 |
+
report_to:
|
| 53 |
+
- wandb
|
| 54 |
+
run_name: p-tuning_llama-3-8b-instruct_train_codealpacapy_101112_1770438262
|
| 55 |
+
|
| 56 |
+
### eval
|
| 57 |
+
per_device_eval_batch_size: 4
|
| 58 |
+
eval_strategy: steps
|
| 59 |
+
eval_steps: 0.05
|
| 60 |
+
val_size: 0.1
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,387 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 38160, "loss": 5.087, "lr": 1.0482180293501048e-06, "epoch": 0.002620545073375262, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "3:17:09", "throughput": 2415.21, "total_tokens": 3744}
|
| 2 |
+
{"current_steps": 10, "total_steps": 38160, "loss": 4.7413, "lr": 2.358490566037736e-06, "epoch": 0.005241090146750524, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "2:27:50", "throughput": 3220.27, "total_tokens": 7488}
|
| 3 |
+
{"current_steps": 15, "total_steps": 38160, "loss": 4.8611, "lr": 3.668763102725367e-06, "epoch": 0.007861635220125786, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:07:54", "throughput": 3467.3, "total_tokens": 10464}
|
| 4 |
+
{"current_steps": 20, "total_steps": 38160, "loss": 4.1091, "lr": 4.979035639412998e-06, "epoch": 0.010482180293501049, "percentage": 0.05, "elapsed_time": "0:00:03", "remaining_time": "1:57:56", "throughput": 3647.59, "total_tokens": 13536}
|
| 5 |
+
{"current_steps": 25, "total_steps": 38160, "loss": 2.8262, "lr": 6.289308176100629e-06, "epoch": 0.01310272536687631, "percentage": 0.07, "elapsed_time": "0:00:04", "remaining_time": "1:57:11", "throughput": 3942.94, "total_tokens": 18176}
|
| 6 |
+
{"current_steps": 30, "total_steps": 38160, "loss": 1.9392, "lr": 7.59958071278826e-06, "epoch": 0.015723270440251572, "percentage": 0.08, "elapsed_time": "0:00:05", "remaining_time": "1:52:30", "throughput": 3988.81, "total_tokens": 21184}
|
| 7 |
+
{"current_steps": 35, "total_steps": 38160, "loss": 1.1864, "lr": 8.90985324947589e-06, "epoch": 0.018343815513626835, "percentage": 0.09, "elapsed_time": "0:00:05", "remaining_time": "1:48:21", "throughput": 4015.78, "total_tokens": 23968}
|
| 8 |
+
{"current_steps": 40, "total_steps": 38160, "loss": 0.8954, "lr": 1.0220125786163522e-05, "epoch": 0.020964360587002098, "percentage": 0.1, "elapsed_time": "0:00:06", "remaining_time": "1:47:14", "throughput": 4104.42, "total_tokens": 27712}
|
| 9 |
+
{"current_steps": 45, "total_steps": 38160, "loss": 0.974, "lr": 1.1530398322851153e-05, "epoch": 0.02358490566037736, "percentage": 0.12, "elapsed_time": "0:00:07", "remaining_time": "1:44:56", "throughput": 4114.98, "total_tokens": 30592}
|
| 10 |
+
{"current_steps": 50, "total_steps": 38160, "loss": 0.8576, "lr": 1.2840670859538784e-05, "epoch": 0.02620545073375262, "percentage": 0.13, "elapsed_time": "0:00:08", "remaining_time": "1:43:02", "throughput": 4122.51, "total_tokens": 33440}
|
| 11 |
+
{"current_steps": 55, "total_steps": 38160, "loss": 1.0613, "lr": 1.4150943396226415e-05, "epoch": 0.028825995807127882, "percentage": 0.14, "elapsed_time": "0:00:08", "remaining_time": "1:42:54", "throughput": 4190.21, "total_tokens": 37344}
|
| 12 |
+
{"current_steps": 60, "total_steps": 38160, "loss": 0.8696, "lr": 1.5461215932914046e-05, "epoch": 0.031446540880503145, "percentage": 0.16, "elapsed_time": "0:00:09", "remaining_time": "1:42:24", "throughput": 4236.15, "total_tokens": 40992}
|
| 13 |
+
{"current_steps": 65, "total_steps": 38160, "loss": 0.6031, "lr": 1.6771488469601677e-05, "epoch": 0.034067085953878404, "percentage": 0.17, "elapsed_time": "0:00:10", "remaining_time": "1:40:54", "throughput": 4224.92, "total_tokens": 43648}
|
| 14 |
+
{"current_steps": 70, "total_steps": 38160, "loss": 0.6284, "lr": 1.8081761006289308e-05, "epoch": 0.03668763102725367, "percentage": 0.18, "elapsed_time": "0:00:11", "remaining_time": "1:40:16", "throughput": 4248.67, "total_tokens": 46976}
|
| 15 |
+
{"current_steps": 75, "total_steps": 38160, "loss": 0.6625, "lr": 1.9392033542976942e-05, "epoch": 0.03930817610062893, "percentage": 0.2, "elapsed_time": "0:00:11", "remaining_time": "1:39:52", "throughput": 4278.72, "total_tokens": 50496}
|
| 16 |
+
{"current_steps": 80, "total_steps": 38160, "loss": 0.6551, "lr": 2.070230607966457e-05, "epoch": 0.041928721174004195, "percentage": 0.21, "elapsed_time": "0:00:12", "remaining_time": "1:39:09", "throughput": 4280.66, "total_tokens": 53504}
|
| 17 |
+
{"current_steps": 85, "total_steps": 38160, "loss": 0.6627, "lr": 2.20125786163522e-05, "epoch": 0.044549266247379454, "percentage": 0.22, "elapsed_time": "0:00:13", "remaining_time": "1:38:00", "throughput": 4268.28, "total_tokens": 56032}
|
| 18 |
+
{"current_steps": 90, "total_steps": 38160, "loss": 0.6161, "lr": 2.3322851153039832e-05, "epoch": 0.04716981132075472, "percentage": 0.24, "elapsed_time": "0:00:13", "remaining_time": "1:37:44", "throughput": 4283.97, "total_tokens": 59392}
|
| 19 |
+
{"current_steps": 95, "total_steps": 38160, "loss": 0.5914, "lr": 2.4633123689727463e-05, "epoch": 0.04979035639412998, "percentage": 0.25, "elapsed_time": "0:00:14", "remaining_time": "1:37:37", "throughput": 4305.46, "total_tokens": 62944}
|
| 20 |
+
{"current_steps": 100, "total_steps": 38160, "loss": 0.4944, "lr": 2.5943396226415097e-05, "epoch": 0.05241090146750524, "percentage": 0.26, "elapsed_time": "0:00:15", "remaining_time": "1:37:30", "throughput": 4322.03, "total_tokens": 66432}
|
| 21 |
+
{"current_steps": 105, "total_steps": 38160, "loss": 0.7286, "lr": 2.7253668763102725e-05, "epoch": 0.055031446540880505, "percentage": 0.28, "elapsed_time": "0:00:16", "remaining_time": "1:36:54", "throughput": 4318.03, "total_tokens": 69280}
|
| 22 |
+
{"current_steps": 110, "total_steps": 38160, "loss": 0.5197, "lr": 2.8563941299790356e-05, "epoch": 0.057651991614255764, "percentage": 0.29, "elapsed_time": "0:00:16", "remaining_time": "1:37:00", "throughput": 4343.78, "total_tokens": 73088}
|
| 23 |
+
{"current_steps": 115, "total_steps": 38160, "loss": 0.7644, "lr": 2.987421383647799e-05, "epoch": 0.06027253668763103, "percentage": 0.3, "elapsed_time": "0:00:17", "remaining_time": "1:36:25", "throughput": 4336.5, "total_tokens": 75840}
|
| 24 |
+
{"current_steps": 120, "total_steps": 38160, "loss": 0.4954, "lr": 3.118448637316562e-05, "epoch": 0.06289308176100629, "percentage": 0.31, "elapsed_time": "0:00:18", "remaining_time": "1:36:07", "throughput": 4342.46, "total_tokens": 79008}
|
| 25 |
+
{"current_steps": 125, "total_steps": 38160, "loss": 0.5742, "lr": 3.2494758909853245e-05, "epoch": 0.06551362683438156, "percentage": 0.33, "elapsed_time": "0:00:18", "remaining_time": "1:35:39", "throughput": 4339.72, "total_tokens": 81856}
|
| 26 |
+
{"current_steps": 130, "total_steps": 38160, "loss": 0.472, "lr": 3.380503144654088e-05, "epoch": 0.06813417190775681, "percentage": 0.34, "elapsed_time": "0:00:19", "remaining_time": "1:35:30", "throughput": 4345.62, "total_tokens": 85120}
|
| 27 |
+
{"current_steps": 135, "total_steps": 38160, "loss": 0.6883, "lr": 3.5115303983228514e-05, "epoch": 0.07075471698113207, "percentage": 0.35, "elapsed_time": "0:00:20", "remaining_time": "1:35:07", "throughput": 4344.09, "total_tokens": 88032}
|
| 28 |
+
{"current_steps": 140, "total_steps": 38160, "loss": 0.4858, "lr": 3.642557651991614e-05, "epoch": 0.07337526205450734, "percentage": 0.37, "elapsed_time": "0:00:20", "remaining_time": "1:34:52", "throughput": 4346.14, "total_tokens": 91104}
|
| 29 |
+
{"current_steps": 145, "total_steps": 38160, "loss": 0.5975, "lr": 3.7735849056603776e-05, "epoch": 0.0759958071278826, "percentage": 0.38, "elapsed_time": "0:00:21", "remaining_time": "1:34:33", "throughput": 4343.37, "total_tokens": 93984}
|
| 30 |
+
{"current_steps": 150, "total_steps": 38160, "loss": 0.5246, "lr": 3.90461215932914e-05, "epoch": 0.07861635220125786, "percentage": 0.39, "elapsed_time": "0:00:22", "remaining_time": "1:34:11", "throughput": 4343.52, "total_tokens": 96864}
|
| 31 |
+
{"current_steps": 155, "total_steps": 38160, "loss": 0.5665, "lr": 4.035639412997904e-05, "epoch": 0.08123689727463312, "percentage": 0.41, "elapsed_time": "0:00:22", "remaining_time": "1:33:49", "throughput": 4339.94, "total_tokens": 99648}
|
| 32 |
+
{"current_steps": 160, "total_steps": 38160, "loss": 1.0498, "lr": 4.1666666666666665e-05, "epoch": 0.08385744234800839, "percentage": 0.42, "elapsed_time": "0:00:23", "remaining_time": "1:33:44", "throughput": 4345.72, "total_tokens": 102912}
|
| 33 |
+
{"current_steps": 165, "total_steps": 38160, "loss": 0.5317, "lr": 4.29769392033543e-05, "epoch": 0.08647798742138364, "percentage": 0.43, "elapsed_time": "0:00:24", "remaining_time": "1:33:20", "throughput": 4340.22, "total_tokens": 105568}
|
| 34 |
+
{"current_steps": 170, "total_steps": 38160, "loss": 0.6695, "lr": 4.4287211740041934e-05, "epoch": 0.08909853249475891, "percentage": 0.45, "elapsed_time": "0:00:24", "remaining_time": "1:33:01", "throughput": 4338.37, "total_tokens": 108352}
|
| 35 |
+
{"current_steps": 175, "total_steps": 38160, "loss": 0.6232, "lr": 4.5597484276729555e-05, "epoch": 0.09171907756813417, "percentage": 0.46, "elapsed_time": "0:00:25", "remaining_time": "1:32:41", "throughput": 4331.09, "total_tokens": 110976}
|
| 36 |
+
{"current_steps": 180, "total_steps": 38160, "loss": 0.4586, "lr": 4.690775681341719e-05, "epoch": 0.09433962264150944, "percentage": 0.47, "elapsed_time": "0:00:26", "remaining_time": "1:32:35", "throughput": 4336.7, "total_tokens": 114176}
|
| 37 |
+
{"current_steps": 185, "total_steps": 38160, "loss": 0.5218, "lr": 4.8218029350104823e-05, "epoch": 0.09696016771488469, "percentage": 0.48, "elapsed_time": "0:00:27", "remaining_time": "1:32:24", "throughput": 4334.02, "total_tokens": 117056}
|
| 38 |
+
{"current_steps": 190, "total_steps": 38160, "loss": 0.5845, "lr": 4.952830188679246e-05, "epoch": 0.09958071278825996, "percentage": 0.5, "elapsed_time": "0:00:27", "remaining_time": "1:32:23", "throughput": 4339.93, "total_tokens": 120384}
|
| 39 |
+
{"current_steps": 195, "total_steps": 38160, "loss": 0.6016, "lr": 5.0838574423480085e-05, "epoch": 0.10220125786163523, "percentage": 0.51, "elapsed_time": "0:00:28", "remaining_time": "1:32:16", "throughput": 4341.69, "total_tokens": 123456}
|
| 40 |
+
{"current_steps": 200, "total_steps": 38160, "loss": 0.4651, "lr": 5.214884696016771e-05, "epoch": 0.10482180293501048, "percentage": 0.52, "elapsed_time": "0:00:29", "remaining_time": "1:31:56", "throughput": 4334.76, "total_tokens": 125984}
|
| 41 |
+
{"current_steps": 205, "total_steps": 38160, "loss": 0.7034, "lr": 5.345911949685535e-05, "epoch": 0.10744234800838574, "percentage": 0.54, "elapsed_time": "0:00:29", "remaining_time": "1:31:57", "throughput": 4338.01, "total_tokens": 129280}
|
| 42 |
+
{"current_steps": 210, "total_steps": 38160, "loss": 0.6468, "lr": 5.4769392033542975e-05, "epoch": 0.11006289308176101, "percentage": 0.55, "elapsed_time": "0:00:30", "remaining_time": "1:31:45", "throughput": 4336.27, "total_tokens": 132096}
|
| 43 |
+
{"current_steps": 215, "total_steps": 38160, "loss": 0.5377, "lr": 5.607966457023061e-05, "epoch": 0.11268343815513626, "percentage": 0.56, "elapsed_time": "0:00:31", "remaining_time": "1:31:33", "throughput": 4333.18, "total_tokens": 134880}
|
| 44 |
+
{"current_steps": 220, "total_steps": 38160, "loss": 0.5866, "lr": 5.7389937106918244e-05, "epoch": 0.11530398322851153, "percentage": 0.58, "elapsed_time": "0:00:31", "remaining_time": "1:31:26", "throughput": 4332.33, "total_tokens": 137824}
|
| 45 |
+
{"current_steps": 225, "total_steps": 38160, "loss": 0.52, "lr": 5.870020964360587e-05, "epoch": 0.1179245283018868, "percentage": 0.59, "elapsed_time": "0:00:32", "remaining_time": "1:31:21", "throughput": 4332.04, "total_tokens": 140832}
|
| 46 |
+
{"current_steps": 230, "total_steps": 38160, "loss": 0.4795, "lr": 6.00104821802935e-05, "epoch": 0.12054507337526206, "percentage": 0.6, "elapsed_time": "0:00:33", "remaining_time": "1:31:32", "throughput": 4344.37, "total_tokens": 144704}
|
| 47 |
+
{"current_steps": 235, "total_steps": 38160, "loss": 0.5782, "lr": 6.132075471698113e-05, "epoch": 0.12316561844863731, "percentage": 0.62, "elapsed_time": "0:00:33", "remaining_time": "1:31:23", "throughput": 4342.16, "total_tokens": 147552}
|
| 48 |
+
{"current_steps": 240, "total_steps": 38160, "loss": 0.6854, "lr": 6.263102725366875e-05, "epoch": 0.12578616352201258, "percentage": 0.63, "elapsed_time": "0:00:34", "remaining_time": "1:31:25", "throughput": 4346.71, "total_tokens": 150912}
