Training in progress, step 1294
Browse files- .gitattributes +1 -0
- adapter_config.json +18 -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 +283 -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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"modules_to_save": null,
|
| 10 |
+
"num_attention_heads": 32,
|
| 11 |
+
"num_layers": 32,
|
| 12 |
+
"num_transformer_submodules": 1,
|
| 13 |
+
"num_virtual_tokens": 100,
|
| 14 |
+
"peft_type": "P_TUNING",
|
| 15 |
+
"revision": null,
|
| 16 |
+
"task_type": "CAUSAL_LM",
|
| 17 |
+
"token_dim": 4096
|
| 18 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:675a81bd6625fdeadebe3c3f35b164c44e35c4d2a754c94cbc4beb141f6f3589
|
| 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: stsb
|
| 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_stsb_101112_1760638038
|
| 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_stsb_101112_1760638038
|
| 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 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 25880, "loss": 7.7862, "lr": 1.5455950540958269e-06, "epoch": 0.0038639876352395673, "percentage": 0.02, "elapsed_time": "0:00:01", "remaining_time": "1:47:35", "throughput": 1205.69, "total_tokens": 1504}
|
| 2 |
+
{"current_steps": 10, "total_steps": 25880, "loss": 7.1288, "lr": 3.4775888717156106e-06, "epoch": 0.0077279752704791345, "percentage": 0.04, "elapsed_time": "0:00:02", "remaining_time": "1:27:09", "throughput": 1456.36, "total_tokens": 2944}
|
| 3 |
+
{"current_steps": 15, "total_steps": 25880, "loss": 6.1085, "lr": 5.409582689335394e-06, "epoch": 0.011591962905718702, "percentage": 0.06, "elapsed_time": "0:00:02", "remaining_time": "1:21:26", "throughput": 1637.29, "total_tokens": 4640}
|
| 4 |
+
{"current_steps": 20, "total_steps": 25880, "loss": 4.9051, "lr": 7.341576506955177e-06, "epoch": 0.015455950540958269, "percentage": 0.08, "elapsed_time": "0:00:03", "remaining_time": "1:21:01", "throughput": 1659.53, "total_tokens": 6240}
|
| 5 |
+
{"current_steps": 25, "total_steps": 25880, "loss": 4.1451, "lr": 9.273570324574962e-06, "epoch": 0.019319938176197836, "percentage": 0.1, "elapsed_time": "0:00:04", "remaining_time": "1:18:43", "throughput": 1716.71, "total_tokens": 7840}
|
| 6 |
+
{"current_steps": 30, "total_steps": 25880, "loss": 4.98, "lr": 1.1205564142194746e-05, "epoch": 0.023183925811437404, "percentage": 0.12, "elapsed_time": "0:00:05", "remaining_time": "1:17:37", "throughput": 1764.11, "total_tokens": 9536}
|
| 7 |
+
{"current_steps": 35, "total_steps": 25880, "loss": 3.9946, "lr": 1.3137557959814529e-05, "epoch": 0.02704791344667697, "percentage": 0.14, "elapsed_time": "0:00:06", "remaining_time": "1:16:56", "throughput": 1806.84, "total_tokens": 11296}
|
| 8 |
+
{"current_steps": 40, "total_steps": 25880, "loss": 4.3828, "lr": 1.5069551777434311e-05, "epoch": 0.030911901081916538, "percentage": 0.15, "elapsed_time": "0:00:07", "remaining_time": "1:16:10", "throughput": 1831.8, "total_tokens": 12960}
|
| 9 |
+
{"current_steps": 45, "total_steps": 25880, "loss": 3.2908, "lr": 1.7001545595054096e-05, "epoch": 0.0347758887171561, "percentage": 0.17, "elapsed_time": "0:00:07", "remaining_time": "1:15:07", "throughput": 1842.2, "total_tokens": 14464}
|
| 10 |
+
{"current_steps": 50, "total_steps": 25880, "loss": 3.2252, "lr": 1.893353941267388e-05, "epoch": 0.03863987635239567, "percentage": 0.19, "elapsed_time": "0:00:08", "remaining_time": "1:14:34", "throughput": 1850.8, "total_tokens": 16032}
|
| 11 |
+
{"current_steps": 55, "total_steps": 25880, "loss": 3.0544, "lr": 2.0865533230293665e-05, "epoch": 0.04250386398763524, "percentage": 0.21, "elapsed_time": "0:00:09", "remaining_time": "1:13:59", "throughput": 1864.74, "total_tokens": 17632}
|
| 12 |
+
{"current_steps": 60, "total_steps": 25880, "loss": 3.4859, "lr": 2.2797527047913446e-05, "epoch": 0.04636785162287481, "percentage": 0.23, "elapsed_time": "0:00:10", "remaining_time": "1:14:04", "throughput": 1880.72, "total_tokens": 19424}
|
| 13 |
+
{"current_steps": 65, "total_steps": 25880, "loss": 3.2878, "lr": 2.472952086553323e-05, "epoch": 0.05023183925811438, "percentage": 0.25, "elapsed_time": "0:00:11", "remaining_time": "1:13:29", "throughput": 1882.24, "total_tokens": 20896}
|
| 14 |
+
{"current_steps": 70, "total_steps": 25880, "loss": 3.338, "lr": 2.6661514683153014e-05, "epoch": 0.05409582689335394, "percentage": 0.27, "elapsed_time": "0:00:11", "remaining_time": "1:13:13", "throughput": 1887.85, "total_tokens": 22496}
|
| 15 |
+
{"current_steps": 75, "total_steps": 25880, "loss": 3.1033, "lr": 2.85935085007728e-05, "epoch": 0.05795981452859351, "percentage": 0.29, "elapsed_time": "0:00:12", "remaining_time": "1:12:55", "throughput": 1887.21, "total_tokens": 24000}
|
| 16 |
+
{"current_steps": 80, "total_steps": 25880, "loss": 3.0596, "lr": 3.0525502318392587e-05, "epoch": 0.061823802163833076, "percentage": 0.31, "elapsed_time": "0:00:13", "remaining_time": "1:12:42", "throughput": 1894.83, "total_tokens": 25632}
|
| 17 |
+
{"current_steps": 85, "total_steps": 25880, "loss": 3.0762, "lr": 3.2457496136012364e-05, "epoch": 0.06568778979907264, "percentage": 0.33, "elapsed_time": "0:00:14", "remaining_time": "1:12:51", "throughput": 1908.09, "total_tokens": 27488}
|
| 18 |
+
{"current_steps": 90, "total_steps": 25880, "loss": 3.2313, "lr": 3.438948995363215e-05, "epoch": 0.0695517774343122, "percentage": 0.35, "elapsed_time": "0:00:15", "remaining_time": "1:12:38", "throughput": 1910.11, "total_tokens": 29056}
|
| 19 |
+
{"current_steps": 95, "total_steps": 25880, "loss": 3.1552, "lr": 3.632148377125193e-05, "epoch": 0.07341576506955177, "percentage": 0.37, "elapsed_time": "0:00:16", "remaining_time": "1:12:28", "throughput": 1913.49, "total_tokens": 30656}
|
| 20 |
+
{"current_steps": 100, "total_steps": 25880, "loss": 3.1216, "lr": 3.825347758887172e-05, "epoch": 0.07727975270479134, "percentage": 0.39, "elapsed_time": "0:00:16", "remaining_time": "1:12:10", "throughput": 1914.63, "total_tokens": 32160}
|
| 21 |
+
{"current_steps": 105, "total_steps": 25880, "loss": 2.4442, "lr": 4.01854714064915e-05, "epoch": 0.08114374034003091, "percentage": 0.41, "elapsed_time": "0:00:17", "remaining_time": "1:12:10", "throughput": 1922.74, "total_tokens": 33920}
|
| 22 |
+
{"current_steps": 110, "total_steps": 25880, "loss": 2.7766, "lr": 4.2117465224111286e-05, "epoch": 0.08500772797527048, "percentage": 0.43, "elapsed_time": "0:00:18", "remaining_time": "1:12:10", "throughput": 1926.88, "total_tokens": 35616}
|
| 23 |
+
{"current_steps": 115, "total_steps": 25880, "loss": 2.5798, "lr": 4.404945904173107e-05, "epoch": 0.08887171561051005, "percentage": 0.44, "elapsed_time": "0:00:19", "remaining_time": "1:12:01", "throughput": 1926.14, "total_tokens": 37152}
|
| 24 |
+
{"current_steps": 120, "total_steps": 25880, "loss": 2.9677, "lr": 4.5981452859350855e-05, "epoch": 0.09273570324574962, "percentage": 0.46, "elapsed_time": "0:00:20", "remaining_time": "1:12:07", "throughput": 1930.35, "total_tokens": 38912}
|
| 25 |
+
{"current_steps": 125, "total_steps": 25880, "loss": 2.4499, "lr": 4.791344667697063e-05, "epoch": 0.09659969088098919, "percentage": 0.48, "elapsed_time": "0:00:20", "remaining_time": "1:12:06", "throughput": 1932.49, "total_tokens": 40576}
|
| 26 |
+
{"current_steps": 130, "total_steps": 25880, "loss": 3.0338, "lr": 4.984544049459042e-05, "epoch": 0.10046367851622875, "percentage": 0.5, "elapsed_time": "0:00:21", "remaining_time": "1:12:12", "throughput": 1939.95, "total_tokens": 42432}
|
| 27 |
+
{"current_steps": 135, "total_steps": 25880, "loss": 2.637, "lr": 5.17774343122102e-05, "epoch": 0.10432766615146831, "percentage": 0.52, "elapsed_time": "0:00:22", "remaining_time": "1:12:05", "throughput": 1941.43, "total_tokens": 44032}
|
| 28 |
+
{"current_steps": 140, "total_steps": 25880, "loss": 2.4155, "lr": 5.3709428129829986e-05, "epoch": 0.10819165378670788, "percentage": 0.54, "elapsed_time": "0:00:23", "remaining_time": "1:12:07", "throughput": 1945.67, "total_tokens": 45792}
|
| 29 |
+
{"current_steps": 145, "total_steps": 25880, "loss": 2.6693, "lr": 5.564142194744977e-05, "epoch": 0.11205564142194745, "percentage": 0.56, "elapsed_time": "0:00:24", "remaining_time": "1:12:00", "throughput": 1947.93, "total_tokens": 47424}
|
| 30 |
+
{"current_steps": 150, "total_steps": 25880, "loss": 2.4271, "lr": 5.7573415765069554e-05, "epoch": 0.11591962905718702, "percentage": 0.58, "elapsed_time": "0:00:25", "remaining_time": "1:12:01", "throughput": 1957.28, "total_tokens": 49312}
|
| 31 |
+
{"current_steps": 155, "total_steps": 25880, "loss": 2.7017, "lr": 5.950540958268934e-05, "epoch": 0.11978361669242658, "percentage": 0.6, "elapsed_time": "0:00:26", "remaining_time": "1:12:01", "throughput": 1961.47, "total_tokens": 51072}