|
| 49 |
+
{"current_steps": 245, "total_steps": 38160, "loss": 0.5103, "lr": 6.39412997903564e-05, "epoch": 0.12840670859538783, "percentage": 0.64, "elapsed_time": "0:00:35", "remaining_time": "1:31:18", "throughput": 4345.28, "total_tokens": 153824}
|
| 50 |
+
{"current_steps": 250, "total_steps": 38160, "loss": 0.5253, "lr": 6.525157232704402e-05, "epoch": 0.1310272536687631, "percentage": 0.66, "elapsed_time": "0:00:36", "remaining_time": "1:31:14", "throughput": 4346.64, "total_tokens": 156928}
|
| 51 |
+
{"current_steps": 255, "total_steps": 38160, "loss": 0.4905, "lr": 6.656184486373166e-05, "epoch": 0.13364779874213836, "percentage": 0.67, "elapsed_time": "0:00:36", "remaining_time": "1:31:25", "throughput": 4361.05, "total_tokens": 160928}
|
| 52 |
+
{"current_steps": 260, "total_steps": 38160, "loss": 0.3949, "lr": 6.787211740041929e-05, "epoch": 0.13626834381551362, "percentage": 0.68, "elapsed_time": "0:00:37", "remaining_time": "1:31:23", "throughput": 4362.48, "total_tokens": 164096}
|
| 53 |
+
{"current_steps": 265, "total_steps": 38160, "loss": 0.5952, "lr": 6.918238993710691e-05, "epoch": 0.1388888888888889, "percentage": 0.69, "elapsed_time": "0:00:38", "remaining_time": "1:31:21", "throughput": 4363.58, "total_tokens": 167264}
|
| 54 |
+
{"current_steps": 270, "total_steps": 38160, "loss": 0.5757, "lr": 7.049266247379455e-05, "epoch": 0.14150943396226415, "percentage": 0.71, "elapsed_time": "0:00:39", "remaining_time": "1:31:18", "throughput": 4364.71, "total_tokens": 170400}
|
| 55 |
+
{"current_steps": 275, "total_steps": 38160, "loss": 0.5771, "lr": 7.180293501048218e-05, "epoch": 0.1441299790356394, "percentage": 0.72, "elapsed_time": "0:00:39", "remaining_time": "1:31:23", "throughput": 4371.44, "total_tokens": 173984}
|
| 56 |
+
{"current_steps": 280, "total_steps": 38160, "loss": 0.463, "lr": 7.311320754716982e-05, "epoch": 0.14675052410901468, "percentage": 0.73, "elapsed_time": "0:00:40", "remaining_time": "1:31:13", "throughput": 4367.19, "total_tokens": 176704}
|
| 57 |
+
{"current_steps": 285, "total_steps": 38160, "loss": 0.4607, "lr": 7.442348008385745e-05, "epoch": 0.14937106918238993, "percentage": 0.75, "elapsed_time": "0:00:41", "remaining_time": "1:31:06", "throughput": 4366.59, "total_tokens": 179616}
|
| 58 |
+
{"current_steps": 290, "total_steps": 38160, "loss": 0.5602, "lr": 7.573375262054507e-05, "epoch": 0.1519916142557652, "percentage": 0.76, "elapsed_time": "0:00:41", "remaining_time": "1:31:03", "throughput": 4364.82, "total_tokens": 182624}
|
| 59 |
+
{"current_steps": 295, "total_steps": 38160, "loss": 0.4618, "lr": 7.70440251572327e-05, "epoch": 0.15461215932914046, "percentage": 0.77, "elapsed_time": "0:00:42", "remaining_time": "1:30:59", "throughput": 4363.39, "total_tokens": 185600}
|
| 60 |
+
{"current_steps": 300, "total_steps": 38160, "loss": 0.5899, "lr": 7.835429769392034e-05, "epoch": 0.15723270440251572, "percentage": 0.79, "elapsed_time": "0:00:43", "remaining_time": "1:31:13", "throughput": 4374.72, "total_tokens": 189728}
|
| 61 |
+
{"current_steps": 305, "total_steps": 38160, "loss": 0.6022, "lr": 7.966457023060797e-05, "epoch": 0.159853249475891, "percentage": 0.8, "elapsed_time": "0:00:44", "remaining_time": "1:31:12", "throughput": 4378.32, "total_tokens": 193056}
|
| 62 |
+
{"current_steps": 310, "total_steps": 38160, "loss": 0.5924, "lr": 8.09748427672956e-05, "epoch": 0.16247379454926625, "percentage": 0.81, "elapsed_time": "0:00:44", "remaining_time": "1:31:13", "throughput": 4380.9, "total_tokens": 196384}
|
| 63 |
+
{"current_steps": 315, "total_steps": 38160, "loss": 0.5828, "lr": 8.228511530398323e-05, "epoch": 0.1650943396226415, "percentage": 0.83, "elapsed_time": "0:00:45", "remaining_time": "1:31:23", "throughput": 4387.08, "total_tokens": 200224}
|
| 64 |
+
{"current_steps": 320, "total_steps": 38160, "loss": 0.4643, "lr": 8.359538784067086e-05, "epoch": 0.16771488469601678, "percentage": 0.84, "elapsed_time": "0:00:46", "remaining_time": "1:31:24", "throughput": 4389.54, "total_tokens": 203584}
|
| 65 |
+
{"current_steps": 325, "total_steps": 38160, "loss": 0.419, "lr": 8.490566037735848e-05, "epoch": 0.17033542976939203, "percentage": 0.85, "elapsed_time": "0:00:47", "remaining_time": "1:31:13", "throughput": 4385.55, "total_tokens": 206208}
|
| 66 |
+
{"current_steps": 330, "total_steps": 38160, "loss": 0.4865, "lr": 8.621593291404613e-05, "epoch": 0.17295597484276728, "percentage": 0.86, "elapsed_time": "0:00:47", "remaining_time": "1:31:23", "throughput": 4391.56, "total_tokens": 210048}
|
| 67 |
+
{"current_steps": 335, "total_steps": 38160, "loss": 0.5182, "lr": 8.752620545073375e-05, "epoch": 0.17557651991614256, "percentage": 0.88, "elapsed_time": "0:00:48", "remaining_time": "1:31:24", "throughput": 4395.09, "total_tokens": 213472}
|
| 68 |
+
{"current_steps": 340, "total_steps": 38160, "loss": 0.6853, "lr": 8.883647798742137e-05, "epoch": 0.17819706498951782, "percentage": 0.89, "elapsed_time": "0:00:49", "remaining_time": "1:31:30", "throughput": 4402.63, "total_tokens": 217312}
|
| 69 |
+
{"current_steps": 345, "total_steps": 38160, "loss": 0.5153, "lr": 9.014675052410902e-05, "epoch": 0.18081761006289307, "percentage": 0.9, "elapsed_time": "0:00:50", "remaining_time": "1:31:24", "throughput": 4400.97, "total_tokens": 220224}
|
| 70 |
+
{"current_steps": 350, "total_steps": 38160, "loss": 0.4777, "lr": 9.145702306079664e-05, "epoch": 0.18343815513626835, "percentage": 0.92, "elapsed_time": "0:00:50", "remaining_time": "1:31:26", "throughput": 4403.65, "total_tokens": 223648}
|
| 71 |
+
{"current_steps": 355, "total_steps": 38160, "loss": 0.5687, "lr": 9.276729559748428e-05, "epoch": 0.1860587002096436, "percentage": 0.93, "elapsed_time": "0:00:51", "remaining_time": "1:31:17", "throughput": 4400.62, "total_tokens": 226336}
|
| 72 |
+
{"current_steps": 360, "total_steps": 38160, "loss": 0.4275, "lr": 9.407756813417191e-05, "epoch": 0.18867924528301888, "percentage": 0.94, "elapsed_time": "0:00:52", "remaining_time": "1:31:06", "throughput": 4395.58, "total_tokens": 228832}
|
| 73 |
+
{"current_steps": 365, "total_steps": 38160, "loss": 0.7019, "lr": 9.538784067085953e-05, "epoch": 0.19129979035639413, "percentage": 0.96, "elapsed_time": "0:00:52", "remaining_time": "1:31:04", "throughput": 4395.95, "total_tokens": 231968}
|
| 74 |
+
{"current_steps": 370, "total_steps": 38160, "loss": 0.54, "lr": 9.669811320754718e-05, "epoch": 0.19392033542976939, "percentage": 0.97, "elapsed_time": "0:00:53", "remaining_time": "1:31:13", "throughput": 4403.49, "total_tokens": 236000}
|
| 75 |
+
{"current_steps": 375, "total_steps": 38160, "loss": 0.7747, "lr": 9.80083857442348e-05, "epoch": 0.19654088050314467, "percentage": 0.98, "elapsed_time": "0:00:54", "remaining_time": "1:31:15", "throughput": 4404.66, "total_tokens": 239360}
|
| 76 |
+
{"current_steps": 380, "total_steps": 38160, "loss": 0.6216, "lr": 9.931865828092243e-05, "epoch": 0.19916142557651992, "percentage": 1.0, "elapsed_time": "0:00:55", "remaining_time": "1:31:21", "throughput": 4410.22, "total_tokens": 243168}
|
| 77 |
+
{"current_steps": 385, "total_steps": 38160, "loss": 0.4984, "lr": 0.00010062893081761007, "epoch": 0.20178197064989517, "percentage": 1.01, "elapsed_time": "0:00:55", "remaining_time": "1:31:29", "throughput": 4417.74, "total_tokens": 247168}
|
| 78 |
+
{"current_steps": 390, "total_steps": 38160, "loss": 0.5427, "lr": 0.0001019392033542977, "epoch": 0.20440251572327045, "percentage": 1.02, "elapsed_time": "0:00:56", "remaining_time": "1:31:28", "throughput": 4418.19, "total_tokens": 250400}
|
| 79 |
+
{"current_steps": 395, "total_steps": 38160, "loss": 0.4951, "lr": 0.00010324947589098532, "epoch": 0.2070230607966457, "percentage": 1.04, "elapsed_time": "0:00:57", "remaining_time": "1:31:24", "throughput": 4417.26, "total_tokens": 253376}
|
| 80 |
+
{"current_steps": 400, "total_steps": 38160, "loss": 0.687, "lr": 0.00010455974842767296, "epoch": 0.20964360587002095, "percentage": 1.05, "elapsed_time": "0:00:58", "remaining_time": "1:31:21", "throughput": 4416.61, "total_tokens": 256448}
|
| 81 |
+
{"current_steps": 405, "total_steps": 38160, "loss": 0.6679, "lr": 0.00010587002096436059, "epoch": 0.21226415094339623, "percentage": 1.06, "elapsed_time": "0:00:58", "remaining_time": "1:31:28", "throughput": 4422.81, "total_tokens": 260384}
|
| 82 |
+
{"current_steps": 410, "total_steps": 38160, "loss": 0.6014, "lr": 0.00010718029350104821, "epoch": 0.2148846960167715, "percentage": 1.07, "elapsed_time": "0:00:59", "remaining_time": "1:31:23", "throughput": 4420.85, "total_tokens": 263264}
|
| 83 |
+
{"current_steps": 415, "total_steps": 38160, "loss": 0.4912, "lr": 0.00010849056603773586, "epoch": 0.21750524109014674, "percentage": 1.09, "elapsed_time": "0:01:00", "remaining_time": "1:31:21", "throughput": 4420.05, "total_tokens": 266400}
|
| 84 |
+
{"current_steps": 420, "total_steps": 38160, "loss": 0.462, "lr": 0.00010980083857442348, "epoch": 0.22012578616352202, "percentage": 1.1, "elapsed_time": "0:01:00", "remaining_time": "1:31:20", "throughput": 4420.66, "total_tokens": 269600}
|
| 85 |
+
{"current_steps": 425, "total_steps": 38160, "loss": 0.4315, "lr": 0.0001111111111111111, "epoch": 0.22274633123689727, "percentage": 1.11, "elapsed_time": "0:01:01", "remaining_time": "1:31:20", "throughput": 4422.96, "total_tokens": 272992}
|
| 86 |
+
{"current_steps": 430, "total_steps": 38160, "loss": 0.5666, "lr": 0.00011242138364779875, "epoch": 0.22536687631027252, "percentage": 1.13, "elapsed_time": "0:01:02", "remaining_time": "1:31:28", "throughput": 4429.34, "total_tokens": 277056}
|
| 87 |
+
{"current_steps": 435, "total_steps": 38160, "loss": 0.553, "lr": 0.00011373165618448637, "epoch": 0.2279874213836478, "percentage": 1.14, "elapsed_time": "0:01:03", "remaining_time": "1:31:23", "throughput": 4427.62, "total_tokens": 279968}
|
| 88 |
+
{"current_steps": 440, "total_steps": 38160, "loss": 0.4713, "lr": 0.00011504192872117402, "epoch": 0.23060796645702306, "percentage": 1.15, "elapsed_time": "0:01:03", "remaining_time": "1:31:16", "throughput": 4424.11, "total_tokens": 282624}
|
| 89 |
+
{"current_steps": 445, "total_steps": 38160, "loss": 0.5849, "lr": 0.00011635220125786164, "epoch": 0.23322851153039834, "percentage": 1.17, "elapsed_time": "0:01:04", "remaining_time": "1:31:08", "throughput": 4420.67, "total_tokens": 285248}
|
| 90 |
+
{"current_steps": 450, "total_steps": 38160, "loss": 0.5078, "lr": 0.00011766247379454926, "epoch": 0.2358490566037736, "percentage": 1.18, "elapsed_time": "0:01:05", "remaining_time": "1:30:58", "throughput": 4415.85, "total_tokens": 287648}
|
| 91 |
+
{"current_steps": 455, "total_steps": 38160, "loss": 0.8014, "lr": 0.00011897274633123691, "epoch": 0.23846960167714884, "percentage": 1.19, "elapsed_time": "0:01:05", "remaining_time": "1:30:49", "throughput": 4410.61, "total_tokens": 290048}
|
| 92 |
+
{"current_steps": 460, "total_steps": 38160, "loss": 0.6081, "lr": 0.00012028301886792453, "epoch": 0.24109014675052412, "percentage": 1.21, "elapsed_time": "0:01:06", "remaining_time": "1:30:45", "throughput": 4409.9, "total_tokens": 293024}
|
| 93 |
+
{"current_steps": 465, "total_steps": 38160, "loss": 0.5142, "lr": 0.00012159329140461216, "epoch": 0.24371069182389937, "percentage": 1.22, "elapsed_time": "0:01:07", "remaining_time": "1:30:52", "throughput": 4415.04, "total_tokens": 296960}
|
| 94 |
+
{"current_steps": 470, "total_steps": 38160, "loss": 0.4685, "lr": 0.0001229035639412998, "epoch": 0.24633123689727462, "percentage": 1.23, "elapsed_time": "0:01:07", "remaining_time": "1:30:48", "throughput": 4414.24, "total_tokens": 299936}
|
| 95 |
+
{"current_steps": 475, "total_steps": 38160, "loss": 0.4175, "lr": 0.00012421383647798743, "epoch": 0.2489517819706499, "percentage": 1.24, "elapsed_time": "0:01:08", "remaining_time": "1:30:45", "throughput": 4414.03, "total_tokens": 302976}
|
| 96 |
+
{"current_steps": 480, "total_steps": 38160, "loss": 0.5388, "lr": 0.00012552410901467507, "epoch": 0.25157232704402516, "percentage": 1.26, "elapsed_time": "0:01:09", "remaining_time": "1:30:40", "throughput": 4412.48, "total_tokens": 305792}
|
| 97 |
+
{"current_steps": 485, "total_steps": 38160, "loss": 0.6229, "lr": 0.00012683438155136267, "epoch": 0.25419287211740044, "percentage": 1.27, "elapsed_time": "0:01:10", "remaining_time": "1:31:22", "throughput": 4434.23, "total_tokens": 312960}
|
| 98 |
+
{"current_steps": 490, "total_steps": 38160, "loss": 0.6136, "lr": 0.0001281446540880503, "epoch": 0.25681341719077566, "percentage": 1.28, "elapsed_time": "0:01:11", "remaining_time": "1:31:27", "throughput": 4438.7, "total_tokens": 316832}
|
| 99 |
+
{"current_steps": 495, "total_steps": 38160, "loss": 0.497, "lr": 0.00012945492662473794, "epoch": 0.25943396226415094, "percentage": 1.3, "elapsed_time": "0:01:12", "remaining_time": "1:31:25", "throughput": 4438.45, "total_tokens": 319968}
|
| 100 |
+
{"current_steps": 500, "total_steps": 38160, "loss": 0.4552, "lr": 0.00013076519916142558, "epoch": 0.2620545073375262, "percentage": 1.31, "elapsed_time": "0:01:12", "remaining_time": "1:31:20", "throughput": 4436.58, "total_tokens": 322816}
|
| 101 |
+
{"current_steps": 505, "total_steps": 38160, "loss": 0.6453, "lr": 0.0001320754716981132, "epoch": 0.26467505241090145, "percentage": 1.32, "elapsed_time": "0:01:13", "remaining_time": "1:31:15", "throughput": 4434.67, "total_tokens": 325664}
|
| 102 |
+
{"current_steps": 510, "total_steps": 38160, "loss": 0.5846, "lr": 0.00013338574423480085, "epoch": 0.2672955974842767, "percentage": 1.34, "elapsed_time": "0:01:14", "remaining_time": "1:31:14", "throughput": 4435.69, "total_tokens": 328960}
|
| 103 |
+
{"current_steps": 515, "total_steps": 38160, "loss": 0.4266, "lr": 0.00013469601677148845, "epoch": 0.269916142557652, "percentage": 1.35, "elapsed_time": "0:01:14", "remaining_time": "1:31:17", "throughput": 4438.55, "total_tokens": 332608}
|
| 104 |
+
{"current_steps": 520, "total_steps": 38160, "loss": 0.7158, "lr": 0.0001360062893081761, "epoch": 0.27253668763102723, "percentage": 1.36, "elapsed_time": "0:01:15", "remaining_time": "1:31:13", "throughput": 4437.83, "total_tokens": 335552}
|
| 105 |
+
{"current_steps": 525, "total_steps": 38160, "loss": 0.5216, "lr": 0.00013731656184486375, "epoch": 0.2751572327044025, "percentage": 1.38, "elapsed_time": "0:01:16", "remaining_time": "1:31:25", "throughput": 4446.31, "total_tokens": 340256}
|
| 106 |
+
{"current_steps": 530, "total_steps": 38160, "loss": 0.5294, "lr": 0.00013862683438155136, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:01:17", "remaining_time": "1:31:18", "throughput": 4442.94, "total_tokens": 342848}
|
| 107 |
+
{"current_steps": 535, "total_steps": 38160, "loss": 0.5951, "lr": 0.000139937106918239, "epoch": 0.280398322851153, "percentage": 1.4, "elapsed_time": "0:01:17", "remaining_time": "1:31:09", "throughput": 4438.78, "total_tokens": 345184}
|
| 108 |
+
{"current_steps": 540, "total_steps": 38160, "loss": 0.5517, "lr": 0.00014124737945492663, "epoch": 0.2830188679245283, "percentage": 1.42, "elapsed_time": "0:01:18", "remaining_time": "1:31:09", "throughput": 4440.1, "total_tokens": 348608}
|
| 109 |
+
{"current_steps": 545, "total_steps": 38160, "loss": 0.4835, "lr": 0.00014255765199161423, "epoch": 0.2856394129979036, "percentage": 1.43, "elapsed_time": "0:01:19", "remaining_time": "1:31:06", "throughput": 4439.88, "total_tokens": 351648}
|
| 110 |
+
{"current_steps": 550, "total_steps": 38160, "loss": 0.6725, "lr": 0.0001438679245283019, "epoch": 0.2882599580712788, "percentage": 1.44, "elapsed_time": "0:01:19", "remaining_time": "1:31:01", "throughput": 4438.2, "total_tokens": 354464}
|
| 111 |
+
{"current_steps": 555, "total_steps": 38160, "loss": 0.5991, "lr": 0.00014517819706498953, "epoch": 0.2908805031446541, "percentage": 1.45, "elapsed_time": "0:01:20", "remaining_time": "1:31:04", "throughput": 4442.02, "total_tokens": 358240}
|
| 112 |
+
{"current_steps": 560, "total_steps": 38160, "loss": 0.4813, "lr": 0.00014648846960167716, "epoch": 0.29350104821802936, "percentage": 1.47, "elapsed_time": "0:01:21", "remaining_time": "1:31:04", "throughput": 4442.94, "total_tokens": 361600}
|
| 113 |
+
{"current_steps": 565, "total_steps": 38160, "loss": 0.4577, "lr": 0.00014779874213836477, "epoch": 0.29612159329140464, "percentage": 1.48, "elapsed_time": "0:01:22", "remaining_time": "1:31:00", "throughput": 4441.13, "total_tokens": 364448}
|
| 114 |
+
{"current_steps": 570, "total_steps": 38160, "loss": 0.4637, "lr": 0.00014910901467505243, "epoch": 0.29874213836477986, "percentage": 1.49, "elapsed_time": "0:01:22", "remaining_time": "1:30:56", "throughput": 4440.75, "total_tokens": 367424}
|
| 115 |
+
{"current_steps": 575, "total_steps": 38160, "loss": 0.5578, "lr": 0.00015041928721174007, "epoch": 0.30136268343815514, "percentage": 1.51, "elapsed_time": "0:01:23", "remaining_time": "1:30:50", "throughput": 4438.19, "total_tokens": 370112}
|
| 116 |
+
{"current_steps": 580, "total_steps": 38160, "loss": 0.6093, "lr": 0.00015172955974842767, "epoch": 0.3039832285115304, "percentage": 1.52, "elapsed_time": "0:01:24", "remaining_time": "1:30:43", "throughput": 4434.91, "total_tokens": 372608}
|
| 117 |
+
{"current_steps": 585, "total_steps": 38160, "loss": 0.5404, "lr": 0.0001530398322851153, "epoch": 0.30660377358490565, "percentage": 1.53, "elapsed_time": "0:01:24", "remaining_time": "1:30:40", "throughput": 4434.21, "total_tokens": 375584}
|
| 118 |
+
{"current_steps": 590, "total_steps": 38160, "loss": 0.5763, "lr": 0.00015435010482180294, "epoch": 0.30922431865828093, "percentage": 1.55, "elapsed_time": "0:01:25", "remaining_time": "1:30:38", "throughput": 4434.42, "total_tokens": 378752}
|
| 119 |
+
{"current_steps": 595, "total_steps": 38160, "loss": 0.4131, "lr": 0.00015566037735849058, "epoch": 0.3118448637316562, "percentage": 1.56, "elapsed_time": "0:01:26", "remaining_time": "1:30:41", "throughput": 4437.26, "total_tokens": 382432}
|
| 120 |
+
{"current_steps": 600, "total_steps": 38160, "loss": 0.5704, "lr": 0.0001569706498951782, "epoch": 0.31446540880503143, "percentage": 1.57, "elapsed_time": "0:01:26", "remaining_time": "1:30:37", "throughput": 4436.48, "total_tokens": 385344}
|
| 121 |
+
{"current_steps": 605, "total_steps": 38160, "loss": 0.4817, "lr": 0.00015828092243186584, "epoch": 0.3170859538784067, "percentage": 1.59, "elapsed_time": "0:01:27", "remaining_time": "1:30:38", "throughput": 4438.38, "total_tokens": 388832}
|
| 122 |
+
{"current_steps": 610, "total_steps": 38160, "loss": 0.5249, "lr": 0.00015959119496855345, "epoch": 0.319706498951782, "percentage": 1.6, "elapsed_time": "0:01:28", "remaining_time": "1:30:41", "throughput": 4441.77, "total_tokens": 392640}
|
| 123 |
+
{"current_steps": 615, "total_steps": 38160, "loss": 0.564, "lr": 0.00016090146750524109, "epoch": 0.3223270440251572, "percentage": 1.61, "elapsed_time": "0:01:29", "remaining_time": "1:30:54", "throughput": 4449.72, "total_tokens": 397568}
|
| 124 |
+
{"current_steps": 620, "total_steps": 38160, "loss": 0.4337, "lr": 0.00016221174004192875, "epoch": 0.3249475890985325, "percentage": 1.62, "elapsed_time": "0:01:30", "remaining_time": "1:30:51", "throughput": 4448.68, "total_tokens": 400512}
|
| 125 |
+
{"current_steps": 625, "total_steps": 38160, "loss": 0.4983, "lr": 0.00016352201257861635, "epoch": 0.3275681341719078, "percentage": 1.64, "elapsed_time": "0:01:30", "remaining_time": "1:30:47", "throughput": 4448.25, "total_tokens": 403520}
|
| 126 |
+
{"current_steps": 630, "total_steps": 38160, "loss": 0.4935, "lr": 0.000164832285115304, "epoch": 0.330188679245283, "percentage": 1.65, "elapsed_time": "0:01:31", "remaining_time": "1:30:49", "throughput": 4450.13, "total_tokens": 407072}
|
| 127 |
+
{"current_steps": 635, "total_steps": 38160, "loss": 0.5046, "lr": 0.00016614255765199162, "epoch": 0.3328092243186583, "percentage": 1.66, "elapsed_time": "0:01:32", "remaining_time": "1:31:01", "throughput": 4456.91, "total_tokens": 411872}
|
| 128 |
+
{"current_steps": 640, "total_steps": 38160, "loss": 0.4818, "lr": 0.00016745283018867923, "epoch": 0.33542976939203356, "percentage": 1.68, "elapsed_time": "0:01:33", "remaining_time": "1:30:57", "throughput": 4455.56, "total_tokens": 414784}
|
| 129 |
+
{"current_steps": 645, "total_steps": 38160, "loss": 0.5976, "lr": 0.0001687631027253669, "epoch": 0.3380503144654088, "percentage": 1.69, "elapsed_time": "0:01:33", "remaining_time": "1:31:00", "throughput": 4459.04, "total_tokens": 418656}
|
| 130 |
+
{"current_steps": 650, "total_steps": 38160, "loss": 0.6086, "lr": 0.00017007337526205453, "epoch": 0.34067085953878407, "percentage": 1.7, "elapsed_time": "0:01:34", "remaining_time": "1:30:59", "throughput": 4458.96, "total_tokens": 421824}
|
| 131 |
+
{"current_steps": 655, "total_steps": 38160, "loss": 0.6018, "lr": 0.00017138364779874213, "epoch": 0.34329140461215935, "percentage": 1.72, "elapsed_time": "0:01:35", "remaining_time": "1:31:02", "throughput": 4461.73, "total_tokens": 425632}
|
| 132 |
+
{"current_steps": 660, "total_steps": 38160, "loss": 0.4711, "lr": 0.00017269392033542977, "epoch": 0.34591194968553457, "percentage": 1.73, "elapsed_time": "0:01:36", "remaining_time": "1:31:00", "throughput": 4462.23, "total_tokens": 428864}
|
| 133 |
+
{"current_steps": 665, "total_steps": 38160, "loss": 0.402, "lr": 0.0001740041928721174, "epoch": 0.34853249475890985, "percentage": 1.74, "elapsed_time": "0:01:36", "remaining_time": "1:30:52", "throughput": 4457.85, "total_tokens": 431104}
|
| 134 |
+
{"current_steps": 670, "total_steps": 38160, "loss": 0.5488, "lr": 0.00017531446540880504, "epoch": 0.35115303983228513, "percentage": 1.76, "elapsed_time": "0:01:37", "remaining_time": "1:30:51", "throughput": 4457.35, "total_tokens": 434240}
|
| 135 |
+
{"current_steps": 675, "total_steps": 38160, "loss": 0.5394, "lr": 0.00017662473794549267, "epoch": 0.35377358490566035, "percentage": 1.77, "elapsed_time": "0:01:38", "remaining_time": "1:30:52", "throughput": 4458.73, "total_tokens": 437792}
|
| 136 |
+
{"current_steps": 680, "total_steps": 38160, "loss": 0.6147, "lr": 0.0001779350104821803, "epoch": 0.35639412997903563, "percentage": 1.78, "elapsed_time": "0:01:38", "remaining_time": "1:30:53", "throughput": 4460.26, "total_tokens": 441280}
|
| 137 |
+
{"current_steps": 685, "total_steps": 38160, "loss": 0.4846, "lr": 0.0001792452830188679, "epoch": 0.3590146750524109, "percentage": 1.8, "elapsed_time": "0:01:39", "remaining_time": "1:30:55", "throughput": 4463.47, "total_tokens": 445120}
|
| 138 |
+
{"current_steps": 690, "total_steps": 38160, "loss": 0.483, "lr": 0.00018055555555555555, "epoch": 0.36163522012578614, "percentage": 1.81, "elapsed_time": "0:01:40", "remaining_time": "1:31:03", "throughput": 4469.01, "total_tokens": 449600}
|
| 139 |
+
{"current_steps": 695, "total_steps": 38160, "loss": 0.4768, "lr": 0.0001818658280922432, "epoch": 0.3642557651991614, "percentage": 1.82, "elapsed_time": "0:01:41", "remaining_time": "1:31:04", "throughput": 4470.16, "total_tokens": 453120}
|
| 140 |
+
{"current_steps": 700, "total_steps": 38160, "loss": 0.5398, "lr": 0.00018317610062893082, "epoch": 0.3668763102725367, "percentage": 1.83, "elapsed_time": "0:01:42", "remaining_time": "1:31:08", "throughput": 4474.48, "total_tokens": 457216}
|
| 141 |
+
{"current_steps": 705, "total_steps": 38160, "loss": 0.4478, "lr": 0.00018448637316561845, "epoch": 0.3694968553459119, "percentage": 1.85, "elapsed_time": "0:01:42", "remaining_time": "1:31:11", "throughput": 4477.75, "total_tokens": 461152}
|
| 142 |
+
{"current_steps": 710, "total_steps": 38160, "loss": 0.6427, "lr": 0.00018579664570230608, "epoch": 0.3721174004192872, "percentage": 1.86, "elapsed_time": "0:01:43", "remaining_time": "1:31:10", "throughput": 4478.19, "total_tokens": 464480}
|
| 143 |
+
{"current_steps": 715, "total_steps": 38160, "loss": 0.525, "lr": 0.0001871069182389937, "epoch": 0.3747379454926625, "percentage": 1.87, "elapsed_time": "0:01:44", "remaining_time": "1:31:09", "throughput": 4478.47, "total_tokens": 467744}
|
| 144 |
+
{"current_steps": 720, "total_steps": 38160, "loss": 0.4655, "lr": 0.00018841719077568135, "epoch": 0.37735849056603776, "percentage": 1.89, "elapsed_time": "0:01:45", "remaining_time": "1:31:06", "throughput": 4477.09, "total_tokens": 470656}
|
| 145 |
+
{"current_steps": 725, "total_steps": 38160, "loss": 0.4892, "lr": 0.000189727463312369, "epoch": 0.379979035639413, "percentage": 1.9, "elapsed_time": "0:01:45", "remaining_time": "1:31:06", "throughput": 4478.04, "total_tokens": 474048}
|
| 146 |
+