|
| 32 |
+
{"current_steps": 160, "total_steps": 25880, "loss": 2.6894, "lr": 6.143740340030912e-05, "epoch": 0.12364760432766615, "percentage": 0.62, "elapsed_time": "0:00:26", "remaining_time": "1:12:06", "throughput": 1965.55, "total_tokens": 52896}
|
| 33 |
+
{"current_steps": 165, "total_steps": 25880, "loss": 2.5421, "lr": 6.33693972179289e-05, "epoch": 0.1275115919629057, "percentage": 0.64, "elapsed_time": "0:00:27", "remaining_time": "1:11:53", "throughput": 1960.74, "total_tokens": 54272}
|
| 34 |
+
{"current_steps": 170, "total_steps": 25880, "loss": 2.7817, "lr": 6.530139103554869e-05, "epoch": 0.13137557959814528, "percentage": 0.66, "elapsed_time": "0:00:28", "remaining_time": "1:11:55", "throughput": 1964.6, "total_tokens": 56064}
|
| 35 |
+
{"current_steps": 175, "total_steps": 25880, "loss": 2.8964, "lr": 6.723338485316847e-05, "epoch": 0.13523956723338484, "percentage": 0.68, "elapsed_time": "0:00:29", "remaining_time": "1:12:01", "throughput": 1969.98, "total_tokens": 57952}
|
| 36 |
+
{"current_steps": 180, "total_steps": 25880, "loss": 2.3523, "lr": 6.916537867078825e-05, "epoch": 0.1391035548686244, "percentage": 0.7, "elapsed_time": "0:00:30", "remaining_time": "1:11:55", "throughput": 1968.98, "total_tokens": 59520}
|
| 37 |
+
{"current_steps": 185, "total_steps": 25880, "loss": 2.4795, "lr": 7.109737248840804e-05, "epoch": 0.14296754250386398, "percentage": 0.71, "elapsed_time": "0:00:31", "remaining_time": "1:11:46", "throughput": 1968.22, "total_tokens": 61024}
|
| 38 |
+
{"current_steps": 190, "total_steps": 25880, "loss": 2.2462, "lr": 7.302936630602782e-05, "epoch": 0.14683153013910355, "percentage": 0.73, "elapsed_time": "0:00:31", "remaining_time": "1:11:50", "throughput": 1972.25, "total_tokens": 62880}
|
| 39 |
+
{"current_steps": 195, "total_steps": 25880, "loss": 2.2522, "lr": 7.496136012364761e-05, "epoch": 0.15069551777434312, "percentage": 0.75, "elapsed_time": "0:00:32", "remaining_time": "1:11:49", "throughput": 1971.73, "total_tokens": 64512}
|
| 40 |
+
{"current_steps": 200, "total_steps": 25880, "loss": 2.1573, "lr": 7.689335394126738e-05, "epoch": 0.1545595054095827, "percentage": 0.77, "elapsed_time": "0:00:33", "remaining_time": "1:11:41", "throughput": 1972.67, "total_tokens": 66080}
|
| 41 |
+
{"current_steps": 205, "total_steps": 25880, "loss": 2.0037, "lr": 7.882534775888716e-05, "epoch": 0.15842349304482226, "percentage": 0.79, "elapsed_time": "0:00:34", "remaining_time": "1:11:45", "throughput": 1976.32, "total_tokens": 67936}
|
| 42 |
+
{"current_steps": 210, "total_steps": 25880, "loss": 1.9472, "lr": 8.075734157650695e-05, "epoch": 0.16228748068006182, "percentage": 0.81, "elapsed_time": "0:00:35", "remaining_time": "1:11:37", "throughput": 1976.27, "total_tokens": 69472}
|
| 43 |
+
{"current_steps": 215, "total_steps": 25880, "loss": 2.8334, "lr": 8.268933539412673e-05, "epoch": 0.1661514683153014, "percentage": 0.83, "elapsed_time": "0:00:35", "remaining_time": "1:11:36", "throughput": 1978.92, "total_tokens": 71232}
|
| 44 |
+
{"current_steps": 220, "total_steps": 25880, "loss": 2.6078, "lr": 8.462132921174652e-05, "epoch": 0.17001545595054096, "percentage": 0.85, "elapsed_time": "0:00:36", "remaining_time": "1:11:32", "throughput": 1978.15, "total_tokens": 72800}
|
| 45 |
+
{"current_steps": 225, "total_steps": 25880, "loss": 2.0779, "lr": 8.65533230293663e-05, "epoch": 0.17387944358578053, "percentage": 0.87, "elapsed_time": "0:00:37", "remaining_time": "1:11:24", "throughput": 1976.59, "total_tokens": 74272}
|
| 46 |
+
{"current_steps": 230, "total_steps": 25880, "loss": 1.7412, "lr": 8.848531684698608e-05, "epoch": 0.1777434312210201, "percentage": 0.89, "elapsed_time": "0:00:38", "remaining_time": "1:11:27", "throughput": 1977.68, "total_tokens": 76032}
|
| 47 |
+
{"current_steps": 235, "total_steps": 25880, "loss": 1.8304, "lr": 9.041731066460587e-05, "epoch": 0.18160741885625967, "percentage": 0.91, "elapsed_time": "0:00:39", "remaining_time": "1:11:24", "throughput": 1980.58, "total_tokens": 77760}
|
| 48 |
+
{"current_steps": 240, "total_steps": 25880, "loss": 1.5196, "lr": 9.234930448222565e-05, "epoch": 0.18547140649149924, "percentage": 0.93, "elapsed_time": "0:00:40", "remaining_time": "1:11:20", "throughput": 1981.35, "total_tokens": 79392}
|
| 49 |
+
{"current_steps": 245, "total_steps": 25880, "loss": 2.0228, "lr": 9.428129829984544e-05, "epoch": 0.1893353941267388, "percentage": 0.95, "elapsed_time": "0:00:40", "remaining_time": "1:11:22", "throughput": 1984.25, "total_tokens": 81216}
|
| 50 |
+
{"current_steps": 250, "total_steps": 25880, "loss": 1.2129, "lr": 9.621329211746522e-05, "epoch": 0.19319938176197837, "percentage": 0.97, "elapsed_time": "0:00:41", "remaining_time": "1:11:26", "throughput": 1986.82, "total_tokens": 83072}
|
| 51 |
+
{"current_steps": 255, "total_steps": 25880, "loss": 1.0463, "lr": 9.8145285935085e-05, "epoch": 0.19706336939721794, "percentage": 0.99, "elapsed_time": "0:00:42", "remaining_time": "1:11:29", "throughput": 1990.18, "total_tokens": 84960}
|
| 52 |
+
{"current_steps": 260, "total_steps": 25880, "loss": 2.0793, "lr": 0.00010007727975270479, "epoch": 0.2009273570324575, "percentage": 1.0, "elapsed_time": "0:00:43", "remaining_time": "1:11:25", "throughput": 1987.42, "total_tokens": 86432}
|
| 53 |
+
{"current_steps": 265, "total_steps": 25880, "loss": 1.8098, "lr": 0.00010200927357032458, "epoch": 0.20479134466769705, "percentage": 1.02, "elapsed_time": "0:00:44", "remaining_time": "1:11:27", "throughput": 1988.13, "total_tokens": 88192}
|
| 54 |
+
{"current_steps": 270, "total_steps": 25880, "loss": 2.0379, "lr": 0.00010394126738794436, "epoch": 0.20865533230293662, "percentage": 1.04, "elapsed_time": "0:00:45", "remaining_time": "1:11:24", "throughput": 1989.3, "total_tokens": 89856}
|
| 55 |
+
{"current_steps": 275, "total_steps": 25880, "loss": 1.7293, "lr": 0.00010587326120556414, "epoch": 0.2125193199381762, "percentage": 1.06, "elapsed_time": "0:00:46", "remaining_time": "1:11:29", "throughput": 1993.01, "total_tokens": 91808}
|
| 56 |
+
{"current_steps": 280, "total_steps": 25880, "loss": 1.5195, "lr": 0.00010780525502318393, "epoch": 0.21638330757341576, "percentage": 1.08, "elapsed_time": "0:00:46", "remaining_time": "1:11:24", "throughput": 1991.0, "total_tokens": 93312}
|
| 57 |
+
{"current_steps": 285, "total_steps": 25880, "loss": 1.5934, "lr": 0.00010973724884080371, "epoch": 0.22024729520865532, "percentage": 1.1, "elapsed_time": "0:00:47", "remaining_time": "1:11:24", "throughput": 1992.11, "total_tokens": 95040}
|
| 58 |
+
{"current_steps": 290, "total_steps": 25880, "loss": 1.2623, "lr": 0.0001116692426584235, "epoch": 0.2241112828438949, "percentage": 1.12, "elapsed_time": "0:00:48", "remaining_time": "1:11:21", "throughput": 1992.52, "total_tokens": 96672}
|
| 59 |
+
{"current_steps": 295, "total_steps": 25880, "loss": 1.1045, "lr": 0.00011360123647604328, "epoch": 0.22797527047913446, "percentage": 1.14, "elapsed_time": "0:00:49", "remaining_time": "1:11:17", "throughput": 1991.79, "total_tokens": 98240}
|
| 60 |
+
{"current_steps": 300, "total_steps": 25880, "loss": 1.6427, "lr": 0.00011553323029366307, "epoch": 0.23183925811437403, "percentage": 1.16, "elapsed_time": "0:00:50", "remaining_time": "1:11:15", "throughput": 1993.13, "total_tokens": 99936}
|
| 61 |
+
{"current_steps": 305, "total_steps": 25880, "loss": 1.6161, "lr": 0.00011746522411128284, "epoch": 0.2357032457496136, "percentage": 1.18, "elapsed_time": "0:00:51", "remaining_time": "1:11:17", "throughput": 1994.7, "total_tokens": 101760}
|
| 62 |
+
{"current_steps": 310, "total_steps": 25880, "loss": 1.5556, "lr": 0.00011939721792890262, "epoch": 0.23956723338485317, "percentage": 1.2, "elapsed_time": "0:00:51", "remaining_time": "1:11:20", "throughput": 1997.86, "total_tokens": 103680}
|
| 63 |
+
{"current_steps": 315, "total_steps": 25880, "loss": 1.3256, "lr": 0.0001213292117465224, "epoch": 0.24343122102009274, "percentage": 1.22, "elapsed_time": "0:00:52", "remaining_time": "1:11:14", "throughput": 1996.98, "total_tokens": 105184}
|
| 64 |
+
{"current_steps": 320, "total_steps": 25880, "loss": 1.2554, "lr": 0.0001232612055641422, "epoch": 0.2472952086553323, "percentage": 1.24, "elapsed_time": "0:00:53", "remaining_time": "1:11:13", "throughput": 1996.32, "total_tokens": 106816}
|
| 65 |
+
{"current_steps": 325, "total_steps": 25880, "loss": 1.5058, "lr": 0.000125193199381762, "epoch": 0.2511591962905719, "percentage": 1.26, "elapsed_time": "0:00:54", "remaining_time": "1:11:10", "throughput": 1995.03, "total_tokens": 108352}