{"current_steps": 730, "total_steps": 38160, "loss": 0.5115, "lr": 0.00019103773584905662, "epoch": 0.38259958071278827, "percentage": 1.91, "elapsed_time": "0:01:46", "remaining_time": "1:31:04", "throughput": 4477.68, "total_tokens": 477184}
|
| 147 |
+
{"current_steps": 735, "total_steps": 38160, "loss": 0.4589, "lr": 0.00019234800838574423, "epoch": 0.38522012578616355, "percentage": 1.93, "elapsed_time": "0:01:47", "remaining_time": "1:31:00", "throughput": 4477.09, "total_tokens": 480160}
|
| 148 |
+
{"current_steps": 740, "total_steps": 38160, "loss": 0.3785, "lr": 0.00019365828092243186, "epoch": 0.38784067085953877, "percentage": 1.94, "elapsed_time": "0:01:48", "remaining_time": "1:31:19", "throughput": 4486.28, "total_tokens": 486144}
|
| 149 |
+
{"current_steps": 745, "total_steps": 38160, "loss": 0.5479, "lr": 0.00019496855345911953, "epoch": 0.39046121593291405, "percentage": 1.95, "elapsed_time": "0:01:49", "remaining_time": "1:31:21", "throughput": 4488.54, "total_tokens": 489920}
|
| 150 |
+
{"current_steps": 750, "total_steps": 38160, "loss": 0.4804, "lr": 0.00019627882599580713, "epoch": 0.39308176100628933, "percentage": 1.97, "elapsed_time": "0:01:49", "remaining_time": "1:31:24", "throughput": 4490.23, "total_tokens": 493728}
|
| 151 |
+
{"current_steps": 755, "total_steps": 38160, "loss": 0.502, "lr": 0.00019758909853249477, "epoch": 0.39570230607966456, "percentage": 1.98, "elapsed_time": "0:01:50", "remaining_time": "1:31:19", "throughput": 4488.18, "total_tokens": 496416}
|
| 152 |
+
{"current_steps": 760, "total_steps": 38160, "loss": 0.503, "lr": 0.0001988993710691824, "epoch": 0.39832285115303984, "percentage": 1.99, "elapsed_time": "0:01:51", "remaining_time": "1:31:23", "throughput": 4490.31, "total_tokens": 500320}
|
| 153 |
+
{"current_steps": 765, "total_steps": 38160, "loss": 0.4651, "lr": 0.00020020964360587, "epoch": 0.4009433962264151, "percentage": 2.0, "elapsed_time": "0:01:52", "remaining_time": "1:31:21", "throughput": 4490.19, "total_tokens": 503520}
|
| 154 |
+
{"current_steps": 770, "total_steps": 38160, "loss": 0.4948, "lr": 0.00020151991614255767, "epoch": 0.40356394129979034, "percentage": 2.02, "elapsed_time": "0:01:52", "remaining_time": "1:31:19", "throughput": 4489.84, "total_tokens": 506656}
|
| 155 |
+
{"current_steps": 775, "total_steps": 38160, "loss": 0.545, "lr": 0.0002028301886792453, "epoch": 0.4061844863731656, "percentage": 2.03, "elapsed_time": "0:01:53", "remaining_time": "1:31:16", "throughput": 4488.77, "total_tokens": 509568}
|
| 156 |
+
{"current_steps": 780, "total_steps": 38160, "loss": 0.4408, "lr": 0.0002041404612159329, "epoch": 0.4088050314465409, "percentage": 2.04, "elapsed_time": "0:01:54", "remaining_time": "1:31:11", "throughput": 4486.2, "total_tokens": 512160}
|
| 157 |
+
{"current_steps": 785, "total_steps": 38160, "loss": 0.4051, "lr": 0.00020545073375262055, "epoch": 0.4114255765199161, "percentage": 2.06, "elapsed_time": "0:01:54", "remaining_time": "1:31:12", "throughput": 4488.04, "total_tokens": 515872}
|
| 158 |
+
{"current_steps": 790, "total_steps": 38160, "loss": 0.5233, "lr": 0.00020676100628930818, "epoch": 0.4140461215932914, "percentage": 2.07, "elapsed_time": "0:01:55", "remaining_time": "1:31:11", "throughput": 4488.75, "total_tokens": 519232}
|
| 159 |
+
{"current_steps": 795, "total_steps": 38160, "loss": 0.343, "lr": 0.00020807127882599581, "epoch": 0.4166666666666667, "percentage": 2.08, "elapsed_time": "0:01:56", "remaining_time": "1:31:10", "throughput": 4488.62, "total_tokens": 522464}
|
| 160 |
+
{"current_steps": 800, "total_steps": 38160, "loss": 0.5028, "lr": 0.00020938155136268345, "epoch": 0.4192872117400419, "percentage": 2.1, "elapsed_time": "0:01:57", "remaining_time": "1:31:09", "throughput": 4488.29, "total_tokens": 525664}
|
| 161 |
+
{"current_steps": 805, "total_steps": 38160, "loss": 0.6085, "lr": 0.00021069182389937108, "epoch": 0.4219077568134172, "percentage": 2.11, "elapsed_time": "0:01:57", "remaining_time": "1:31:10", "throughput": 4488.91, "total_tokens": 529216}
|
| 162 |
+
{"current_steps": 810, "total_steps": 38160, "loss": 0.5685, "lr": 0.0002120020964360587, "epoch": 0.42452830188679247, "percentage": 2.12, "elapsed_time": "0:01:58", "remaining_time": "1:31:14", "throughput": 4492.6, "total_tokens": 533376}
|
| 163 |
+
{"current_steps": 815, "total_steps": 38160, "loss": 0.5844, "lr": 0.00021331236897274632, "epoch": 0.4271488469601677, "percentage": 2.14, "elapsed_time": "0:01:59", "remaining_time": "1:31:10", "throughput": 4491.01, "total_tokens": 536192}
|
| 164 |
+
{"current_steps": 820, "total_steps": 38160, "loss": 0.472, "lr": 0.00021462264150943399, "epoch": 0.429769392033543, "percentage": 2.15, "elapsed_time": "0:02:00", "remaining_time": "1:31:08", "throughput": 4491.25, "total_tokens": 539392}
|
| 165 |
+
{"current_steps": 825, "total_steps": 38160, "loss": 0.4573, "lr": 0.0002159329140461216, "epoch": 0.43238993710691825, "percentage": 2.16, "elapsed_time": "0:02:00", "remaining_time": "1:31:07", "throughput": 4491.49, "total_tokens": 542656}
|
| 166 |
+
{"current_steps": 830, "total_steps": 38160, "loss": 0.2961, "lr": 0.00021724318658280923, "epoch": 0.4350104821802935, "percentage": 2.18, "elapsed_time": "0:02:01", "remaining_time": "1:31:19", "throughput": 4498.57, "total_tokens": 548064}
|
| 167 |
+
{"current_steps": 835, "total_steps": 38160, "loss": 0.5164, "lr": 0.00021855345911949686, "epoch": 0.43763102725366876, "percentage": 2.19, "elapsed_time": "0:02:02", "remaining_time": "1:31:16", "throughput": 4498.09, "total_tokens": 551104}
|
| 168 |
+
{"current_steps": 840, "total_steps": 38160, "loss": 0.7053, "lr": 0.00021986373165618447, "epoch": 0.44025157232704404, "percentage": 2.2, "elapsed_time": "0:02:03", "remaining_time": "1:31:23", "throughput": 4502.08, "total_tokens": 555680}
|
| 169 |
+
{"current_steps": 845, "total_steps": 38160, "loss": 0.3938, "lr": 0.00022117400419287213, "epoch": 0.44287211740041926, "percentage": 2.21, "elapsed_time": "0:02:04", "remaining_time": "1:31:17", "throughput": 4499.52, "total_tokens": 558144}
|
| 170 |
+
{"current_steps": 850, "total_steps": 38160, "loss": 0.5376, "lr": 0.00022248427672955977, "epoch": 0.44549266247379454, "percentage": 2.23, "elapsed_time": "0:02:04", "remaining_time": "1:31:10", "throughput": 4496.21, "total_tokens": 560384}
|
| 171 |
+
{"current_steps": 855, "total_steps": 38160, "loss": 0.502, "lr": 0.00022379454926624737, "epoch": 0.4481132075471698, "percentage": 2.24, "elapsed_time": "0:02:05", "remaining_time": "1:31:06", "throughput": 4494.39, "total_tokens": 563072}
|
| 172 |
+
{"current_steps": 860, "total_steps": 38160, "loss": 0.5916, "lr": 0.000225104821802935, "epoch": 0.45073375262054505, "percentage": 2.25, "elapsed_time": "0:02:05", "remaining_time": "1:31:02", "throughput": 4492.59, "total_tokens": 565792}
|
| 173 |
+
{"current_steps": 865, "total_steps": 38160, "loss": 0.3766, "lr": 0.00022641509433962264, "epoch": 0.4533542976939203, "percentage": 2.27, "elapsed_time": "0:02:06", "remaining_time": "1:30:56", "throughput": 4489.42, "total_tokens": 568160}
|
| 174 |
+
{"current_steps": 870, "total_steps": 38160, "loss": 0.5778, "lr": 0.00022772536687631028, "epoch": 0.4559748427672956, "percentage": 2.28, "elapsed_time": "0:02:07", "remaining_time": "1:30:56", "throughput": 4489.84, "total_tokens": 571584}
|
| 175 |
+
{"current_steps": 875, "total_steps": 38160, "loss": 0.4738, "lr": 0.0002290356394129979, "epoch": 0.4585953878406709, "percentage": 2.29, "elapsed_time": "0:02:08", "remaining_time": "1:31:03", "throughput": 4494.47, "total_tokens": 576288}
|
| 176 |
+
{"current_steps": 880, "total_steps": 38160, "loss": 0.5048, "lr": 0.00023034591194968554, "epoch": 0.4612159329140461, "percentage": 2.31, "elapsed_time": "0:02:08", "remaining_time": "1:31:01", "throughput": 4494.39, "total_tokens": 579456}
|
| 177 |
+
{"current_steps": 885, "total_steps": 38160, "loss": 0.6095, "lr": 0.00023165618448637318, "epoch": 0.4638364779874214, "percentage": 2.32, "elapsed_time": "0:02:09", "remaining_time": "1:31:06", "throughput": 4497.5, "total_tokens": 583680}
|
| 178 |
+
{"current_steps": 890, "total_steps": 38160, "loss": 0.5889, "lr": 0.00023296645702306079, "epoch": 0.46645702306079667, "percentage": 2.33, "elapsed_time": "0:02:10", "remaining_time": "1:31:05", "throughput": 4497.98, "total_tokens": 587040}
|
| 179 |
+
{"current_steps": 895, "total_steps": 38160, "loss": 0.3633, "lr": 0.00023427672955974845, "epoch": 0.4690775681341719, "percentage": 2.35, "elapsed_time": "0:02:11", "remaining_time": "1:31:02", "throughput": 4496.7, "total_tokens": 589952}
|
| 180 |
+
{"current_steps": 900, "total_steps": 38160, "loss": 0.5763, "lr": 0.00023558700209643608, "epoch": 0.4716981132075472, "percentage": 2.36, "elapsed_time": "0:02:11", "remaining_time": "1:31:03", "throughput": 4498.09, "total_tokens": 593600}
|
| 181 |
+
{"current_steps": 905, "total_steps": 38160, "loss": 0.4922, "lr": 0.0002368972746331237, "epoch": 0.47431865828092246, "percentage": 2.37, "elapsed_time": "0:02:12", "remaining_time": "1:31:03", "throughput": 4499.48, "total_tokens": 597216}
|
| 182 |
+
{"current_steps": 910, "total_steps": 38160, "loss": 0.6615, "lr": 0.00023820754716981132, "epoch": 0.4769392033542977, "percentage": 2.38, "elapsed_time": "0:02:13", "remaining_time": "1:31:03", "throughput": 4499.75, "total_tokens": 600576}
|
| 183 |
+
{"current_steps": 915, "total_steps": 38160, "loss": 0.4774, "lr": 0.00023951781970649896, "epoch": 0.47955974842767296, "percentage": 2.4, "elapsed_time": "0:02:14", "remaining_time": "1:31:03", "throughput": 4499.9, "total_tokens": 603936}
|
| 184 |
+
{"current_steps": 920, "total_steps": 38160, "loss": 0.5874, "lr": 0.0002408280922431866, "epoch": 0.48218029350104824, "percentage": 2.41, "elapsed_time": "0:02:14", "remaining_time": "1:30:59", "throughput": 4498.96, "total_tokens": 606816}
|
| 185 |
+
{"current_steps": 925, "total_steps": 38160, "loss": 0.4446, "lr": 0.00024213836477987423, "epoch": 0.48480083857442346, "percentage": 2.42, "elapsed_time": "0:02:15", "remaining_time": "1:30:58", "throughput": 4499.03, "total_tokens": 610112}
|
| 186 |
+
{"current_steps": 930, "total_steps": 38160, "loss": 0.4771, "lr": 0.00024344863731656186, "epoch": 0.48742138364779874, "percentage": 2.44, "elapsed_time": "0:02:16", "remaining_time": "1:30:56", "throughput": 4498.55, "total_tokens": 613216}
|
| 187 |
+
{"current_steps": 935, "total_steps": 38160, "loss": 0.5798, "lr": 0.00024475890985324947, "epoch": 0.490041928721174, "percentage": 2.45, "elapsed_time": "0:02:16", "remaining_time": "1:30:53", "throughput": 4496.56, "total_tokens": 615904}
|
| 188 |
+
{"current_steps": 940, "total_steps": 38160, "loss": 0.6769, "lr": 0.0002460691823899371, "epoch": 0.49266247379454925, "percentage": 2.46, "elapsed_time": "0:02:17", "remaining_time": "1:30:53", "throughput": 4497.25, "total_tokens": 619456}
|
| 189 |
+
{"current_steps": 945, "total_steps": 38160, "loss": 0.5178, "lr": 0.00024737945492662474, "epoch": 0.49528301886792453, "percentage": 2.48, "elapsed_time": "0:02:18", "remaining_time": "1:30:52", "throughput": 4497.01, "total_tokens": 622656}
|
| 190 |
+
{"current_steps": 950, "total_steps": 38160, "loss": 0.5536, "lr": 0.00024868972746331237, "epoch": 0.4979035639412998, "percentage": 2.49, "elapsed_time": "0:02:19", "remaining_time": "1:30:52", "throughput": 4497.18, "total_tokens": 626016}
|
| 191 |
+
{"current_steps": 955, "total_steps": 38160, "loss": 0.4922, "lr": 0.00025, "epoch": 0.500524109014675, "percentage": 2.5, "elapsed_time": "0:02:19", "remaining_time": "1:30:50", "throughput": 4496.85, "total_tokens": 629120}
|
| 192 |
+
{"current_steps": 960, "total_steps": 38160, "loss": 0.539, "lr": 0.00025131027253668764, "epoch": 0.5031446540880503, "percentage": 2.52, "elapsed_time": "0:02:20", "remaining_time": "1:30:48", "throughput": 4496.25, "total_tokens": 632160}
|
| 193 |
+
{"current_steps": 965, "total_steps": 38160, "loss": 0.4622, "lr": 0.0002526205450733753, "epoch": 0.5057651991614256, "percentage": 2.53, "elapsed_time": "0:02:21", "remaining_time": "1:30:43", "throughput": 4494.45, "total_tokens": 634784}
|
| 194 |
+
{"current_steps": 970, "total_steps": 38160, "loss": 0.5827, "lr": 0.0002539308176100629, "epoch": 0.5083857442348009, "percentage": 2.54, "elapsed_time": "0:02:21", "remaining_time": "1:30:41", "throughput": 4493.72, "total_tokens": 637792}
|
| 195 |
+
{"current_steps": 975, "total_steps": 38160, "loss": 0.4433, "lr": 0.0002552410901467505, "epoch": 0.5110062893081762, "percentage": 2.56, "elapsed_time": "0:02:22", "remaining_time": "1:30:42", "throughput": 4494.24, "total_tokens": 641312}
|
| 196 |
+
{"current_steps": 980, "total_steps": 38160, "loss": 0.5475, "lr": 0.0002565513626834381, "epoch": 0.5136268343815513, "percentage": 2.57, "elapsed_time": "0:02:23", "remaining_time": "1:30:42", "throughput": 4495.11, "total_tokens": 644832}
|
| 197 |
+
{"current_steps": 985, "total_steps": 38160, "loss": 0.6165, "lr": 0.0002578616352201258, "epoch": 0.5162473794549266, "percentage": 2.58, "elapsed_time": "0:02:24", "remaining_time": "1:30:40", "throughput": 4494.7, "total_tokens": 647904}
|
| 198 |
+
{"current_steps": 990, "total_steps": 38160, "loss": 0.5711, "lr": 0.00025917190775681345, "epoch": 0.5188679245283019, "percentage": 2.59, "elapsed_time": "0:02:24", "remaining_time": "1:30:36", "throughput": 4493.09, "total_tokens": 650624}
|
| 199 |
+
{"current_steps": 995, "total_steps": 38160, "loss": 0.5352, "lr": 0.0002604821802935011, "epoch": 0.5214884696016772, "percentage": 2.61, "elapsed_time": "0:02:25", "remaining_time": "1:30:32", "throughput": 4491.14, "total_tokens": 653248}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 38160, "loss": 0.567, "lr": 0.0002617924528301887, "epoch": 0.5241090146750524, "percentage": 2.62, "elapsed_time": "0:02:26", "remaining_time": "1:30:29", "throughput": 4489.64, "total_tokens": 655936}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 38160, "loss": 0.438, "lr": 0.0002631027253668763, "epoch": 0.5267295597484277, "percentage": 2.63, "elapsed_time": "0:02:27", "remaining_time": "1:30:42", "throughput": 4495.96, "total_tokens": 661888}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 38160, "loss": 0.5353, "lr": 0.00026441299790356393, "epoch": 0.5293501048218029, "percentage": 2.65, "elapsed_time": "0:02:27", "remaining_time": "1:30:38", "throughput": 4494.24, "total_tokens": 664512}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 38160, "loss": 0.3974, "lr": 0.00026572327044025156, "epoch": 0.5319706498951782, "percentage": 2.66, "elapsed_time": "0:02:28", "remaining_time": "1:30:38", "throughput": 4495.35, "total_tokens": 668096}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 38160, "loss": 0.7355, "lr": 0.0002670335429769392, "epoch": 0.5345911949685535, "percentage": 2.67, "elapsed_time": "0:02:29", "remaining_time": "1:30:40", "throughput": 4495.99, "total_tokens": 671744}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 38160, "loss": 0.4028, "lr": 0.00026834381551362683, "epoch": 0.5372117400419287, "percentage": 2.69, "elapsed_time": "0:02:30", "remaining_time": "1:30:35", "throughput": 4493.61, "total_tokens": 674144}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 38160, "loss": 0.7217, "lr": 0.0002696540880503145, "epoch": 0.539832285115304, "percentage": 2.7, "elapsed_time": "0:02:30", "remaining_time": "1:30:33", "throughput": 4493.79, "total_tokens": 677312}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 38160, "loss": 0.4206, "lr": 0.0002709643605870021, "epoch": 0.5424528301886793, "percentage": 2.71, "elapsed_time": "0:02:31", "remaining_time": "1:30:30", "throughput": 4493.05, "total_tokens": 680256}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 38160, "loss": 0.4244, "lr": 0.00027227463312368973, "epoch": 0.5450733752620545, "percentage": 2.73, "elapsed_time": "0:02:32", "remaining_time": "1:30:30", "throughput": 4493.75, "total_tokens": 683744}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 38160, "loss": 0.5124, "lr": 0.00027358490566037737, "epoch": 0.5476939203354297, "percentage": 2.74, "elapsed_time": "0:02:32", "remaining_time": "1:30:32", "throughput": 4495.53, "total_tokens": 687616}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 38160, "loss": 0.5329, "lr": 0.000274895178197065, "epoch": 0.550314465408805, "percentage": 2.75, "elapsed_time": "0:02:33", "remaining_time": "1:30:34", "throughput": 4496.72, "total_tokens": 691392}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 38160, "loss": 0.5519, "lr": 0.00027620545073375264, "epoch": 0.5529350104821803, "percentage": 2.76, "elapsed_time": "0:02:34", "remaining_time": "1:30:38", "throughput": 4500.17, "total_tokens": 695904}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 38160, "loss": 0.4415, "lr": 0.00027751572327044027, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:02:35", "remaining_time": "1:30:34", "throughput": 4498.26, "total_tokens": 698496}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 38160, "loss": 0.5836, "lr": 0.00027882599580712785, "epoch": 0.5581761006289309, "percentage": 2.79, "elapsed_time": "0:02:35", "remaining_time": "1:30:31", "throughput": 4497.22, "total_tokens": 701344}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 38160, "loss": 0.5231, "lr": 0.0002801362683438155, "epoch": 0.560796645702306, "percentage": 2.8, "elapsed_time": "0:02:36", "remaining_time": "1:30:27", "throughput": 4495.66, "total_tokens": 703968}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 38160, "loss": 0.4473, "lr": 0.0002814465408805031, "epoch": 0.5634171907756813, "percentage": 2.82, "elapsed_time": "0:02:37", "remaining_time": "1:30:25", "throughput": 4495.4, "total_tokens": 707040}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 38160, "loss": 0.4794, "lr": 0.0002827568134171908, "epoch": 0.5660377358490566, "percentage": 2.83, "elapsed_time": "0:02:37", "remaining_time": "1:30:20", "throughput": 4492.6, "total_tokens": 709280}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 38160, "loss": 0.4386, "lr": 0.00028406708595387844, "epoch": 0.5686582809224319, "percentage": 2.84, "elapsed_time": "0:02:38", "remaining_time": "1:30:24", "throughput": 4496.38, "total_tokens": 713792}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 38160, "loss": 0.7812, "lr": 0.0002853773584905661, "epoch": 0.5712788259958071, "percentage": 2.86, "elapsed_time": "0:02:39", "remaining_time": "1:30:21", "throughput": 4494.82, "total_tokens": 716480}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 38160, "loss": 0.476, "lr": 0.00028668763102725366, "epoch": 0.5738993710691824, "percentage": 2.87, "elapsed_time": "0:02:40", "remaining_time": "1:30:17", "throughput": 4493.4, "total_tokens": 719136}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 38160, "loss": 0.446, "lr": 0.0002879979035639413, "epoch": 0.5765199161425576, "percentage": 2.88, "elapsed_time": "0:02:40", "remaining_time": "1:30:18", "throughput": 4494.21, "total_tokens": 722752}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 38160, "loss": 0.6234, "lr": 0.00028930817610062893, "epoch": 0.5791404612159329, "percentage": 2.9, "elapsed_time": "0:02:41", "remaining_time": "1:30:16", "throughput": 4494.29, "total_tokens": 725920}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 38160, "loss": 0.4598, "lr": 0.00029061844863731656, "epoch": 0.5817610062893082, "percentage": 2.91, "elapsed_time": "0:02:42", "remaining_time": "1:30:13", "throughput": 4493.06, "total_tokens": 728736}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 38160, "loss": 0.5175, "lr": 0.0002919287211740042, "epoch": 0.5843815513626834, "percentage": 2.92, "elapsed_time": "0:02:42", "remaining_time": "1:30:12", "throughput": 4492.35, "total_tokens": 731776}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 38160, "loss": 0.493, "lr": 0.00029323899371069183, "epoch": 0.5870020964360587, "percentage": 2.94, "elapsed_time": "0:02:43", "remaining_time": "1:30:09", "throughput": 4491.78, "total_tokens": 734784}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 38160, "loss": 0.5541, "lr": 0.00029454926624737946, "epoch": 0.589622641509434, "percentage": 2.95, "elapsed_time": "0:02:44", "remaining_time": "1:30:08", "throughput": 4491.54, "total_tokens": 737888}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 38160, "loss": 0.3686, "lr": 0.0002958595387840671, "epoch": 0.5922431865828093, "percentage": 2.96, "elapsed_time": "0:02:45", "remaining_time": "1:30:10", "throughput": 4493.32, "total_tokens": 741824}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 38160, "loss": 0.4942, "lr": 0.00029716981132075473, "epoch": 0.5948637316561844, "percentage": 2.97, "elapsed_time": "0:02:45", "remaining_time": "1:30:05", "throughput": 4491.39, "total_tokens": 744288}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 38160, "loss": 0.4932, "lr": 0.00029848008385744237, "epoch": 0.5974842767295597, "percentage": 2.99, "elapsed_time": "0:02:46", "remaining_time": "1:30:05", "throughput": 4491.39, "total_tokens": 747648}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 38160, "loss": 0.5235, "lr": 0.00029979035639413, "epoch": 0.600104821802935, "percentage": 3.0, "elapsed_time": "0:02:47", "remaining_time": "1:30:06", "throughput": 4491.93, "total_tokens": 751168}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 38160, "loss": 0.4722, "lr": 0.00030110062893081764, "epoch": 0.6027253668763103, "percentage": 3.01, "elapsed_time": "0:02:47", "remaining_time": "1:30:05", "throughput": 4492.29, "total_tokens": 754528}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 38160, "loss": 0.5785, "lr": 0.00030241090146750527, "epoch": 0.6053459119496856, "percentage": 3.03, "elapsed_time": "0:02:48", "remaining_time": "1:30:02", "throughput": 4490.59, "total_tokens": 757152}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 38160, "loss": 0.6139, "lr": 0.00030372117400419285, "epoch": 0.6079664570230608, "percentage": 3.04, "elapsed_time": "0:02:49", "remaining_time": "1:29:59", "throughput": 4489.85, "total_tokens": 760064}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 38160, "loss": 0.4821, "lr": 0.0003050314465408805, "epoch": 0.610587002096436, "percentage": 3.05, "elapsed_time": "0:02:49", "remaining_time": "1:29:57", "throughput": 4488.98, "total_tokens": 762976}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 38160, "loss": 0.4645, "lr": 0.0003063417190775681, "epoch": 0.6132075471698113, "percentage": 3.07, "elapsed_time": "0:02:50", "remaining_time": "1:29:53", "throughput": 4487.57, "total_tokens": 765600}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 38160, "loss": 0.5225, "lr": 0.00030765199161425575, "epoch": 0.6158280922431866, "percentage": 3.08, "elapsed_time": "0:02:51", "remaining_time": "1:29:50", "throughput": 4486.26, "total_tokens": 768320}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 38160, "loss": 0.5035, "lr": 0.00030896226415094344, "epoch": 0.6184486373165619, "percentage": 3.09, "elapsed_time": "0:02:51", "remaining_time": "1:29:49", "throughput": 4485.86, "total_tokens": 771392}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 38160, "loss": 0.4519, "lr": 0.0003102725366876311, "epoch": 0.6210691823899371, "percentage": 3.11, "elapsed_time": "0:02:52", "remaining_time": "1:29:46", "throughput": 4484.29, "total_tokens": 774080}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 38160, "loss": 0.5028, "lr": 0.00031158280922431866, "epoch": 0.6236897274633124, "percentage": 3.12, "elapsed_time": "0:02:53", "remaining_time": "1:29:44", "throughput": 4483.81, "total_tokens": 777184}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 38160, "loss": 0.5188, "lr": 0.0003128930817610063, "epoch": 0.6263102725366876, "percentage": 3.13, "elapsed_time": "0:02:54", "remaining_time": "1:29:44", "throughput": 4485.0, "total_tokens": 780768}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 38160, "loss": 0.6431, "lr": 0.0003142033542976939, "epoch": 0.6289308176100629, "percentage": 3.14, "elapsed_time": "0:02:54", "remaining_time": "1:29:44", "throughput": 4485.14, "total_tokens": 784128}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 38160, "loss": 0.5443, "lr": 0.00031551362683438156, "epoch": 0.6315513626834381, "percentage": 3.16, "elapsed_time": "0:02:55", "remaining_time": "1:29:43", "throughput": 4484.52, "total_tokens": 787200}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 38160, "loss": 0.4501, "lr": 0.0003168238993710692, "epoch": 0.6341719077568134, "percentage": 3.17, "elapsed_time": "0:02:56", "remaining_time": "1:29:41", "throughput": 4483.75, "total_tokens": 790176}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 