|
| 66 |
+
{"current_steps": 330, "total_steps": 25880, "loss": 1.2992, "lr": 0.00012712519319938177, "epoch": 0.2550231839258114, "percentage": 1.28, "elapsed_time": "0:00:55", "remaining_time": "1:11:04", "throughput": 1993.19, "total_tokens": 109792}
|
| 67 |
+
{"current_steps": 335, "total_steps": 25880, "loss": 1.2302, "lr": 0.00012905718701700157, "epoch": 0.258887171561051, "percentage": 1.29, "elapsed_time": "0:00:55", "remaining_time": "1:11:07", "throughput": 1994.64, "total_tokens": 111616}
|
| 68 |
+
{"current_steps": 340, "total_steps": 25880, "loss": 0.8572, "lr": 0.00013098918083462134, "epoch": 0.26275115919629055, "percentage": 1.31, "elapsed_time": "0:00:56", "remaining_time": "1:11:08", "throughput": 1994.57, "total_tokens": 113344}
|
| 69 |
+
{"current_steps": 345, "total_steps": 25880, "loss": 0.9835, "lr": 0.00013292117465224114, "epoch": 0.26661514683153015, "percentage": 1.33, "elapsed_time": "0:00:57", "remaining_time": "1:11:05", "throughput": 1993.82, "total_tokens": 114912}
|
| 70 |
+
{"current_steps": 350, "total_steps": 25880, "loss": 1.5822, "lr": 0.0001348531684698609, "epoch": 0.2704791344667697, "percentage": 1.35, "elapsed_time": "0:00:58", "remaining_time": "1:11:05", "throughput": 1996.08, "total_tokens": 116736}
|
| 71 |
+
{"current_steps": 355, "total_steps": 25880, "loss": 1.399, "lr": 0.0001367851622874807, "epoch": 0.2743431221020093, "percentage": 1.37, "elapsed_time": "0:00:59", "remaining_time": "1:11:03", "throughput": 1996.35, "total_tokens": 118368}
|
| 72 |
+
{"current_steps": 360, "total_steps": 25880, "loss": 0.9106, "lr": 0.00013871715610510048, "epoch": 0.2782071097372488, "percentage": 1.39, "elapsed_time": "0:01:00", "remaining_time": "1:11:08", "throughput": 1999.96, "total_tokens": 120416}
|
| 73 |
+
{"current_steps": 365, "total_steps": 25880, "loss": 1.0348, "lr": 0.00014064914992272025, "epoch": 0.2820710973724884, "percentage": 1.41, "elapsed_time": "0:01:01", "remaining_time": "1:11:07", "throughput": 1998.83, "total_tokens": 122016}
|
| 74 |
+
{"current_steps": 370, "total_steps": 25880, "loss": 1.5247, "lr": 0.00014258114374034005, "epoch": 0.28593508500772796, "percentage": 1.43, "elapsed_time": "0:01:01", "remaining_time": "1:11:04", "throughput": 1999.51, "total_tokens": 123680}
|
| 75 |
+
{"current_steps": 375, "total_steps": 25880, "loss": 0.9227, "lr": 0.00014451313755795982, "epoch": 0.28979907264296756, "percentage": 1.45, "elapsed_time": "0:01:02", "remaining_time": "1:11:02", "throughput": 1999.68, "total_tokens": 125312}
|
| 76 |
+
{"current_steps": 380, "total_steps": 25880, "loss": 0.9477, "lr": 0.00014644513137557962, "epoch": 0.2936630602782071, "percentage": 1.47, "elapsed_time": "0:01:03", "remaining_time": "1:11:06", "throughput": 2004.88, "total_tokens": 127456}
|
| 77 |
+
{"current_steps": 385, "total_steps": 25880, "loss": 1.3193, "lr": 0.0001483771251931994, "epoch": 0.2975270479134467, "percentage": 1.49, "elapsed_time": "0:01:04", "remaining_time": "1:11:05", "throughput": 2005.45, "total_tokens": 129184}
|
| 78 |
+
{"current_steps": 390, "total_steps": 25880, "loss": 1.3801, "lr": 0.00015030911901081918, "epoch": 0.30139103554868624, "percentage": 1.51, "elapsed_time": "0:01:05", "remaining_time": "1:11:07", "throughput": 2006.53, "total_tokens": 131008}
|
| 79 |
+
{"current_steps": 395, "total_steps": 25880, "loss": 1.095, "lr": 0.00015224111282843896, "epoch": 0.30525502318392583, "percentage": 1.53, "elapsed_time": "0:01:06", "remaining_time": "1:11:08", "throughput": 2006.77, "total_tokens": 132768}
|
| 80 |
+
{"current_steps": 400, "total_steps": 25880, "loss": 0.9064, "lr": 0.00015417310664605875, "epoch": 0.3091190108191654, "percentage": 1.55, "elapsed_time": "0:01:07", "remaining_time": "1:11:08", "throughput": 2007.75, "total_tokens": 134528}
|
| 81 |
+
{"current_steps": 405, "total_steps": 25880, "loss": 1.3143, "lr": 0.00015610510046367852, "epoch": 0.31298299845440497, "percentage": 1.56, "elapsed_time": "0:01:07", "remaining_time": "1:11:15", "throughput": 2012.17, "total_tokens": 136768}
|
| 82 |
+
{"current_steps": 410, "total_steps": 25880, "loss": 1.2316, "lr": 0.00015803709428129832, "epoch": 0.3168469860896445, "percentage": 1.58, "elapsed_time": "0:01:08", "remaining_time": "1:11:10", "throughput": 2011.36, "total_tokens": 138272}
|
| 83 |
+
{"current_steps": 415, "total_steps": 25880, "loss": 0.8127, "lr": 0.0001599690880989181, "epoch": 0.3207109737248841, "percentage": 1.6, "elapsed_time": "0:01:09", "remaining_time": "1:11:08", "throughput": 2011.48, "total_tokens": 139936}
|
| 84 |
+
{"current_steps": 420, "total_steps": 25880, "loss": 1.0606, "lr": 0.0001619010819165379, "epoch": 0.32457496136012365, "percentage": 1.62, "elapsed_time": "0:01:10", "remaining_time": "1:11:08", "throughput": 2011.49, "total_tokens": 141632}
|
| 85 |
+
{"current_steps": 425, "total_steps": 25880, "loss": 1.0405, "lr": 0.00016383307573415766, "epoch": 0.3284389489953632, "percentage": 1.64, "elapsed_time": "0:01:11", "remaining_time": "1:11:07", "throughput": 2010.79, "total_tokens": 143264}
|
| 86 |
+
{"current_steps": 430, "total_steps": 25880, "loss": 1.0991, "lr": 0.00016576506955177746, "epoch": 0.3323029366306028, "percentage": 1.66, "elapsed_time": "0:01:12", "remaining_time": "1:11:04", "throughput": 2010.83, "total_tokens": 144896}
|
| 87 |
+
{"current_steps": 435, "total_steps": 25880, "loss": 0.8358, "lr": 0.00016769706336939723, "epoch": 0.3361669242658423, "percentage": 1.68, "elapsed_time": "0:01:12", "remaining_time": "1:11:06", "throughput": 2012.82, "total_tokens": 146816}
|
| 88 |
+
{"current_steps": 440, "total_steps": 25880, "loss": 1.0301, "lr": 0.00016962905718701703, "epoch": 0.3400309119010819, "percentage": 1.7, "elapsed_time": "0:01:13", "remaining_time": "1:11:05", "throughput": 2012.49, "total_tokens": 148480}
|
| 89 |
+
{"current_steps": 445, "total_steps": 25880, "loss": 0.8317, "lr": 0.0001715610510046368, "epoch": 0.34389489953632146, "percentage": 1.72, "elapsed_time": "0:01:14", "remaining_time": "1:11:03", "throughput": 2012.51, "total_tokens": 150112}
|
| 90 |
+
{"current_steps": 450, "total_steps": 25880, "loss": 0.971, "lr": 0.0001734930448222566, "epoch": 0.34775888717156106, "percentage": 1.74, "elapsed_time": "0:01:15", "remaining_time": "1:11:00", "throughput": 2011.04, "total_tokens": 151616}
|
| 91 |
+
{"current_steps": 455, "total_steps": 25880, "loss": 0.7506, "lr": 0.00017542503863987637, "epoch": 0.3516228748068006, "percentage": 1.76, "elapsed_time": "0:01:16", "remaining_time": "1:10:55", "throughput": 2009.57, "total_tokens": 153056}
|
| 92 |
+
{"current_steps": 460, "total_steps": 25880, "loss": 0.9361, "lr": 0.00017735703245749617, "epoch": 0.3554868624420402, "percentage": 1.78, "elapsed_time": "0:01:17", "remaining_time": "1:10:57", "throughput": 2010.05, "total_tokens": 154848}
|
| 93 |
+
{"current_steps": 465, "total_steps": 25880, "loss": 0.8521, "lr": 0.00017928902627511594, "epoch": 0.35935085007727974, "percentage": 1.8, "elapsed_time": "0:01:17", "remaining_time": "1:10:54", "throughput": 2007.94, "total_tokens": 156288}
|
| 94 |
+
{"current_steps": 470, "total_steps": 25880, "loss": 0.6877, "lr": 0.00018122102009273568, "epoch": 0.36321483771251933, "percentage": 1.82, "elapsed_time": "0:01:18", "remaining_time": "1:10:50", "throughput": 2007.59, "total_tokens": 157824}
|
| 95 |
+
{"current_steps": 475, "total_steps": 25880, "loss": 0.6205, "lr": 0.0001831530139103555, "epoch": 0.3670788253477589, "percentage": 1.84, "elapsed_time": "0:01:19", "remaining_time": "1:10:48", "throughput": 2009.37, "total_tokens": 159616}
|
| 96 |
+
{"current_steps": 480, "total_steps": 25880, "loss": 0.9056, "lr": 0.00018508500772797525, "epoch": 0.37094281298299847, "percentage": 1.85, "elapsed_time": "0:01:20", "remaining_time": "1:10:47", "throughput": 2009.45, "total_tokens": 161280}
|
| 97 |
+
{"current_steps": 485, "total_steps": 25880, "loss": 0.7008, "lr": 0.00018701700154559507, "epoch": 0.374806800618238, "percentage": 1.87, "elapsed_time": "0:01:21", "remaining_time": "1:10:44", "throughput": 2009.18, "total_tokens": 162880}
|
| 98 |
+
{"current_steps": 490, "total_steps": 25880, "loss": 0.5929, "lr": 0.00018894899536321482, "epoch": 0.3786707882534776, "percentage": 1.89, "elapsed_time": "0:01:21", "remaining_time": "1:10:40", "throughput": 2007.44, "total_tokens": 164288}
|
| 99 |
+
{"current_steps": 495, "total_steps": 25880, "loss": 0.783, "lr": 0.00019088098918083462, "epoch": 0.38253477588871715, "percentage": 1.91, "elapsed_time": "0:01:22", "remaining_time": "1:10:36", "throughput": 2005.11, "total_tokens": 165632}
|
| 100 |
+
{"current_steps": 500, "total_steps": 25880, "loss": 0.8702, "lr": 0.0001928129829984544, "epoch": 0.38639876352395675, "percentage": 1.93, "elapsed_time": "0:01:23", "remaining_time": "1:10:34", "throughput": 2005.15, "total_tokens": 167264}
|
| 101 |
+
{"current_steps": 505, "total_steps": 25880, "loss": 1.4047, "lr": 0.00019474497681607419, "epoch": 0.3902627511591963, "percentage": 1.95, "elapsed_time": "0:01:24", "remaining_time": "1:10:35", "throughput": 2005.26, "total_tokens": 169024}
|
| 102 |
+
{"current_steps": 510, "total_steps": 25880, "loss": 0.7587, "lr": 0.00019667697063369396, "epoch": 0.3941267387944359, "percentage": 1.97, "elapsed_time": "0:01:25", "remaining_time": "1:10:33", "throughput": 2005.64, "total_tokens": 170688}
|
| 103 |
+
{"current_steps": 515, "total_steps": 25880, "loss": 0.8392, "lr": 0.00019860896445131375, "epoch": 0.3979907264296754, "percentage": 1.99, "elapsed_time": "0:01:25", "remaining_time": "1:10:32", "throughput": 2005.44, "total_tokens": 172352}
|
| 104 |
+
{"current_steps": 520, "total_steps": 25880, "loss": 0.8286, "lr": 0.00020054095826893352, "epoch": 0.401854714064915, "percentage": 2.01, "elapsed_time": "0:01:26", "remaining_time": "1:10:30", "throughput": 2004.85, "total_tokens": 173920}
|
| 105 |
+
{"current_steps": 525, "total_steps": 25880, "loss": 0.9881, "lr": 0.00020247295208655332, "epoch": 0.40571870170015456, "percentage": 2.03, "elapsed_time": "0:01:27", "remaining_time": "1:10:28", "throughput": 2004.96, "total_tokens": 175552}
|
| 106 |
+
{"current_steps": 530, "total_steps": 25880, "loss": 0.7107, "lr": 0.0002044049459041731, "epoch": 0.4095826893353941, "percentage": 2.05, "elapsed_time": "0:01:28", "remaining_time": "1:10:25", "throughput": 2004.35, "total_tokens": 177056}
|
| 107 |
+
{"current_steps": 535, "total_steps": 25880, "loss": 1.0233, "lr": 0.0002063369397217929, "epoch": 0.4134466769706337, "percentage": 2.07, "elapsed_time": "0:01:29", "remaining_time": "1:10:26", "throughput": 2005.46, "total_tokens": 178912}
|
| 108 |
+
{"current_steps": 540, "total_steps": 25880, "loss": 0.6322, "lr": 0.00020826893353941266, "epoch": 0.41731066460587324, "percentage": 2.09, "elapsed_time": "0:01:30", "remaining_time": "1:10:24", "throughput": 2004.91, "total_tokens": 180480}
|
| 109 |
+
{"current_steps": 545, "total_steps": 25880, "loss": 0.6568, "lr": 0.00021020092735703246, "epoch": 0.42117465224111283, "percentage": 2.11, "elapsed_time": "0:01:30", "remaining_time": "1:10:22", "throughput": 2004.96, "total_tokens": 182112}
|
| 110 |
+
{"current_steps": 550, "total_steps": 25880, "loss": 1.3266, "lr": 0.00021213292117465223, "epoch": 0.4250386398763524, "percentage": 2.13, "elapsed_time": "0:01:31", "remaining_time": "1:10:21", "throughput": 2005.07, "total_tokens": 183808}
|
| 111 |
+
{"current_steps": 555, "total_steps": 25880, "loss": 0.8833, "lr": 0.00021406491499227203, "epoch": 0.42890262751159197, "percentage": 2.14, "elapsed_time": "0:01:32", "remaining_time": "1:10:19", "throughput": 2004.22, "total_tokens": 185344}
|
| 112 |
+
{"current_steps": 560, "total_steps": 25880, "loss": 0.624, "lr": 0.0002159969088098918, "epoch": 0.4327666151468315, "percentage": 2.16, "elapsed_time": "0:01:33", "remaining_time": "1:10:20", "throughput": 2005.88, "total_tokens": 187232}
|
| 113 |
+
{"current_steps": 565, "total_steps": 25880, "loss": 0.6282, "lr": 0.00021792890262751157, "epoch": 0.4366306027820711, "percentage": 2.18, "elapsed_time": "0:01:34", "remaining_time": "1:10:18", "throughput": 2004.75, "total_tokens": 188736}
|
| 114 |
+
{"current_steps": 570, "total_steps": 25880, "loss": 0.5607, "lr": 0.00021986089644513137, "epoch": 0.44049459041731065, "percentage": 2.2, "elapsed_time": "0:01:34", "remaining_time": "1:10:16", "throughput": 2004.81, "total_tokens": 190368}
|
| 115 |
+
{"current_steps": 575, "total_steps": 25880, "loss": 0.6528, "lr": 0.00022179289026275114, "epoch": 0.44435857805255025, "percentage": 2.22, "elapsed_time": "0:01:35", "remaining_time": "1:10:15", "throughput": 2004.61, "total_tokens": 192032}
|
| 116 |
+
{"current_steps": 580, "total_steps": 25880, "loss": 0.7162, "lr": 0.00022372488408037094, "epoch": 0.4482225656877898, "percentage": 2.24, "elapsed_time": "0:01:36", "remaining_time": "1:10:15", "throughput": 2004.73, "total_tokens": 193728}
|
| 117 |
+
{"current_steps": 585, "total_steps": 25880, "loss": 0.7922, "lr": 0.0002256568778979907, "epoch": 0.4520865533230294, "percentage": 2.26, "elapsed_time": "0:01:37", "remaining_time": "1:10:17", "throughput": 2005.18, "total_tokens": 195584}
|
| 118 |
+
{"current_steps": 590, "total_steps": 25880, "loss": 1.141, "lr": 0.0002275888717156105, "epoch": 0.4559505409582689, "percentage": 2.28, "elapsed_time": "0:01:38", "remaining_time": "1:10:14", "throughput": 2004.65, "total_tokens": 197088}
|
| 119 |
+
{"current_steps": 595, "total_steps": 25880, "loss": 1.0742, "lr": 0.00022952086553323028, "epoch": 0.4598145285935085, "percentage": 2.3, "elapsed_time": "0:01:39", "remaining_time": "1:10:11", "throughput": 2004.32, "total_tokens": 198624}
|
| 120 |
+
{"current_steps": 600, "total_steps": 25880, "loss": 0.7939, "lr": 0.00023145285935085008, "epoch": 0.46367851622874806, "percentage": 2.32, "elapsed_time": "0:01:39", "remaining_time": "1:10:10", "throughput": 2005.0, "total_tokens": 200384}
|
| 121 |
+
{"current_steps": 605, "total_steps": 25880, "loss": 0.8594, "lr": 0.00023338485316846985, "epoch": 0.46754250386398766, "percentage": 2.34, "elapsed_time": "0:01:40", "remaining_time": "1:10:09", "throughput": 2005.36, "total_tokens": 202048}
|
| 122 |
+
{"current_steps": 610, "total_steps": 25880, "loss": 0.7498, "lr": 0.00023531684698608964, "epoch": 0.4714064914992272, "percentage": 2.36, "elapsed_time": "0:01:41", "remaining_time": "1:10:08", "throughput": 2004.61, "total_tokens": 203648}
|
| 123 |
+
{"current_steps": 615, "total_steps": 25880, "loss": 0.7602, "lr": 0.00023724884080370941, "epoch": 0.4752704791344668, "percentage": 2.38, "elapsed_time": "0:01:42", "remaining_time": "1:10:07", "throughput": 2004.43, "total_tokens": 205312}
|
| 124 |
+
{"current_steps": 620, "total_steps": 25880, "loss": 0.9076, "lr": 0.0002391808346213292, "epoch": 0.47913446676970634, "percentage": 2.4, "elapsed_time": "0:01:43", "remaining_time": "1:10:16", "throughput": 2001.05, "total_tokens": 207104}
|
| 125 |
+
{"current_steps": 625, "total_steps": 25880, "loss": 0.6358, "lr": 0.00024111282843894898, "epoch": 0.48299845440494593, "percentage": 2.41, "elapsed_time": "0:01:44", "remaining_time": "1:10:16", "throughput": 2001.42, "total_tokens": 208832}
|
| 126 |
+
{"current_steps": 630, "total_steps": 25880, "loss": 0.8636, "lr": 0.00024304482225656878, "epoch": 0.4868624420401855, "percentage": 2.43, "elapsed_time": "0:01:45", "remaining_time": "1:10:15", "throughput": 2001.83, "total_tokens": 210560}
|
| 127 |
+
{"current_steps": 635, "total_steps": 25880, "loss": 1.0252, "lr": 0.0002449768160741886, "epoch": 0.490726429675425, "percentage": 2.45, "elapsed_time": "0:01:45", "remaining_time": "1:10:12", "throughput": 2001.64, "total_tokens": 212096}
|
| 128 |
+
{"current_steps": 640, "total_steps": 25880, "loss": 0.8559, "lr": 0.00024690880989180835, "epoch": 0.4945904173106646, "percentage": 2.47, "elapsed_time": "0:01:46", "remaining_time": "1:10:10", "throughput": 2001.73, "total_tokens": 213728}
|
| 129 |
+
{"current_steps": 645, "total_steps": 25880, "loss": 0.559, "lr": 0.0002488408037094281, "epoch": 0.49845440494590415, "percentage": 2.49, "elapsed_time": "0:01:47", "remaining_time": "1:10:13", "throughput": 2004.22, "total_tokens": 215840}
|
| 130 |
+
{"current_steps": 650, "total_steps": 25880, "loss": 0.6065, "lr": 0.0002507727975270479, "epoch": 0.5023183925811437, "percentage": 2.51, "elapsed_time": "0:01:48", "remaining_time": "1:10:10", "throughput": 2003.23, "total_tokens": 217280}
|
| 131 |
+
{"current_steps": 655, "total_steps": 25880, "loss": 0.7811, "lr": 0.0002527047913446677, "epoch": 0.5061823802163833, "percentage": 2.53, "elapsed_time": "0:01:49", "remaining_time": "1:10:09", "throughput": 2003.61, "total_tokens": 219008}
|
| 132 |
+
{"current_steps": 660, "total_steps": 25880, "loss": 0.6922, "lr": 0.0002546367851622875, "epoch": 0.5100463678516228, "percentage": 2.55, "elapsed_time": "0:01:50", "remaining_time": "1:10:06", "throughput": 2002.65, "total_tokens": 220448}
|
| 133 |
+
{"current_steps": 665, "total_steps": 25880, "loss": 0.6251, "lr": 0.00025656877897990726, "epoch": 0.5139103554868625, "percentage": 2.57, "elapsed_time": "0:01:50", "remaining_time": "1:10:04", "throughput": 2002.51, "total_tokens": 222048}
|
| 134 |
+