38160, "loss": 0.5331, "lr": 0.00031813417190775683, "epoch": 0.6367924528301887, "percentage": 3.18, "elapsed_time": "0:02:57", "remaining_time": "1:29:44", "throughput": 4485.94, "total_tokens": 794368}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 38160, "loss": 0.5395, "lr": 0.0003194444444444444, "epoch": 0.639412997903564, "percentage": 3.2, "elapsed_time": "0:02:57", "remaining_time": "1:29:41", "throughput": 4484.79, "total_tokens": 797120}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 38160, "loss": 0.4325, "lr": 0.00032075471698113204, "epoch": 0.6420335429769392, "percentage": 3.21, "elapsed_time": "0:02:58", "remaining_time": "1:29:43", "throughput": 4486.7, "total_tokens": 801088}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 38160, "loss": 0.5181, "lr": 0.00032206498951781973, "epoch": 0.6446540880503144, "percentage": 3.22, "elapsed_time": "0:02:59", "remaining_time": "1:29:43", "throughput": 4487.88, "total_tokens": 804704}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 38160, "loss": 0.6132, "lr": 0.00032337526205450737, "epoch": 0.6472746331236897, "percentage": 3.24, "elapsed_time": "0:03:00", "remaining_time": "1:29:42", "throughput": 4488.14, "total_tokens": 808000}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 38160, "loss": 0.5488, "lr": 0.000324685534591195, "epoch": 0.649895178197065, "percentage": 3.25, "elapsed_time": "0:03:00", "remaining_time": "1:29:40", "throughput": 4487.15, "total_tokens": 810848}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 38160, "loss": 0.5863, "lr": 0.00032599580712788263, "epoch": 0.6525157232704403, "percentage": 3.26, "elapsed_time": "0:03:01", "remaining_time": "1:29:38", "throughput": 4486.29, "total_tokens": 813728}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 38160, "loss": 0.4873, "lr": 0.0003273060796645702, "epoch": 0.6551362683438156, "percentage": 3.28, "elapsed_time": "0:03:02", "remaining_time": "1:29:36", "throughput": 4486.59, "total_tokens": 816992}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 38160, "loss": 0.4592, "lr": 0.00032861635220125785, "epoch": 0.6577568134171907, "percentage": 3.29, "elapsed_time": "0:03:02", "remaining_time": "1:29:33", "throughput": 4485.21, "total_tokens": 819584}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 38160, "loss": 0.5736, "lr": 0.0003299266247379455, "epoch": 0.660377358490566, "percentage": 3.3, "elapsed_time": "0:03:03", "remaining_time": "1:29:31", "throughput": 4484.66, "total_tokens": 822560}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 38160, "loss": 0.6482, "lr": 0.0003312368972746331, "epoch": 0.6629979035639413, "percentage": 3.31, "elapsed_time": "0:03:04", "remaining_time": "1:29:30", "throughput": 4484.56, "total_tokens": 825792}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 38160, "loss": 0.4976, "lr": 0.00033254716981132075, "epoch": 0.6656184486373166, "percentage": 3.33, "elapsed_time": "0:03:04", "remaining_time": "1:29:31", "throughput": 4485.97, "total_tokens": 829632}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 38160, "loss": 0.4729, "lr": 0.0003338574423480084, "epoch": 0.6682389937106918, "percentage": 3.34, "elapsed_time": "0:03:05", "remaining_time": "1:29:30", "throughput": 4485.49, "total_tokens": 832672}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 38160, "loss": 0.4756, "lr": 0.0003351677148846961, "epoch": 0.6708595387840671, "percentage": 3.35, "elapsed_time": "0:03:06", "remaining_time": "1:29:29", "throughput": 4485.38, "total_tokens": 835840}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 38160, "loss": 0.4865, "lr": 0.00033647798742138366, "epoch": 0.6734800838574424, "percentage": 3.37, "elapsed_time": "0:03:07", "remaining_time": "1:29:31", "throughput": 4488.16, "total_tokens": 840160}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 38160, "loss": 0.5699, "lr": 0.0003377882599580713, "epoch": 0.6761006289308176, "percentage": 3.38, "elapsed_time": "0:03:07", "remaining_time": "1:29:31", "throughput": 4487.98, "total_tokens": 843392}
|
| 259 |
+
{"current_steps": 1295, "total_steps": 38160, "loss": 0.4094, "lr": 0.0003390985324947589, "epoch": 0.6787211740041929, "percentage": 3.39, "elapsed_time": "0:03:08", "remaining_time": "1:29:34", "throughput": 4489.74, "total_tokens": 847616}
|
| 260 |
+
{"current_steps": 1300, "total_steps": 38160, "loss": 0.5101, "lr": 0.00034040880503144656, "epoch": 0.6813417190775681, "percentage": 3.41, "elapsed_time": "0:03:09", "remaining_time": "1:29:35", "throughput": 4491.0, "total_tokens": 851392}
|
| 261 |
+
{"current_steps": 1305, "total_steps": 38160, "loss": 0.543, "lr": 0.0003417190775681342, "epoch": 0.6839622641509434, "percentage": 3.42, "elapsed_time": "0:03:10", "remaining_time": "1:29:33", "throughput": 4490.44, "total_tokens": 854336}
|
| 262 |
+
{"current_steps": 1310, "total_steps": 38160, "loss": 0.4848, "lr": 0.00034302935010482183, "epoch": 0.6865828092243187, "percentage": 3.43, "elapsed_time": "0:03:10", "remaining_time": "1:29:31", "throughput": 4489.99, "total_tokens": 857312}
|
| 263 |
+
{"current_steps": 1315, "total_steps": 38160, "loss": 0.5321, "lr": 0.0003443396226415094, "epoch": 0.689203354297694, "percentage": 3.45, "elapsed_time": "0:03:11", "remaining_time": "1:29:32", "throughput": 4491.52, "total_tokens": 861152}
|
| 264 |
+
{"current_steps": 1320, "total_steps": 38160, "loss": 0.6204, "lr": 0.00034564989517819704, "epoch": 0.6918238993710691, "percentage": 3.46, "elapsed_time": "0:03:12", "remaining_time": "1:29:32", "throughput": 4492.22, "total_tokens": 864704}
|
| 265 |
+
{"current_steps": 1325, "total_steps": 38160, "loss": 0.554, "lr": 0.0003469601677148847, "epoch": 0.6944444444444444, "percentage": 3.47, "elapsed_time": "0:03:13", "remaining_time": "1:29:29", "throughput": 4491.0, "total_tokens": 867360}
|
| 266 |
+
{"current_steps": 1330, "total_steps": 38160, "loss": 0.598, "lr": 0.00034827044025157236, "epoch": 0.6970649895178197, "percentage": 3.49, "elapsed_time": "0:03:13", "remaining_time": "1:29:27", "throughput": 4490.8, "total_tokens": 870464}
|
| 267 |
+
{"current_steps": 1335, "total_steps": 38160, "loss": 0.3874, "lr": 0.00034958071278826, "epoch": 0.699685534591195, "percentage": 3.5, "elapsed_time": "0:03:14", "remaining_time": "1:29:27", "throughput": 4490.69, "total_tokens": 873792}
|
| 268 |
+
{"current_steps": 1340, "total_steps": 38160, "loss": 0.6038, "lr": 0.00035089098532494763, "epoch": 0.7023060796645703, "percentage": 3.51, "elapsed_time": "0:03:15", "remaining_time": "1:29:30", "throughput": 4493.51, "total_tokens": 878336}
|
| 269 |
+
{"current_steps": 1345, "total_steps": 38160, "loss": 0.667, "lr": 0.0003522012578616352, "epoch": 0.7049266247379455, "percentage": 3.52, "elapsed_time": "0:03:16", "remaining_time": "1:29:31", "throughput": 4494.39, "total_tokens": 881984}
|
| 270 |
+
{"current_steps": 1350, "total_steps": 38160, "loss": 0.4298, "lr": 0.00035351153039832285, "epoch": 0.7075471698113207, "percentage": 3.54, "elapsed_time": "0:03:17", "remaining_time": "1:29:32", "throughput": 4494.99, "total_tokens": 885632}
|
| 271 |
+
{"current_steps": 1355, "total_steps": 38160, "loss": 0.4324, "lr": 0.0003548218029350105, "epoch": 0.710167714884696, "percentage": 3.55, "elapsed_time": "0:03:17", "remaining_time": "1:29:30", "throughput": 4494.39, "total_tokens": 888544}
|
| 272 |
+
{"current_steps": 1360, "total_steps": 38160, "loss": 0.4871, "lr": 0.0003561320754716981, "epoch": 0.7127882599580713, "percentage": 3.56, "elapsed_time": "0:03:18", "remaining_time": "1:29:27", "throughput": 4493.36, "total_tokens": 891328}
|
| 273 |
+
{"current_steps": 1365, "total_steps": 38160, "loss": 0.6039, "lr": 0.00035744234800838575, "epoch": 0.7154088050314465, "percentage": 3.58, "elapsed_time": "0:03:19", "remaining_time": "1:29:25", "throughput": 4493.15, "total_tokens": 894400}
|
| 274 |
+
{"current_steps": 1370, "total_steps": 38160, "loss": 0.462, "lr": 0.0003587526205450734, "epoch": 0.7180293501048218, "percentage": 3.59, "elapsed_time": "0:03:19", "remaining_time": "1:29:21", "throughput": 4491.08, "total_tokens": 896704}
|
| 275 |
+
{"current_steps": 1375, "total_steps": 38160, "loss": 0.4818, "lr": 0.00036006289308176097, "epoch": 0.7206498951781971, "percentage": 3.6, "elapsed_time": "0:03:20", "remaining_time": "1:29:19", "throughput": 4490.03, "total_tokens": 899520}
|
| 276 |
+
{"current_steps": 1380, "total_steps": 38160, "loss": 0.53, "lr": 0.00036137316561844865, "epoch": 0.7232704402515723, "percentage": 3.62, "elapsed_time": "0:03:21", "remaining_time": "1:29:17", "throughput": 4489.01, "total_tokens": 902304}
|
| 277 |
+
{"current_steps": 1385, "total_steps": 38160, "loss": 0.5635, "lr": 0.0003626834381551363, "epoch": 0.7258909853249476, "percentage": 3.63, "elapsed_time": "0:03:21", "remaining_time": "1:29:16", "throughput": 4489.55, "total_tokens": 905760}
|
| 278 |
+
{"current_steps": 1390, "total_steps": 38160, "loss": 0.5573, "lr": 0.0003639937106918239, "epoch": 0.7285115303983228, "percentage": 3.64, "elapsed_time": "0:03:22", "remaining_time": "1:29:14", "throughput": 4488.43, "total_tokens": 908512}
|
| 279 |
+
{"current_steps": 1395, "total_steps": 38160, "loss": 0.4697, "lr": 0.00036530398322851156, "epoch": 0.7311320754716981, "percentage": 3.66, "elapsed_time": "0:03:23", "remaining_time": "1:29:16", "throughput": 4490.57, "total_tokens": 912736}
|
| 280 |
+
{"current_steps": 1400, "total_steps": 38160, "loss": 0.8091, "lr": 0.0003666142557651992, "epoch": 0.7337526205450734, "percentage": 3.67, "elapsed_time": "0:03:24", "remaining_time": "1:29:16", "throughput": 4491.58, "total_tokens": 916352}
|
| 281 |
+
{"current_steps": 1405, "total_steps": 38160, "loss": 0.5876, "lr": 0.00036792452830188677, "epoch": 0.7363731656184487, "percentage": 3.68, "elapsed_time": "0:03:24", "remaining_time": "1:29:14", "throughput": 4490.58, "total_tokens": 919136}
|
| 282 |
+
{"current_steps": 1410, "total_steps": 38160, "loss": 0.6209, "lr": 0.0003692348008385744, "epoch": 0.7389937106918238, "percentage": 3.69, "elapsed_time": "0:03:25", "remaining_time": "1:29:11", "throughput": 4489.13, "total_tokens": 921760}
|
| 283 |
+
{"current_steps": 1415, "total_steps": 38160, "loss": 0.4471, "lr": 0.00037054507337526204, "epoch": 0.7416142557651991, "percentage": 3.71, "elapsed_time": "0:03:25", "remaining_time": "1:29:07", "throughput": 4487.29, "total_tokens": 924096}
|
| 284 |
+
{"current_steps": 1420, "total_steps": 38160, "loss": 0.5425, "lr": 0.0003718553459119497, "epoch": 0.7442348008385744, "percentage": 3.72, "elapsed_time": "0:03:26", "remaining_time": "1:29:03", "throughput": 4484.95, "total_tokens": 926240}
|
| 285 |
+
{"current_steps": 1425, "total_steps": 38160, "loss": 0.4887, "lr": 0.0003731656184486373, "epoch": 0.7468553459119497, "percentage": 3.73, "elapsed_time": "0:03:27", "remaining_time": "1:29:00", "throughput": 4483.99, "total_tokens": 928928}
|
| 286 |
+
{"current_steps": 1430, "total_steps": 38160, "loss": 0.6563, "lr": 0.000374475890985325, "epoch": 0.749475890985325, "percentage": 3.75, "elapsed_time": "0:03:27", "remaining_time": "1:28:57", "throughput": 4482.75, "total_tokens": 931552}
|
| 287 |
+
{"current_steps": 1435, "total_steps": 38160, "loss": 0.4741, "lr": 0.00037578616352201263, "epoch": 0.7520964360587002, "percentage": 3.76, "elapsed_time": "0:03:28", "remaining_time": "1:28:59", "throughput": 4484.75, "total_tokens": 935648}
|
| 288 |
+
{"current_steps": 1440, "total_steps": 38160, "loss": 0.4865, "lr": 0.0003770964360587002, "epoch": 0.7547169811320755, "percentage": 3.77, "elapsed_time": "0:03:29", "remaining_time": "1:28:56", "throughput": 4483.66, "total_tokens": 938336}
|
| 289 |
+
{"current_steps": 1445, "total_steps": 38160, "loss": 0.514, "lr": 0.00037840670859538785, "epoch": 0.7573375262054507, "percentage": 3.79, "elapsed_time": "0:03:30", "remaining_time": "1:28:56", "throughput": 4484.48, "total_tokens": 941952}
|
| 290 |
+
{"current_steps": 1450, "total_steps": 38160, "loss": 0.4452, "lr": 0.0003797169811320755, "epoch": 0.759958071278826, "percentage": 3.8, "elapsed_time": "0:03:30", "remaining_time": "1:28:56", "throughput": 4484.79, "total_tokens": 945248}
|
| 291 |
+
{"current_steps": 1455, "total_steps": 38160, "loss": 0.5142, "lr": 0.0003810272536687631, "epoch": 0.7625786163522013, "percentage": 3.81, "elapsed_time": "0:03:31", "remaining_time": "1:28:55", "throughput": 4484.7, "total_tokens": 948512}