{"current_steps": 670, "total_steps": 25880, "loss": 0.65, "lr": 0.00025850077279752703, "epoch": 0.517774343122102, "percentage": 2.59, "elapsed_time": "0:01:51", "remaining_time": "1:10:02", "throughput": 2002.12, "total_tokens": 223616}
|
| 135 |
+
{"current_steps": 675, "total_steps": 25880, "loss": 0.7307, "lr": 0.0002604327666151468, "epoch": 0.5216383307573416, "percentage": 2.61, "elapsed_time": "0:01:52", "remaining_time": "1:10:03", "throughput": 2003.03, "total_tokens": 225472}
|
| 136 |
+
{"current_steps": 680, "total_steps": 25880, "loss": 0.715, "lr": 0.0002623647604327666, "epoch": 0.5255023183925811, "percentage": 2.63, "elapsed_time": "0:01:53", "remaining_time": "1:10:02", "throughput": 2003.41, "total_tokens": 227200}
|
| 137 |
+
{"current_steps": 685, "total_steps": 25880, "loss": 0.7115, "lr": 0.0002642967542503864, "epoch": 0.5293663060278208, "percentage": 2.65, "elapsed_time": "0:01:54", "remaining_time": "1:09:59", "throughput": 2001.76, "total_tokens": 228544}
|
| 138 |
+
{"current_steps": 690, "total_steps": 25880, "loss": 0.5457, "lr": 0.00026622874806800617, "epoch": 0.5332302936630603, "percentage": 2.67, "elapsed_time": "0:01:54", "remaining_time": "1:09:57", "throughput": 2000.88, "total_tokens": 230048}
|
| 139 |
+
{"current_steps": 695, "total_steps": 25880, "loss": 1.0726, "lr": 0.00026816074188562594, "epoch": 0.5370942812982998, "percentage": 2.69, "elapsed_time": "0:01:55", "remaining_time": "1:09:56", "throughput": 2001.0, "total_tokens": 231744}
|
| 140 |
+
{"current_steps": 700, "total_steps": 25880, "loss": 0.6066, "lr": 0.00027009273570324576, "epoch": 0.5409582689335394, "percentage": 2.7, "elapsed_time": "0:01:56", "remaining_time": "1:09:57", "throughput": 2000.94, "total_tokens": 233472}
|
| 141 |
+
{"current_steps": 705, "total_steps": 25880, "loss": 0.5757, "lr": 0.00027202472952086553, "epoch": 0.544822256568779, "percentage": 2.72, "elapsed_time": "0:01:57", "remaining_time": "1:09:55", "throughput": 2001.11, "total_tokens": 235136}
|
| 142 |
+
{"current_steps": 710, "total_steps": 25880, "loss": 0.7589, "lr": 0.0002739567233384853, "epoch": 0.5486862442040186, "percentage": 2.74, "elapsed_time": "0:01:58", "remaining_time": "1:09:55", "throughput": 2001.97, "total_tokens": 236928}
|
| 143 |
+
{"current_steps": 715, "total_steps": 25880, "loss": 0.6419, "lr": 0.0002758887171561051, "epoch": 0.5525502318392581, "percentage": 2.76, "elapsed_time": "0:01:59", "remaining_time": "1:09:52", "throughput": 2002.3, "total_tokens": 238528}
|
| 144 |
+
{"current_steps": 720, "total_steps": 25880, "loss": 0.6745, "lr": 0.0002778207109737249, "epoch": 0.5564142194744977, "percentage": 2.78, "elapsed_time": "0:01:59", "remaining_time": "1:09:51", "throughput": 2002.38, "total_tokens": 240160}
|
| 145 |
+
{"current_steps": 725, "total_steps": 25880, "loss": 0.7336, "lr": 0.00027975270479134467, "epoch": 0.5602782071097373, "percentage": 2.8, "elapsed_time": "0:02:00", "remaining_time": "1:09:49", "throughput": 2003.84, "total_tokens": 241984}
|
| 146 |
+
{"current_steps": 730, "total_steps": 25880, "loss": 0.6876, "lr": 0.00028168469860896444, "epoch": 0.5641421947449768, "percentage": 2.82, "elapsed_time": "0:02:01", "remaining_time": "1:09:51", "throughput": 2006.06, "total_tokens": 244064}
|
| 147 |
+
{"current_steps": 735, "total_steps": 25880, "loss": 0.8033, "lr": 0.0002836166924265842, "epoch": 0.5680061823802164, "percentage": 2.84, "elapsed_time": "0:02:02", "remaining_time": "1:09:52", "throughput": 2007.54, "total_tokens": 246016}
|
| 148 |
+
{"current_steps": 740, "total_steps": 25880, "loss": 0.5904, "lr": 0.00028554868624420404, "epoch": 0.5718701700154559, "percentage": 2.86, "elapsed_time": "0:02:03", "remaining_time": "1:09:52", "throughput": 2009.41, "total_tokens": 247968}
|
| 149 |
+
{"current_steps": 745, "total_steps": 25880, "loss": 0.6715, "lr": 0.0002874806800618238, "epoch": 0.5757341576506955, "percentage": 2.88, "elapsed_time": "0:02:04", "remaining_time": "1:09:50", "throughput": 2009.89, "total_tokens": 249664}
|
| 150 |
+
{"current_steps": 750, "total_steps": 25880, "loss": 0.5648, "lr": 0.0002894126738794436, "epoch": 0.5795981452859351, "percentage": 2.9, "elapsed_time": "0:02:05", "remaining_time": "1:09:50", "throughput": 2009.95, "total_tokens": 251360}
|
| 151 |
+
{"current_steps": 755, "total_steps": 25880, "loss": 0.6401, "lr": 0.00029134466769706335, "epoch": 0.5834621329211747, "percentage": 2.92, "elapsed_time": "0:02:05", "remaining_time": "1:09:48", "throughput": 2009.54, "total_tokens": 252928}
|
| 152 |
+
{"current_steps": 760, "total_steps": 25880, "loss": 0.785, "lr": 0.0002932766615146832, "epoch": 0.5873261205564142, "percentage": 2.94, "elapsed_time": "0:02:06", "remaining_time": "1:09:47", "throughput": 2008.96, "total_tokens": 254528}
|
| 153 |
+
{"current_steps": 765, "total_steps": 25880, "loss": 0.579, "lr": 0.00029520865533230295, "epoch": 0.5911901081916537, "percentage": 2.96, "elapsed_time": "0:02:07", "remaining_time": "1:09:46", "throughput": 2009.24, "total_tokens": 256192}
|
| 154 |
+
{"current_steps": 770, "total_steps": 25880, "loss": 0.8475, "lr": 0.0002971406491499227, "epoch": 0.5950540958268934, "percentage": 2.98, "elapsed_time": "0:02:08", "remaining_time": "1:09:48", "throughput": 2010.7, "total_tokens": 258240}
|
| 155 |
+
{"current_steps": 775, "total_steps": 25880, "loss": 0.5753, "lr": 0.0002990726429675425, "epoch": 0.5989180834621329, "percentage": 2.99, "elapsed_time": "0:02:09", "remaining_time": "1:09:48", "throughput": 2011.16, "total_tokens": 260064}
|
| 156 |
+
{"current_steps": 780, "total_steps": 25880, "loss": 0.9831, "lr": 0.00030100463678516226, "epoch": 0.6027820710973725, "percentage": 3.01, "elapsed_time": "0:02:10", "remaining_time": "1:09:49", "throughput": 2012.09, "total_tokens": 261952}
|
| 157 |
+
{"current_steps": 785, "total_steps": 25880, "loss": 1.0871, "lr": 0.0003029366306027821, "epoch": 0.606646058732612, "percentage": 3.03, "elapsed_time": "0:02:11", "remaining_time": "1:09:49", "throughput": 2012.63, "total_tokens": 263744}
|
| 158 |
+
{"current_steps": 790, "total_steps": 25880, "loss": 0.7419, "lr": 0.00030486862442040185, "epoch": 0.6105100463678517, "percentage": 3.05, "elapsed_time": "0:02:11", "remaining_time": "1:09:47", "throughput": 2012.02, "total_tokens": 265280}
|
| 159 |
+
{"current_steps": 795, "total_steps": 25880, "loss": 0.9272, "lr": 0.0003068006182380216, "epoch": 0.6143740340030912, "percentage": 3.07, "elapsed_time": "0:02:12", "remaining_time": "1:09:45", "throughput": 2012.24, "total_tokens": 266944}
|
| 160 |
+
{"current_steps": 800, "total_steps": 25880, "loss": 0.7439, "lr": 0.0003087326120556414, "epoch": 0.6182380216383307, "percentage": 3.09, "elapsed_time": "0:02:13", "remaining_time": "1:09:44", "throughput": 2012.05, "total_tokens": 268544}
|
| 161 |
+
{"current_steps": 805, "total_steps": 25880, "loss": 0.5123, "lr": 0.0003106646058732612, "epoch": 0.6221020092735703, "percentage": 3.11, "elapsed_time": "0:02:14", "remaining_time": "1:09:43", "throughput": 2012.92, "total_tokens": 270368}
|
| 162 |
+
{"current_steps": 810, "total_steps": 25880, "loss": 1.0628, "lr": 0.000312596599690881, "epoch": 0.6259659969088099, "percentage": 3.13, "elapsed_time": "0:02:15", "remaining_time": "1:09:43", "throughput": 2012.76, "total_tokens": 272032}
|
| 163 |
+
{"current_steps": 815, "total_steps": 25880, "loss": 0.6237, "lr": 0.00031452859350850076, "epoch": 0.6298299845440495, "percentage": 3.15, "elapsed_time": "0:02:15", "remaining_time": "1:09:42", "throughput": 2013.64, "total_tokens": 273824}
|
| 164 |
+
{"current_steps": 820, "total_steps": 25880, "loss": 0.9402, "lr": 0.00031646058732612053, "epoch": 0.633693972179289, "percentage": 3.17, "elapsed_time": "0:02:16", "remaining_time": "1:09:41", "throughput": 2014.26, "total_tokens": 275616}
|
| 165 |
+
{"current_steps": 825, "total_steps": 25880, "loss": 0.6184, "lr": 0.00031839258114374036, "epoch": 0.6375579598145286, "percentage": 3.19, "elapsed_time": "0:02:17", "remaining_time": "1:09:40", "throughput": 2014.09, "total_tokens": 277248}
|
| 166 |
+
{"current_steps": 830, "total_steps": 25880, "loss": 0.5459, "lr": 0.00032032457496136013, "epoch": 0.6414219474497682, "percentage": 3.21, "elapsed_time": "0:02:18", "remaining_time": "1:09:38", "throughput": 2013.7, "total_tokens": 278816}
|
| 167 |
+
{"current_steps": 835, "total_steps": 25880, "loss": 0.59, "lr": 0.0003222565687789799, "epoch": 0.6452859350850078, "percentage": 3.23, "elapsed_time": "0:02:19", "remaining_time": "1:09:36", "throughput": 2013.24, "total_tokens": 280320}
|
| 168 |
+
{"current_steps": 840, "total_steps": 25880, "loss": 0.721, "lr": 0.00032418856259659967, "epoch": 0.6491499227202473, "percentage": 3.25, "elapsed_time": "0:02:20", "remaining_time": "1:09:33", "throughput": 2012.84, "total_tokens": 281824}
|
| 169 |
+
{"current_steps": 845, "total_steps": 25880, "loss": 0.632, "lr": 0.0003261205564142195, "epoch": 0.6530139103554868, "percentage": 3.27, "elapsed_time": "0:02:20", "remaining_time": "1:09:32", "throughput": 2012.83, "total_tokens": 283456}
|
| 170 |
+
{"current_steps": 850, "total_steps": 25880, "loss": 0.6296, "lr": 0.00032805255023183927, "epoch": 0.6568778979907264, "percentage": 3.28, "elapsed_time": "0:02:21", "remaining_time": "1:09:33", "throughput": 2013.7, "total_tokens": 285408}
|
| 171 |
+
{"current_steps": 855, "total_steps": 25880, "loss": 0.5817, "lr": 0.00032998454404945904, "epoch": 0.660741885625966, "percentage": 3.3, "elapsed_time": "0:02:22", "remaining_time": "1:09:32", "throughput": 2013.16, "total_tokens": 286976}
|
| 172 |
+
{"current_steps": 860, "total_steps": 25880, "loss": 0.55, "lr": 0.0003319165378670788, "epoch": 0.6646058732612056, "percentage": 3.32, "elapsed_time": "0:02:23", "remaining_time": "1:09:29", "throughput": 2012.96, "total_tokens": 288512}
|
| 173 |
+
{"current_steps": 865, "total_steps": 25880, "loss": 0.5713, "lr": 0.00033384853168469863, "epoch": 0.6684698608964451, "percentage": 3.34, "elapsed_time": "0:02:24", "remaining_time": "1:09:30", "throughput": 2013.59, "total_tokens": 290368}
|
| 174 |
+
{"current_steps": 870, "total_steps": 25880, "loss": 0.865, "lr": 0.0003357805255023184, "epoch": 0.6723338485316847, "percentage": 3.36, "elapsed_time": "0:02:25", "remaining_time": "1:09:41", "throughput": 2009.29, "total_tokens": 292288}
|
| 175 |
+
{"current_steps": 875, "total_steps": 25880, "loss": 0.6506, "lr": 0.0003377125193199382, "epoch": 0.6761978361669243, "percentage": 3.38, "elapsed_time": "0:02:26", "remaining_time": "1:09:42", "throughput": 2009.99, "total_tokens": 294176}
|
| 176 |
+
{"current_steps": 880, "total_steps": 25880, "loss": 0.6484, "lr": 0.00033964451313755795, "epoch": 0.6800618238021638, "percentage": 3.4, "elapsed_time": "0:02:27", "remaining_time": "1:09:41", "throughput": 2010.41, "total_tokens": 295936}
|
| 177 |
+
{"current_steps": 885, "total_steps": 25880, "loss": 0.6994, "lr": 0.0003415765069551777, "epoch": 0.6839258114374034, "percentage": 3.42, "elapsed_time": "0:02:28", "remaining_time": "1:09:40", "throughput": 2010.41, "total_tokens": 297568}
|
| 178 |
+
{"current_steps": 890, "total_steps": 25880, "loss": 0.6498, "lr": 0.00034350850077279754, "epoch": 0.6877897990726429, "percentage": 3.44, "elapsed_time": "0:02:28", "remaining_time": "1:09:38", "throughput": 2010.05, "total_tokens": 299136}
|
| 179 |
+
{"current_steps": 895, "total_steps": 25880, "loss": 0.6284, "lr": 0.0003454404945904173, "epoch": 0.6916537867078826, "percentage": 3.46, "elapsed_time": "0:02:29", "remaining_time": "1:09:39", "throughput": 2010.83, "total_tokens": 301024}
|
| 180 |
+
{"current_steps": 900, "total_steps": 25880, "loss": 0.7848, "lr": 0.0003473724884080371, "epoch": 0.6955177743431221, "percentage": 3.48, "elapsed_time": "0:02:30", "remaining_time": "1:09:38", "throughput": 2011.58, "total_tokens": 302848}
|
| 181 |
+
{"current_steps": 905, "total_steps": 25880, "loss": 0.6568, "lr": 0.00034930448222565686, "epoch": 0.6993817619783617, "percentage": 3.5, "elapsed_time": "0:02:31", "remaining_time": "1:09:37", "throughput": 2011.78, "total_tokens": 304512}
|
| 182 |
+
{"current_steps": 910, "total_steps": 25880, "loss": 0.6552, "lr": 0.0003512364760432767, "epoch": 0.7032457496136012, "percentage": 3.52, "elapsed_time": "0:02:32", "remaining_time": "1:09:35", "throughput": 2011.03, "total_tokens": 306016}
|
| 183 |
+
{"current_steps": 915, "total_steps": 25880, "loss": 0.7681, "lr": 0.00035316846986089645, "epoch": 0.7071097372488409, "percentage": 3.54, "elapsed_time": "0:02:32", "remaining_time": "1:09:32", "throughput": 2010.27, "total_tokens": 307456}
|
| 184 |
+
{"current_steps": 920, "total_steps": 25880, "loss": 0.6274, "lr": 0.0003551004636785162, "epoch": 0.7109737248840804, "percentage": 3.55, "elapsed_time": "0:02:33", "remaining_time": "1:09:33", "throughput": 2010.86, "total_tokens": 309312}
|
| 185 |
+
{"current_steps": 925, "total_steps": 25880, "loss": 0.5667, "lr": 0.000357032457496136, "epoch": 0.7148377125193199, "percentage": 3.57, "elapsed_time": "0:02:34", "remaining_time": "1:09:32", "throughput": 2010.73, "total_tokens": 310976}
|
| 186 |
+
{"current_steps": 930, "total_steps": 25880, "loss": 0.4947, "lr": 0.0003589644513137558, "epoch": 0.7187017001545595, "percentage": 3.59, "elapsed_time": "0:02:35", "remaining_time": "1:09:31", "throughput": 2010.95, "total_tokens": 312704}
|
| 187 |
+
{"current_steps": 935, "total_steps": 25880, "loss": 0.6226, "lr": 0.0003608964451313756, "epoch": 0.7225656877897991, "percentage": 3.61, "elapsed_time": "0:02:36", "remaining_time": "1:09:31", "throughput": 2011.17, "total_tokens": 314496}
|
| 188 |
+
{"current_steps": 940, "total_steps": 25880, "loss": 0.6378, "lr": 0.00036282843894899536, "epoch": 0.7264296754250387, "percentage": 3.63, "elapsed_time": "0:02:37", "remaining_time": "1:09:31", "throughput": 2011.19, "total_tokens": 316192}
|
| 189 |
+
{"current_steps": 945, "total_steps": 25880, "loss": 0.8018, "lr": 0.00036476043276661513, "epoch": 0.7302936630602782, "percentage": 3.65, "elapsed_time": "0:02:37", "remaining_time": "1:09:28", "throughput": 2010.29, "total_tokens": 317600}
|
| 190 |
+
{"current_steps": 950, "total_steps": 25880, "loss": 0.6515, "lr": 0.00036669242658423496, "epoch": 0.7341576506955177, "percentage": 3.67, "elapsed_time": "0:02:38", "remaining_time": "1:09:26", "throughput": 2010.09, "total_tokens": 319136}
|
| 191 |
+
{"current_steps": 955, "total_steps": 25880, "loss": 0.8588, "lr": 0.0003686244204018547, "epoch": 0.7380216383307573, "percentage": 3.69, "elapsed_time": "0:02:39", "remaining_time": "1:09:25", "throughput": 2010.48, "total_tokens": 320896}
|
| 192 |
+
{"current_steps": 960, "total_steps": 25880, "loss": 0.6086, "lr": 0.0003705564142194745, "epoch": 0.7418856259659969, "percentage": 3.71, "elapsed_time": "0:02:40", "remaining_time": "1:09:25", "throughput": 2011.2, "total_tokens": 322720}
|
| 193 |
+
{"current_steps": 965, "total_steps": 25880, "loss": 0.719, "lr": 0.00037248840803709427, "epoch": 0.7457496136012365, "percentage": 3.73, "elapsed_time": "0:02:41", "remaining_time": "1:09:24", "throughput": 2012.26, "total_tokens": 324608}
|
| 194 |
+
{"current_steps": 970, "total_steps": 25880, "loss": 0.5609, "lr": 0.0003744204018547141, "epoch": 0.749613601236476, "percentage": 3.75, "elapsed_time": "0:02:42", "remaining_time": "1:09:23", "throughput": 2011.75, "total_tokens": 326144}
|
| 195 |
+
{"current_steps": 975, "total_steps": 25880, "loss": 0.6545, "lr": 0.00037635239567233386, "epoch": 0.7534775888717156, "percentage": 3.77, "elapsed_time": "0:02:43", "remaining_time": "1:09:23", "throughput": 2012.66, "total_tokens": 328064}
|
| 196 |
+
{"current_steps": 980, "total_steps": 25880, "loss": 0.6244, "lr": 0.00037828438948995363, "epoch": 0.7573415765069552, "percentage": 3.79, "elapsed_time": "0:02:43", "remaining_time": "1:09:23", "throughput": 2012.72, "total_tokens": 329824}
|
| 197 |
+
{"current_steps": 985, "total_steps": 25880, "loss": 0.5253, "lr": 0.0003802163833075734, "epoch": 0.7612055641421948, "percentage": 3.81, "elapsed_time": "0:02:44", "remaining_time": "1:09:22", "throughput": 2012.54, "total_tokens": 331424}
|
| 198 |
+
{"current_steps": 990, "total_steps": 25880, "loss": 0.589, "lr": 0.0003821483771251932, "epoch": 0.7650695517774343, "percentage": 3.83, "elapsed_time": "0:02:45", "remaining_time": "1:09:20", "throughput": 2012.19, "total_tokens": 332992}
|
| 199 |
+
{"current_steps": 995, "total_steps": 25880, "loss": 0.6413, "lr": 0.000384080370942813, "epoch": 0.7689335394126738, "percentage": 3.84, "elapsed_time": "0:02:46", "remaining_time": "1:09:18", "throughput": 2011.68, "total_tokens": 334528}
|
| 200 |
+
{"current_steps": 1000, "total_steps": 25880, "loss": 0.7308, "lr": 0.00038601236476043277, "epoch": 0.7727975270479135, "percentage": 3.86, "elapsed_time": "0:02:47", "remaining_time": "1:09:17", "throughput": 2011.68, "total_tokens": 336160}
|
| 201 |
+
{"current_steps": 1005, "total_steps": 25880, "loss": 0.6021, "lr": 0.00038794435857805254, "epoch": 0.776661514683153, "percentage": 3.88, "elapsed_time": "0:02:47", "remaining_time": "1:09:15", "throughput": 2010.83, "total_tokens": 337568}
|
| 202 |
+