|
| 292 |
+
{"current_steps": 1460, "total_steps": 38160, "loss": 0.468, "lr": 0.00038233752620545075, "epoch": 0.7651991614255765, "percentage": 3.83, "elapsed_time": "0:03:32", "remaining_time": "1:28:54", "throughput": 4484.66, "total_tokens": 951744}
|
| 293 |
+
{"current_steps": 1465, "total_steps": 38160, "loss": 0.5076, "lr": 0.0003836477987421384, "epoch": 0.7678197064989518, "percentage": 3.84, "elapsed_time": "0:03:32", "remaining_time": "1:28:50", "throughput": 4482.44, "total_tokens": 953920}
|
| 294 |
+
{"current_steps": 1470, "total_steps": 38160, "loss": 0.4649, "lr": 0.00038495807127882596, "epoch": 0.7704402515723271, "percentage": 3.85, "elapsed_time": "0:03:33", "remaining_time": "1:28:50", "throughput": 4482.78, "total_tokens": 957376}
|
| 295 |
+
{"current_steps": 1475, "total_steps": 38160, "loss": 0.5104, "lr": 0.0003862683438155136, "epoch": 0.7730607966457023, "percentage": 3.87, "elapsed_time": "0:03:34", "remaining_time": "1:28:48", "throughput": 4482.08, "total_tokens": 960288}
|
| 296 |
+
{"current_steps": 1480, "total_steps": 38160, "loss": 0.4789, "lr": 0.0003875786163522013, "epoch": 0.7756813417190775, "percentage": 3.88, "elapsed_time": "0:03:35", "remaining_time": "1:28:49", "throughput": 4482.65, "total_tokens": 963872}
|
| 297 |
+
{"current_steps": 1485, "total_steps": 38160, "loss": 0.5305, "lr": 0.0003888888888888889, "epoch": 0.7783018867924528, "percentage": 3.89, "elapsed_time": "0:03:35", "remaining_time": "1:28:46", "throughput": 4481.03, "total_tokens": 966368}
|
| 298 |
+
{"current_steps": 1490, "total_steps": 38160, "loss": 0.4744, "lr": 0.00039019916142557656, "epoch": 0.7809224318658281, "percentage": 3.9, "elapsed_time": "0:03:36", "remaining_time": "1:28:44", "throughput": 4480.54, "total_tokens": 969344}
|
| 299 |
+
{"current_steps": 1495, "total_steps": 38160, "loss": 0.5631, "lr": 0.0003915094339622642, "epoch": 0.7835429769392034, "percentage": 3.92, "elapsed_time": "0:03:37", "remaining_time": "1:28:42", "throughput": 4480.02, "total_tokens": 972320}
|
| 300 |
+
{"current_steps": 1500, "total_steps": 38160, "loss": 0.5202, "lr": 0.00039281970649895177, "epoch": 0.7861635220125787, "percentage": 3.93, "elapsed_time": "0:03:37", "remaining_time": "1:28:45", "throughput": 4481.47, "total_tokens": 976448}
|
| 301 |
+
{"current_steps": 1505, "total_steps": 38160, "loss": 0.4556, "lr": 0.0003941299790356394, "epoch": 0.7887840670859538, "percentage": 3.94, "elapsed_time": "0:03:38", "remaining_time": "1:28:44", "throughput": 4481.51, "total_tokens": 979648}
|
| 302 |
+
{"current_steps": 1510, "total_steps": 38160, "loss": 0.3888, "lr": 0.00039544025157232704, "epoch": 0.7914046121593291, "percentage": 3.96, "elapsed_time": "0:03:39", "remaining_time": "1:28:44", "throughput": 4481.55, "total_tokens": 983040}
|
| 303 |
+
{"current_steps": 1515, "total_steps": 38160, "loss": 0.3768, "lr": 0.0003967505241090147, "epoch": 0.7940251572327044, "percentage": 3.97, "elapsed_time": "0:03:40", "remaining_time": "1:28:41", "throughput": 4480.71, "total_tokens": 985824}
|
| 304 |
+
{"current_steps": 1520, "total_steps": 38160, "loss": 0.6914, "lr": 0.0003980607966457023, "epoch": 0.7966457023060797, "percentage": 3.98, "elapsed_time": "0:03:40", "remaining_time": "1:28:44", "throughput": 4483.28, "total_tokens": 990368}
|
| 305 |
+
{"current_steps": 1525, "total_steps": 38160, "loss": 0.5481, "lr": 0.00039937106918238994, "epoch": 0.799266247379455, "percentage": 4.0, "elapsed_time": "0:03:41", "remaining_time": "1:28:44", "throughput": 4483.94, "total_tokens": 993920}
|
| 306 |
+
{"current_steps": 1530, "total_steps": 38160, "loss": 0.54, "lr": 0.0004006813417190776, "epoch": 0.8018867924528302, "percentage": 4.01, "elapsed_time": "0:03:42", "remaining_time": "1:28:44", "throughput": 4484.15, "total_tokens": 997280}
|
| 307 |
+
{"current_steps": 1535, "total_steps": 38160, "loss": 0.6919, "lr": 0.0004019916142557652, "epoch": 0.8045073375262054, "percentage": 4.02, "elapsed_time": "0:03:43", "remaining_time": "1:28:42", "throughput": 4483.44, "total_tokens": 1000096}
|
| 308 |
+
{"current_steps": 1540, "total_steps": 38160, "loss": 0.3974, "lr": 0.00040330188679245284, "epoch": 0.8071278825995807, "percentage": 4.04, "elapsed_time": "0:03:43", "remaining_time": "1:28:39", "throughput": 4482.18, "total_tokens": 1002624}
|
| 309 |
+
{"current_steps": 1545, "total_steps": 38160, "loss": 0.5033, "lr": 0.0004046121593291405, "epoch": 0.809748427672956, "percentage": 4.05, "elapsed_time": "0:03:44", "remaining_time": "1:28:37", "throughput": 4481.32, "total_tokens": 1005440}
|
| 310 |
+
{"current_steps": 1550, "total_steps": 38160, "loss": 0.6111, "lr": 0.0004059224318658281, "epoch": 0.8123689727463312, "percentage": 4.06, "elapsed_time": "0:03:45", "remaining_time": "1:28:38", "throughput": 4482.34, "total_tokens": 1009248}
|
| 311 |
+
{"current_steps": 1555, "total_steps": 38160, "loss": 0.5193, "lr": 0.00040723270440251575, "epoch": 0.8149895178197065, "percentage": 4.07, "elapsed_time": "0:03:45", "remaining_time": "1:28:35", "throughput": 4480.88, "total_tokens": 1011744}
|
| 312 |
+
{"current_steps": 1560, "total_steps": 38160, "loss": 0.4926, "lr": 0.00040854297693920333, "epoch": 0.8176100628930818, "percentage": 4.09, "elapsed_time": "0:03:46", "remaining_time": "1:28:32", "throughput": 4479.98, "total_tokens": 1014432}
|
| 313 |
+
{"current_steps": 1565, "total_steps": 38160, "loss": 0.5703, "lr": 0.00040985324947589096, "epoch": 0.820230607966457, "percentage": 4.1, "elapsed_time": "0:03:47", "remaining_time": "1:28:31", "throughput": 4479.59, "total_tokens": 1017472}
|
| 314 |
+
{"current_steps": 1570, "total_steps": 38160, "loss": 0.6236, "lr": 0.0004111635220125786, "epoch": 0.8228511530398323, "percentage": 4.11, "elapsed_time": "0:03:47", "remaining_time": "1:28:28", "throughput": 4478.46, "total_tokens": 1020128}
|
| 315 |
+
{"current_steps": 1575, "total_steps": 38160, "loss": 0.4076, "lr": 0.00041247379454926623, "epoch": 0.8254716981132075, "percentage": 4.13, "elapsed_time": "0:03:48", "remaining_time": "1:28:27", "throughput": 4478.44, "total_tokens": 1023200}
|
| 316 |
+
{"current_steps": 1580, "total_steps": 38160, "loss": 0.648, "lr": 0.0004137840670859539, "epoch": 0.8280922431865828, "percentage": 4.14, "elapsed_time": "0:03:49", "remaining_time": "1:28:26", "throughput": 4478.76, "total_tokens": 1026592}
|
| 317 |
+
{"current_steps": 1585, "total_steps": 38160, "loss": 0.4616, "lr": 0.00041509433962264155, "epoch": 0.8307127882599581, "percentage": 4.15, "elapsed_time": "0:03:49", "remaining_time": "1:28:24", "throughput": 4477.5, "total_tokens": 1029216}
|
| 318 |
+
{"current_steps": 1590, "total_steps": 38160, "loss": 0.6045, "lr": 0.00041640461215932913, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:03:50", "remaining_time": "1:28:25", "throughput": 4478.32, "total_tokens": 1032960}
|
| 319 |
+
{"current_steps": 1595, "total_steps": 38160, "loss": 0.5001, "lr": 0.00041771488469601677, "epoch": 0.8359538784067087, "percentage": 4.18, "elapsed_time": "0:03:51", "remaining_time": "1:28:24", "throughput": 4478.38, "total_tokens": 1036224}
|
| 320 |
+
{"current_steps": 1600, "total_steps": 38160, "loss": 0.4573, "lr": 0.0004190251572327044, "epoch": 0.8385744234800838, "percentage": 4.19, "elapsed_time": "0:03:52", "remaining_time": "1:28:26", "throughput": 4480.65, "total_tokens": 1040608}
|
| 321 |
+
{"current_steps": 1605, "total_steps": 38160, "loss": 0.4586, "lr": 0.00042033542976939204, "epoch": 0.8411949685534591, "percentage": 4.21, "elapsed_time": "0:03:52", "remaining_time": "1:28:25", "throughput": 4480.29, "total_tokens": 1043648}
|
| 322 |
+
{"current_steps": 1610, "total_steps": 38160, "loss": 0.4629, "lr": 0.00042164570230607967, "epoch": 0.8438155136268344, "percentage": 4.22, "elapsed_time": "0:03:53", "remaining_time": "1:28:23", "throughput": 4479.35, "total_tokens": 1046400}
|
| 323 |
+
{"current_steps": 1615, "total_steps": 38160, "loss": 0.4952, "lr": 0.0004229559748427673, "epoch": 0.8464360587002097, "percentage": 4.23, "elapsed_time": "0:03:54", "remaining_time": "1:28:22", "throughput": 4479.04, "total_tokens": 1049568}
|
| 324 |
+
{"current_steps": 1620, "total_steps": 38160, "loss": 0.5862, "lr": 0.00042426624737945494, "epoch": 0.8490566037735849, "percentage": 4.25, "elapsed_time": "0:03:54", "remaining_time": "1:28:20", "throughput": 4478.02, "total_tokens": 1052288}
|
| 325 |
+
{"current_steps": 1625, "total_steps": 38160, "loss": 0.6671, "lr": 0.0004255765199161425, "epoch": 0.8516771488469602, "percentage": 4.26, "elapsed_time": "0:03:55", "remaining_time": "1:28:21", "throughput": 4479.04, "total_tokens": 1056096}
|
| 326 |
+
{"current_steps": 1630, "total_steps": 38160, "loss": 0.4759, "lr": 0.0004268867924528302, "epoch": 0.8542976939203354, "percentage": 4.27, "elapsed_time": "0:03:56", "remaining_time": "1:28:22", "throughput": 4480.2, "total_tokens": 1059968}
|
| 327 |
+
{"current_steps": 1635, "total_steps": 38160, "loss": 0.452, "lr": 0.00042819706498951784, "epoch": 0.8569182389937107, "percentage": 4.28, "elapsed_time": "0:03:57", "remaining_time": "1:28:21", "throughput": 4480.1, "total_tokens": 1063136}
|
| 328 |
+
{"current_steps": 1640, "total_steps": 38160, "loss": 0.5213, "lr": 0.0004295073375262055, "epoch": 0.859538784067086, "percentage": 4.3, "elapsed_time": "0:03:58", "remaining_time": "1:28:24", "throughput": 4482.11, "total_tokens": 1067616}
|
| 329 |
+
{"current_steps": 1645, "total_steps": 38160, "loss": 0.5748, "lr": 0.0004308176100628931, "epoch": 0.8621593291404612, "percentage": 4.31, "elapsed_time": "0:03:58", "remaining_time": "1:28:24", "throughput": 4482.78, "total_tokens": 1071168}
|
| 330 |
+
{"current_steps": 1650, "total_steps": 38160, "loss": 0.3935, "lr": 0.00043212788259958075, "epoch": 0.8647798742138365, "percentage": 4.32, "elapsed_time": "0:03:59", "remaining_time": "1:28:27", "throughput": 4485.14, "total_tokens": 1075808}
|
| 331 |
+
{"current_steps": 1655, "total_steps": 38160, "loss": 0.5966, "lr": 0.0004334381551362683, "epoch": 0.8674004192872118, "percentage": 4.34, "elapsed_time": "0:04:00", "remaining_time": "1:28:30", "throughput": 4486.84, "total_tokens": 1080224}
|
| 332 |
+
{"current_steps": 1660, "total_steps": 38160, "loss": 0.6491, "lr": 0.00043474842767295596, "epoch": 0.870020964360587, "percentage": 4.35, "elapsed_time": "0:04:01", "remaining_time": "1:28:30", "throughput": 4487.6, "total_tokens": 1083808}
|
| 333 |
+
{"current_steps": 1665, "total_steps": 38160, "loss": 0.6254, "lr": 0.0004360587002096436, "epoch": 0.8726415094339622, "percentage": 4.36, "elapsed_time": "0:04:02", "remaining_time": "1:28:27", "throughput": 4486.22, "total_tokens": 1086304}
|
| 334 |
+
{"current_steps": 1670, "total_steps": 38160, "loss": 0.6262, "lr": 0.00043736897274633123, "epoch": 0.8752620545073375, "percentage": 4.38, "elapsed_time": "0:04:02", "remaining_time": "1:28:27", "throughput": 4486.75, "total_tokens": 1089856}
|
| 335 |
+
{"current_steps": 1675, "total_steps": 38160, "loss": 0.4421, "lr": 0.00043867924528301886, "epoch": 0.8778825995807128, "percentage": 4.39, "elapsed_time": "0:04:03", "remaining_time": "1:28:25", "throughput": 4486.05, "total_tokens": 1092576}
|
| 336 |
+
{"current_steps": 1680, "total_steps": 38160, "loss": 0.453, "lr": 0.00043998951781970655, "epoch": 0.8805031446540881, "percentage": 4.4, "elapsed_time": "0:04:04", "remaining_time": "1:28:25", "throughput": 4487.37, "total_tokens": 1096448}
|
| 337 |
+
{"current_steps": 1685, "total_steps": 38160, "loss": 0.4301, "lr": 0.00044129979035639413, "epoch": 0.8831236897274634, "percentage": 4.42, "elapsed_time": "0:04:05", "remaining_time": "1:28:27", "throughput": 4488.59, "total_tokens": 1100448}
|
| 338 |
+
{"current_steps": 1690, "total_steps": 38160, "loss": 0.5105, "lr": 0.00044261006289308177, "epoch": 0.8857442348008385, "percentage": 4.43, "elapsed_time": "0:04:05", "remaining_time": "1:28:25", "throughput": 4488.14, "total_tokens": 1103520}
|
| 339 |
+
{"current_steps": 1695, "total_steps": 38160, "loss": 0.3949, "lr": 0.0004439203354297694, "epoch": 0.8883647798742138, "percentage": 4.44, "elapsed_time": "0:04:06", "remaining_time": "1:28:23", "throughput": 4487.37, "total_tokens": 1106304}
|
| 340 |
+