{"current_steps": 1010, "total_steps": 25880, "loss": 0.6099, "lr": 0.0003898763523956723, "epoch": 0.7805255023183926, "percentage": 3.9, "elapsed_time": "0:02:48", "remaining_time": "1:09:15", "throughput": 2010.9, "total_tokens": 339328}
|
| 203 |
+
{"current_steps": 1015, "total_steps": 25880, "loss": 0.5976, "lr": 0.00039180834621329214, "epoch": 0.7843894899536321, "percentage": 3.92, "elapsed_time": "0:02:49", "remaining_time": "1:09:13", "throughput": 2011.4, "total_tokens": 341056}
|
| 204 |
+
{"current_steps": 1020, "total_steps": 25880, "loss": 0.7878, "lr": 0.0003937403400309119, "epoch": 0.7882534775888718, "percentage": 3.94, "elapsed_time": "0:02:50", "remaining_time": "1:09:13", "throughput": 2011.6, "total_tokens": 342784}
|
| 205 |
+
{"current_steps": 1025, "total_steps": 25880, "loss": 0.7116, "lr": 0.0003956723338485317, "epoch": 0.7921174652241113, "percentage": 3.96, "elapsed_time": "0:02:51", "remaining_time": "1:09:11", "throughput": 2011.78, "total_tokens": 344448}
|
| 206 |
+
{"current_steps": 1030, "total_steps": 25880, "loss": 0.5051, "lr": 0.00039760432766615145, "epoch": 0.7959814528593508, "percentage": 3.98, "elapsed_time": "0:02:52", "remaining_time": "1:09:10", "throughput": 2011.57, "total_tokens": 346048}
|
| 207 |
+
{"current_steps": 1035, "total_steps": 25880, "loss": 0.7918, "lr": 0.0003995363214837713, "epoch": 0.7998454404945904, "percentage": 4.0, "elapsed_time": "0:02:52", "remaining_time": "1:09:09", "throughput": 2011.75, "total_tokens": 347776}
|
| 208 |
+
{"current_steps": 1040, "total_steps": 25880, "loss": 0.5818, "lr": 0.00040146831530139105, "epoch": 0.80370942812983, "percentage": 4.02, "elapsed_time": "0:02:53", "remaining_time": "1:09:08", "throughput": 2011.91, "total_tokens": 349440}
|
| 209 |
+
{"current_steps": 1045, "total_steps": 25880, "loss": 0.5718, "lr": 0.0004034003091190108, "epoch": 0.8075734157650696, "percentage": 4.04, "elapsed_time": "0:02:54", "remaining_time": "1:09:07", "throughput": 2012.56, "total_tokens": 351264}
|
| 210 |
+
{"current_steps": 1050, "total_steps": 25880, "loss": 0.88, "lr": 0.0004053323029366306, "epoch": 0.8114374034003091, "percentage": 4.06, "elapsed_time": "0:02:55", "remaining_time": "1:09:06", "throughput": 2012.07, "total_tokens": 352800}
|
| 211 |
+
{"current_steps": 1055, "total_steps": 25880, "loss": 0.5376, "lr": 0.0004072642967542504, "epoch": 0.8153013910355487, "percentage": 4.08, "elapsed_time": "0:02:56", "remaining_time": "1:09:04", "throughput": 2011.1, "total_tokens": 354176}
|
| 212 |
+
{"current_steps": 1060, "total_steps": 25880, "loss": 0.5657, "lr": 0.0004091962905718702, "epoch": 0.8191653786707882, "percentage": 4.1, "elapsed_time": "0:02:56", "remaining_time": "1:09:03", "throughput": 2010.83, "total_tokens": 355872}
|
| 213 |
+
{"current_steps": 1065, "total_steps": 25880, "loss": 0.4973, "lr": 0.00041112828438948996, "epoch": 0.8230293663060279, "percentage": 4.12, "elapsed_time": "0:02:57", "remaining_time": "1:09:01", "throughput": 2009.88, "total_tokens": 357248}
|
| 214 |
+
{"current_steps": 1070, "total_steps": 25880, "loss": 0.5324, "lr": 0.0004130602782071097, "epoch": 0.8268933539412674, "percentage": 4.13, "elapsed_time": "0:02:58", "remaining_time": "1:09:00", "throughput": 2010.19, "total_tokens": 358944}
|
| 215 |
+
{"current_steps": 1075, "total_steps": 25880, "loss": 1.2081, "lr": 0.00041499227202472955, "epoch": 0.8307573415765069, "percentage": 4.15, "elapsed_time": "0:02:59", "remaining_time": "1:08:58", "throughput": 2009.75, "total_tokens": 360480}
|
| 216 |
+
{"current_steps": 1080, "total_steps": 25880, "loss": 0.8546, "lr": 0.0004169242658423493, "epoch": 0.8346213292117465, "percentage": 4.17, "elapsed_time": "0:03:00", "remaining_time": "1:08:57", "throughput": 2010.07, "total_tokens": 362176}
|
| 217 |
+
{"current_steps": 1085, "total_steps": 25880, "loss": 0.5484, "lr": 0.0004188562596599691, "epoch": 0.8384853168469861, "percentage": 4.19, "elapsed_time": "0:03:00", "remaining_time": "1:08:56", "throughput": 2009.91, "total_tokens": 363776}
|
| 218 |
+
{"current_steps": 1090, "total_steps": 25880, "loss": 1.0906, "lr": 0.00042078825347758886, "epoch": 0.8423493044822257, "percentage": 4.21, "elapsed_time": "0:03:01", "remaining_time": "1:08:54", "throughput": 2010.05, "total_tokens": 365376}
|
| 219 |
+
{"current_steps": 1095, "total_steps": 25880, "loss": 0.6446, "lr": 0.00042272024729520863, "epoch": 0.8462132921174652, "percentage": 4.23, "elapsed_time": "0:03:02", "remaining_time": "1:08:52", "throughput": 2009.44, "total_tokens": 366880}
|
| 220 |
+
{"current_steps": 1100, "total_steps": 25880, "loss": 0.6651, "lr": 0.00042465224111282846, "epoch": 0.8500772797527048, "percentage": 4.25, "elapsed_time": "0:03:03", "remaining_time": "1:08:53", "throughput": 2009.82, "total_tokens": 368768}
|
| 221 |
+
{"current_steps": 1105, "total_steps": 25880, "loss": 0.5539, "lr": 0.00042658423493044823, "epoch": 0.8539412673879444, "percentage": 4.27, "elapsed_time": "0:03:04", "remaining_time": "1:08:52", "throughput": 2010.32, "total_tokens": 370560}
|
| 222 |
+
{"current_steps": 1110, "total_steps": 25880, "loss": 0.5595, "lr": 0.000428516228748068, "epoch": 0.8578052550231839, "percentage": 4.29, "elapsed_time": "0:03:05", "remaining_time": "1:08:52", "throughput": 2010.48, "total_tokens": 372288}
|
| 223 |
+
{"current_steps": 1115, "total_steps": 25880, "loss": 0.6353, "lr": 0.00043044822256568777, "epoch": 0.8616692426584235, "percentage": 4.31, "elapsed_time": "0:03:05", "remaining_time": "1:08:50", "throughput": 2010.16, "total_tokens": 373792}
|
| 224 |
+
{"current_steps": 1120, "total_steps": 25880, "loss": 0.8796, "lr": 0.0004323802163833076, "epoch": 0.865533230293663, "percentage": 4.33, "elapsed_time": "0:03:06", "remaining_time": "1:08:49", "throughput": 2011.21, "total_tokens": 375712}
|
| 225 |
+
{"current_steps": 1125, "total_steps": 25880, "loss": 0.7909, "lr": 0.00043431221020092737, "epoch": 0.8693972179289027, "percentage": 4.35, "elapsed_time": "0:03:07", "remaining_time": "1:08:49", "throughput": 2011.24, "total_tokens": 377408}
|
| 226 |
+
{"current_steps": 1130, "total_steps": 25880, "loss": 0.9569, "lr": 0.00043624420401854714, "epoch": 0.8732612055641422, "percentage": 4.37, "elapsed_time": "0:03:08", "remaining_time": "1:08:49", "throughput": 2011.75, "total_tokens": 379328}
|
| 227 |
+
{"current_steps": 1135, "total_steps": 25880, "loss": 0.8012, "lr": 0.0004381761978361669, "epoch": 0.8771251931993818, "percentage": 4.39, "elapsed_time": "0:03:09", "remaining_time": "1:08:48", "throughput": 2011.29, "total_tokens": 380864}
|
| 228 |
+
{"current_steps": 1140, "total_steps": 25880, "loss": 0.8789, "lr": 0.00044010819165378673, "epoch": 0.8809891808346213, "percentage": 4.4, "elapsed_time": "0:03:10", "remaining_time": "1:08:48", "throughput": 2011.85, "total_tokens": 382752}
|
| 229 |
+
{"current_steps": 1145, "total_steps": 25880, "loss": 0.7288, "lr": 0.0004420401854714065, "epoch": 0.884853168469861, "percentage": 4.42, "elapsed_time": "0:03:11", "remaining_time": "1:08:46", "throughput": 2011.81, "total_tokens": 384320}
|
| 230 |
+
{"current_steps": 1150, "total_steps": 25880, "loss": 0.5117, "lr": 0.0004439721792890263, "epoch": 0.8887171561051005, "percentage": 4.44, "elapsed_time": "0:03:11", "remaining_time": "1:08:46", "throughput": 2011.71, "total_tokens": 385984}
|
| 231 |
+
{"current_steps": 1155, "total_steps": 25880, "loss": 0.6013, "lr": 0.00044590417310664605, "epoch": 0.89258114374034, "percentage": 4.46, "elapsed_time": "0:03:12", "remaining_time": "1:08:43", "throughput": 2011.11, "total_tokens": 387424}
|
| 232 |
+
{"current_steps": 1160, "total_steps": 25880, "loss": 0.5985, "lr": 0.00044783616692426587, "epoch": 0.8964451313755796, "percentage": 4.48, "elapsed_time": "0:03:13", "remaining_time": "1:08:43", "throughput": 2011.56, "total_tokens": 389216}
|
| 233 |
+
{"current_steps": 1165, "total_steps": 25880, "loss": 0.5921, "lr": 0.00044976816074188564, "epoch": 0.9003091190108191, "percentage": 4.5, "elapsed_time": "0:03:14", "remaining_time": "1:08:42", "throughput": 2011.47, "total_tokens": 390912}
|
| 234 |
+
{"current_steps": 1170, "total_steps": 25880, "loss": 0.6275, "lr": 0.0004517001545595054, "epoch": 0.9041731066460588, "percentage": 4.52, "elapsed_time": "0:03:15", "remaining_time": "1:08:40", "throughput": 2011.03, "total_tokens": 392384}
|
| 235 |
+
{"current_steps": 1175, "total_steps": 25880, "loss": 0.7864, "lr": 0.0004536321483771252, "epoch": 0.9080370942812983, "percentage": 4.54, "elapsed_time": "0:03:15", "remaining_time": "1:08:39", "throughput": 2011.04, "total_tokens": 394016}
|
| 236 |
+
{"current_steps": 1180, "total_steps": 25880, "loss": 0.5851, "lr": 0.000455564142194745, "epoch": 0.9119010819165378, "percentage": 4.56, "elapsed_time": "0:03:16", "remaining_time": "1:08:38", "throughput": 2011.47, "total_tokens": 395808}