{"current_steps": 1700, "total_steps": 38160, "loss": 0.5114, "lr": 0.00044523060796645704, "epoch": 0.8909853249475891, "percentage": 4.45, "elapsed_time": "0:04:07", "remaining_time": "1:28:24", "throughput": 4488.52, "total_tokens": 1110176}
|
| 341 |
+
{"current_steps": 1705, "total_steps": 38160, "loss": 0.4924, "lr": 0.00044654088050314467, "epoch": 0.8936058700209644, "percentage": 4.47, "elapsed_time": "0:04:07", "remaining_time": "1:28:21", "throughput": 4487.02, "total_tokens": 1112640}
|
| 342 |
+
{"current_steps": 1710, "total_steps": 38160, "loss": 0.516, "lr": 0.0004478511530398323, "epoch": 0.8962264150943396, "percentage": 4.48, "elapsed_time": "0:04:08", "remaining_time": "1:28:23", "throughput": 4488.6, "total_tokens": 1116736}
|
| 343 |
+
{"current_steps": 1715, "total_steps": 38160, "loss": 0.4428, "lr": 0.0004491614255765199, "epoch": 0.8988469601677149, "percentage": 4.49, "elapsed_time": "0:04:09", "remaining_time": "1:28:22", "throughput": 4488.68, "total_tokens": 1120000}
|
| 344 |
+
{"current_steps": 1720, "total_steps": 38160, "loss": 0.4131, "lr": 0.0004504716981132075, "epoch": 0.9014675052410901, "percentage": 4.51, "elapsed_time": "0:04:10", "remaining_time": "1:28:20", "throughput": 4487.51, "total_tokens": 1122656}
|
| 345 |
+
{"current_steps": 1725, "total_steps": 38160, "loss": 0.4884, "lr": 0.00045178197064989515, "epoch": 0.9040880503144654, "percentage": 4.52, "elapsed_time": "0:04:10", "remaining_time": "1:28:19", "throughput": 4487.38, "total_tokens": 1125856}
|
| 346 |
+
{"current_steps": 1730, "total_steps": 38160, "loss": 0.4906, "lr": 0.00045309224318658284, "epoch": 0.9067085953878407, "percentage": 4.53, "elapsed_time": "0:04:11", "remaining_time": "1:28:16", "throughput": 4486.02, "total_tokens": 1128288}
|
| 347 |
+
{"current_steps": 1735, "total_steps": 38160, "loss": 0.5725, "lr": 0.0004544025157232705, "epoch": 0.9093291404612159, "percentage": 4.55, "elapsed_time": "0:04:12", "remaining_time": "1:28:15", "throughput": 4486.18, "total_tokens": 1131680}
|
| 348 |
+
{"current_steps": 1740, "total_steps": 38160, "loss": 0.4744, "lr": 0.0004557127882599581, "epoch": 0.9119496855345912, "percentage": 4.56, "elapsed_time": "0:04:12", "remaining_time": "1:28:14", "throughput": 4485.45, "total_tokens": 1134496}
|
| 349 |
+
{"current_steps": 1745, "total_steps": 38160, "loss": 0.4571, "lr": 0.0004570230607966457, "epoch": 0.9145702306079665, "percentage": 4.57, "elapsed_time": "0:04:13", "remaining_time": "1:28:14", "throughput": 4485.85, "total_tokens": 1138176}
|
| 350 |
+
{"current_steps": 1750, "total_steps": 38160, "loss": 0.3959, "lr": 0.0004583333333333333, "epoch": 0.9171907756813418, "percentage": 4.59, "elapsed_time": "0:04:14", "remaining_time": "1:28:12", "throughput": 4485.28, "total_tokens": 1141056}
|
| 351 |
+
{"current_steps": 1755, "total_steps": 38160, "loss": 0.4691, "lr": 0.00045964360587002096, "epoch": 0.9198113207547169, "percentage": 4.6, "elapsed_time": "0:04:15", "remaining_time": "1:28:12", "throughput": 4485.0, "total_tokens": 1144224}
|
| 352 |
+
{"current_steps": 1760, "total_steps": 38160, "loss": 0.5113, "lr": 0.0004609538784067086, "epoch": 0.9224318658280922, "percentage": 4.61, "elapsed_time": "0:04:15", "remaining_time": "1:28:09", "throughput": 4483.75, "total_tokens": 1146720}
|
| 353 |
+
{"current_steps": 1765, "total_steps": 38160, "loss": 0.6513, "lr": 0.00046226415094339623, "epoch": 0.9250524109014675, "percentage": 4.63, "elapsed_time": "0:04:16", "remaining_time": "1:28:06", "throughput": 4482.64, "total_tokens": 1149312}
|
| 354 |
+
{"current_steps": 1770, "total_steps": 38160, "loss": 0.5014, "lr": 0.00046357442348008386, "epoch": 0.9276729559748428, "percentage": 4.64, "elapsed_time": "0:04:17", "remaining_time": "1:28:05", "throughput": 4482.0, "total_tokens": 1152224}
|
| 355 |
+
{"current_steps": 1775, "total_steps": 38160, "loss": 0.4911, "lr": 0.00046488469601677155, "epoch": 0.9302935010482181, "percentage": 4.65, "elapsed_time": "0:04:17", "remaining_time": "1:28:04", "throughput": 4481.97, "total_tokens": 1155456}
|
| 356 |
+
{"current_steps": 1780, "total_steps": 38160, "loss": 0.4912, "lr": 0.00046619496855345913, "epoch": 0.9329140461215933, "percentage": 4.66, "elapsed_time": "0:04:18", "remaining_time": "1:28:04", "throughput": 4481.95, "total_tokens": 1158752}
|
| 357 |
+
{"current_steps": 1785, "total_steps": 38160, "loss": 0.5525, "lr": 0.00046750524109014677, "epoch": 0.9355345911949685, "percentage": 4.68, "elapsed_time": "0:04:19", "remaining_time": "1:28:02", "throughput": 4481.25, "total_tokens": 1161632}
|
| 358 |
+
{"current_steps": 1790, "total_steps": 38160, "loss": 0.4952, "lr": 0.0004688155136268344, "epoch": 0.9381551362683438, "percentage": 4.69, "elapsed_time": "0:04:20", "remaining_time": "1:28:03", "throughput": 4482.42, "total_tokens": 1165536}
|
| 359 |
+
{"current_steps": 1795, "total_steps": 38160, "loss": 0.6191, "lr": 0.00047012578616352203, "epoch": 0.9407756813417191, "percentage": 4.7, "elapsed_time": "0:04:20", "remaining_time": "1:28:02", "throughput": 4482.97, "total_tokens": 1168992}
|
| 360 |
+
{"current_steps": 1800, "total_steps": 38160, "loss": 0.444, "lr": 0.00047143605870020967, "epoch": 0.9433962264150944, "percentage": 4.72, "elapsed_time": "0:04:21", "remaining_time": "1:28:00", "throughput": 4482.13, "total_tokens": 1171648}
|
| 361 |
+
{"current_steps": 1805, "total_steps": 38160, "loss": 0.6414, "lr": 0.0004727463312368973, "epoch": 0.9460167714884696, "percentage": 4.73, "elapsed_time": "0:04:22", "remaining_time": "1:27:59", "throughput": 4482.13, "total_tokens": 1174912}
|
| 362 |
+
{"current_steps": 1810, "total_steps": 38160, "loss": 0.4039, "lr": 0.0004740566037735849, "epoch": 0.9486373165618449, "percentage": 4.74, "elapsed_time": "0:04:22", "remaining_time": "1:27:58", "throughput": 4482.28, "total_tokens": 1178144}
|
| 363 |
+
{"current_steps": 1815, "total_steps": 38160, "loss": 0.403, "lr": 0.0004753668763102725, "epoch": 0.9512578616352201, "percentage": 4.76, "elapsed_time": "0:04:23", "remaining_time": "1:27:59", "throughput": 4482.96, "total_tokens": 1181856}
|
| 364 |
+
{"current_steps": 1820, "total_steps": 38160, "loss": 0.6034, "lr": 0.00047667714884696015, "epoch": 0.9538784067085954, "percentage": 4.77, "elapsed_time": "0:04:24", "remaining_time": "1:27:58", "throughput": 4482.54, "total_tokens": 1184896}
|
| 365 |
+
{"current_steps": 1825, "total_steps": 38160, "loss": 0.7188, "lr": 0.00047798742138364784, "epoch": 0.9564989517819706, "percentage": 4.78, "elapsed_time": "0:04:24", "remaining_time": "1:27:54", "throughput": 4481.14, "total_tokens": 1187264}
|
| 366 |
+
{"current_steps": 1830, "total_steps": 38160, "loss": 0.4858, "lr": 0.0004792976939203355, "epoch": 0.9591194968553459, "percentage": 4.8, "elapsed_time": "0:04:25", "remaining_time": "1:27:55", "throughput": 4482.36, "total_tokens": 1191168}
|
| 367 |
+
{"current_steps": 1835, "total_steps": 38160, "loss": 0.4371, "lr": 0.0004806079664570231, "epoch": 0.9617400419287212, "percentage": 4.81, "elapsed_time": "0:04:26", "remaining_time": "1:27:52", "throughput": 4481.2, "total_tokens": 1193664}
|
| 368 |
+
{"current_steps": 1840, "total_steps": 38160, "loss": 0.4543, "lr": 0.0004819182389937107, "epoch": 0.9643605870020965, "percentage": 4.82, "elapsed_time": "0:04:27", "remaining_time": "1:28:03", "throughput": 4486.68, "total_tokens": 1200864}
|
| 369 |
+
{"current_steps": 1845, "total_steps": 38160, "loss": 0.4646, "lr": 0.0004832285115303983, "epoch": 0.9669811320754716, "percentage": 4.83, "elapsed_time": "0:04:28", "remaining_time": "1:28:01", "throughput": 4485.97, "total_tokens": 1203680}
|
| 370 |
+
{"current_steps": 1850, "total_steps": 38160, "loss": 0.5537, "lr": 0.00048453878406708596, "epoch": 0.9696016771488469, "percentage": 4.85, "elapsed_time": "0:04:29", "remaining_time": "1:28:02", "throughput": 4487.04, "total_tokens": 1207648}
|
| 371 |
+
{"current_steps": 1855, "total_steps": 38160, "loss": 0.4967, "lr": 0.0004858490566037736, "epoch": 0.9722222222222222, "percentage": 4.86, "elapsed_time": "0:04:29", "remaining_time": "1:28:02", "throughput": 4487.47, "total_tokens": 1211232}
|
| 372 |
+
{"current_steps": 1860, "total_steps": 38160, "loss": 0.4525, "lr": 0.0004871593291404612, "epoch": 0.9748427672955975, "percentage": 4.87, "elapsed_time": "0:04:30", "remaining_time": "1:28:01", "throughput": 4487.2, "total_tokens": 1214304}
|
| 373 |
+
{"current_steps": 1865, "total_steps": 38160, "loss": 0.3894, "lr": 0.0004884696016771489, "epoch": 0.9774633123689728, "percentage": 4.89, "elapsed_time": "0:04:31", "remaining_time": "1:28:00", "throughput": 4487.44, "total_tokens": 1217664}
|
| 374 |
+
{"current_steps": 1870, "total_steps": 38160, "loss": 0.3924, "lr": 0.0004897798742138365, "epoch": 0.980083857442348, "percentage": 4.9, "elapsed_time": "0:04:32", "remaining_time": "1:28:00", "throughput": 4487.74, "total_tokens": 1221184}
|
| 375 |
+
{"current_steps": 1875, "total_steps": 38160, "loss": 0.4821, "lr": 0.0004910901467505241, "epoch": 0.9827044025157232, "percentage": 4.91, "elapsed_time": "0:04:32", "remaining_time": "1:28:00", "throughput": 4488.13, "total_tokens": 1224736}
|
| 376 |
+
{"current_steps": 1880, "total_steps": 38160, "loss": 0.4982, "lr": 0.0004924004192872118, "epoch": 0.9853249475890985, "percentage": 4.93, "elapsed_time": "0:04:33", "remaining_time": "1:28:00", "throughput": 4488.74, "total_tokens": 1228256}
|
| 377 |
+
{"current_steps": 1885, "total_steps": 38160, "loss": 0.7353, "lr": 0.0004937106918238993, "epoch": 0.9879454926624738, "percentage": 4.94, "elapsed_time": "0:04:34", "remaining_time": "1:27:58", "throughput": 4488.08, "total_tokens": 1231104}
|
| 378 |
+
{"current_steps": 1890, "total_steps": 38160, "loss": 0.4709, "lr": 0.000495020964360587, "epoch": 0.9905660377358491, "percentage": 4.95, "elapsed_time": "0:04:35", "remaining_time": "1:27:57", "throughput": 4487.81, "total_tokens": 1234176}
|
| 379 |
+
{"current_steps": 1895, "total_steps": 38160, "loss": 0.4626, "lr": 0.0004963312368972746, "epoch": 0.9931865828092243, "percentage": 4.97, "elapsed_time": "0:04:35", "remaining_time": "1:27:57", "throughput": 4487.97, "total_tokens": 1237568}
|
| 380 |
+
{"current_steps": 1900, "total_steps": 38160, "loss": 0.6021, "lr": 0.0004976415094339623, "epoch": 0.9958071278825996, "percentage": 4.98, "elapsed_time": "0:04:36", "remaining_time": "1:27:56", "throughput": 4488.16, "total_tokens": 1240896}
|
| 381 |
+
{"current_steps": 1905, "total_steps": 38160, "loss": 0.6502, "lr": 0.0004989517819706499, "epoch": 0.9984276729559748, "percentage": 4.99, "elapsed_time": "0:04:37", "remaining_time": "1:27:55", "throughput": 4488.58, "total_tokens": 1244288}
|
| 382 |
+
{"current_steps": 1908, "total_steps": 38160, "eval_loss": 0.5047244429588318, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:04:51", "remaining_time": "1:32:15", "throughput": 4274.59, "total_tokens": 1245424}
|
| 383 |
+
{"current_steps": 1910, "total_steps": 38160, "loss": 0.4655, "lr": 0.0005002620545073376, "epoch": 1.00104821802935, "percentage": 5.01, "elapsed_time": "0:04:53", "remaining_time": "1:32:47", "throughput": 4250.11, "total_tokens": 1246832}
|
| 384 |
+
{"current_steps": 1915, "total_steps": 38160, "loss": 0.45, "lr": 0.0005015723270440253, "epoch": 1.0036687631027255, "percentage": 5.02, "elapsed_time": "0:04:54", "remaining_time": "1:32:45", "throughput": 4250.58, "total_tokens": 1250000}
|
| 385 |
+
{"current_steps": 1920, "total_steps": 38160, "loss": 0.5823, "lr": 0.0005028825995807128, "epoch": 1.0062893081761006, "percentage": 5.03, "elapsed_time": "0:04:54", "remaining_time": "1:32:44", "throughput": 4251.57, "total_tokens": 1253488}
|
| 386 |
+
{"current_steps": 1925, "total_steps": 38160, "loss": 0.527, "lr": 0.0005041928721174004, "epoch": 1.0089098532494758, "percentage": 5.04, "elapsed_time": "0:04:55", "remaining_time": "1:32:45", "throughput": 4253.79, "total_tokens": 1257744}
|
| 387 |
+
{"current_steps": 1930, "total_steps": 38160, "loss": 0.3572, "lr": 0.0005055031446540881, "epoch": 1.0115303983228512, "percentage": 5.06, "elapsed_time": "0:04:56", "remaining_time": "1:32:43", "throughput": 4253.9, "total_tokens": 1260688}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf8d49de24776200830d820d6d179a5cb44f256ad7c0e23e1c671e3eb1328b2c
|
| 3 |
+
size 6353
|