|
| 237 |
+
{"current_steps": 1185, "total_steps": 25880, "loss": 0.5756, "lr": 0.0004574961360123648, "epoch": 0.9157650695517774, "percentage": 4.58, "elapsed_time": "0:03:17", "remaining_time": "1:08:38", "throughput": 2011.35, "total_tokens": 397472}
|
| 238 |
+
{"current_steps": 1190, "total_steps": 25880, "loss": 0.5097, "lr": 0.00045942812982998455, "epoch": 0.919629057187017, "percentage": 4.6, "elapsed_time": "0:03:18", "remaining_time": "1:08:37", "throughput": 2011.36, "total_tokens": 399168}
|
| 239 |
+
{"current_steps": 1195, "total_steps": 25880, "loss": 0.6278, "lr": 0.0004613601236476043, "epoch": 0.9234930448222566, "percentage": 4.62, "elapsed_time": "0:03:19", "remaining_time": "1:08:37", "throughput": 2011.4, "total_tokens": 400928}
|
| 240 |
+
{"current_steps": 1200, "total_steps": 25880, "loss": 0.7935, "lr": 0.0004632921174652241, "epoch": 0.9273570324574961, "percentage": 4.64, "elapsed_time": "0:03:20", "remaining_time": "1:08:37", "throughput": 2012.25, "total_tokens": 402816}
|
| 241 |
+
{"current_steps": 1205, "total_steps": 25880, "loss": 0.5923, "lr": 0.0004652241112828439, "epoch": 0.9312210200927357, "percentage": 4.66, "elapsed_time": "0:03:21", "remaining_time": "1:08:36", "throughput": 2012.7, "total_tokens": 404608}
|
| 242 |
+
{"current_steps": 1210, "total_steps": 25880, "loss": 0.5173, "lr": 0.0004671561051004637, "epoch": 0.9350850077279753, "percentage": 4.68, "elapsed_time": "0:03:21", "remaining_time": "1:08:35", "throughput": 2012.45, "total_tokens": 406240}
|
| 243 |
+
{"current_steps": 1215, "total_steps": 25880, "loss": 0.7029, "lr": 0.00046908809891808346, "epoch": 0.9389489953632149, "percentage": 4.69, "elapsed_time": "0:03:22", "remaining_time": "1:08:34", "throughput": 2012.04, "total_tokens": 407776}
|
| 244 |
+
{"current_steps": 1220, "total_steps": 25880, "loss": 0.6173, "lr": 0.00047102009273570323, "epoch": 0.9428129829984544, "percentage": 4.71, "elapsed_time": "0:03:23", "remaining_time": "1:08:33", "throughput": 2012.61, "total_tokens": 409600}
|
| 245 |
+
{"current_steps": 1225, "total_steps": 25880, "loss": 0.8142, "lr": 0.00047295208655332306, "epoch": 0.9466769706336939, "percentage": 4.73, "elapsed_time": "0:03:24", "remaining_time": "1:08:31", "throughput": 2012.74, "total_tokens": 411200}
|
| 246 |
+
{"current_steps": 1230, "total_steps": 25880, "loss": 0.4915, "lr": 0.0004748840803709428, "epoch": 0.9505409582689336, "percentage": 4.75, "elapsed_time": "0:03:25", "remaining_time": "1:08:32", "throughput": 2012.93, "total_tokens": 413024}
|
| 247 |
+
{"current_steps": 1235, "total_steps": 25880, "loss": 0.7434, "lr": 0.0004768160741885626, "epoch": 0.9544049459041731, "percentage": 4.77, "elapsed_time": "0:03:26", "remaining_time": "1:08:31", "throughput": 2013.09, "total_tokens": 414752}
|
| 248 |
+
{"current_steps": 1240, "total_steps": 25880, "loss": 0.6039, "lr": 0.00047874806800618237, "epoch": 0.9582689335394127, "percentage": 4.79, "elapsed_time": "0:03:26", "remaining_time": "1:08:29", "throughput": 2012.0, "total_tokens": 416064}
|
| 249 |
+
{"current_steps": 1245, "total_steps": 25880, "loss": 0.5613, "lr": 0.0004806800618238022, "epoch": 0.9621329211746522, "percentage": 4.81, "elapsed_time": "0:03:27", "remaining_time": "1:08:29", "throughput": 2013.11, "total_tokens": 418144}
|
| 250 |
+
{"current_steps": 1250, "total_steps": 25880, "loss": 0.7158, "lr": 0.00048261205564142196, "epoch": 0.9659969088098919, "percentage": 4.83, "elapsed_time": "0:03:28", "remaining_time": "1:08:29", "throughput": 2013.13, "total_tokens": 419840}
|
| 251 |
+
{"current_steps": 1255, "total_steps": 25880, "loss": 0.5848, "lr": 0.00048454404945904174, "epoch": 0.9698608964451314, "percentage": 4.85, "elapsed_time": "0:03:29", "remaining_time": "1:08:29", "throughput": 2013.17, "total_tokens": 421600}
|
| 252 |
+
{"current_steps": 1260, "total_steps": 25880, "loss": 0.5809, "lr": 0.0004864760432766615, "epoch": 0.973724884080371, "percentage": 4.87, "elapsed_time": "0:03:30", "remaining_time": "1:08:27", "throughput": 2013.02, "total_tokens": 423136}
|
| 253 |
+
{"current_steps": 1265, "total_steps": 25880, "loss": 0.6045, "lr": 0.0004884080370942814, "epoch": 0.9775888717156105, "percentage": 4.89, "elapsed_time": "0:03:31", "remaining_time": "1:08:27", "throughput": 2013.3, "total_tokens": 424960}
|
| 254 |
+
{"current_steps": 1270, "total_steps": 25880, "loss": 0.5388, "lr": 0.0004903400309119011, "epoch": 0.98145285935085, "percentage": 4.91, "elapsed_time": "0:03:31", "remaining_time": "1:08:25", "throughput": 2012.63, "total_tokens": 426432}
|
| 255 |
+
{"current_steps": 1275, "total_steps": 25880, "loss": 0.5762, "lr": 0.0004922720247295209, "epoch": 0.9853168469860897, "percentage": 4.93, "elapsed_time": "0:03:32", "remaining_time": "1:08:26", "throughput": 2013.85, "total_tokens": 428512}
|
| 256 |
+
{"current_steps": 1280, "total_steps": 25880, "loss": 0.7917, "lr": 0.0004942040185471406, "epoch": 0.9891808346213292, "percentage": 4.95, "elapsed_time": "0:03:33", "remaining_time": "1:08:26", "throughput": 2014.25, "total_tokens": 430368}
|
| 257 |
+
{"current_steps": 1285, "total_steps": 25880, "loss": 0.6463, "lr": 0.0004961360123647605, "epoch": 0.9930448222565688, "percentage": 4.97, "elapsed_time": "0:03:34", "remaining_time": "1:08:24", "throughput": 2014.24, "total_tokens": 431936}
|
| 258 |
+
{"current_steps": 1290, "total_steps": 25880, "loss": 0.7815, "lr": 0.0004980680061823803, "epoch": 0.9969088098918083, "percentage": 4.98, "elapsed_time": "0:03:35", "remaining_time": "1:08:23", "throughput": 2013.7, "total_tokens": 433440}
|
| 259 |
+
{"current_steps": 1294, "total_steps": 25880, "eval_loss": 0.6249460577964783, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:03:46", "remaining_time": "1:11:45", "throughput": 1918.03, "total_tokens": 434624}
|
| 260 |
+
{"current_steps": 1295, "total_steps": 25880, "loss": 0.5995, "lr": 0.0005, "epoch": 1.000772797527048, "percentage": 5.0, "elapsed_time": "0:03:48", "remaining_time": "1:12:12", "throughput": 1906.07, "total_tokens": 434976}
|
| 261 |
+
{"current_steps": 1300, "total_steps": 25880, "loss": 0.6224, "lr": 0.0005019319938176197, "epoch": 1.0046367851622875, "percentage": 5.02, "elapsed_time": "0:03:49", "remaining_time": "1:12:10", "throughput": 1906.57, "total_tokens": 436704}
|
| 262 |
+
{"current_steps": 1305, "total_steps": 25880, "loss": 0.9499, "lr": 0.0005038639876352396, "epoch": 1.008500772797527, "percentage": 5.04, "elapsed_time": "0:03:49", "remaining_time": "1:12:09", "throughput": 1907.47, "total_tokens": 438528}
|
| 263 |
+
{"current_steps": 1310, "total_steps": 25880, "loss": 0.7801, "lr": 0.0005057959814528593, "epoch": 1.0123647604327666, "percentage": 5.06, "elapsed_time": "0:03:50", "remaining_time": "1:12:07", "throughput": 1907.32, "total_tokens": 440032}
|
| 264 |
+
{"current_steps": 1315, "total_steps": 25880, "loss": 0.7724, "lr": 0.0005077279752704791, "epoch": 1.0162287480680061, "percentage": 5.08, "elapsed_time": "0:03:51", "remaining_time": "1:12:04", "throughput": 1907.08, "total_tokens": 441504}
|
| 265 |
+
{"current_steps": 1320, "total_steps": 25880, "loss": 0.6407, "lr": 0.000509659969088099, "epoch": 1.0200927357032457, "percentage": 5.1, "elapsed_time": "0:03:52", "remaining_time": "1:12:02", "throughput": 1907.78, "total_tokens": 443232}
|
| 266 |
+
{"current_steps": 1325, "total_steps": 25880, "loss": 1.2082, "lr": 0.0005115919629057187, "epoch": 1.0239567233384854, "percentage": 5.12, "elapsed_time": "0:03:53", "remaining_time": "1:12:00", "throughput": 1908.24, "total_tokens": 444896}
|
| 267 |
+
{"current_steps": 1330, "total_steps": 25880, "loss": 0.6601, "lr": 0.0005135239567233385, "epoch": 1.027820710973725, "percentage": 5.14, "elapsed_time": "0:03:54", "remaining_time": "1:12:00", "throughput": 1908.75, "total_tokens": 446752}
|
| 268 |
+
{"current_steps": 1335, "total_steps": 25880, "loss": 0.5897, "lr": 0.0005154559505409583, "epoch": 1.0316846986089645, "percentage": 5.16, "elapsed_time": "0:03:54", "remaining_time": "1:11:58", "throughput": 1908.6, "total_tokens": 448256}
|
| 269 |
+
{"current_steps": 1340, "total_steps": 25880, "loss": 0.881, "lr": 0.000517387944358578, "epoch": 1.035548686244204, "percentage": 5.18, "elapsed_time": "0:03:55", "remaining_time": "1:11:56", "throughput": 1909.37, "total_tokens": 450080}
|
| 270 |
+
{"current_steps": 1345, "total_steps": 25880, "loss": 0.7475, "lr": 0.0005193199381761978, "epoch": 1.0394126738794436, "percentage": 5.2, "elapsed_time": "0:03:56", "remaining_time": "1:11:54", "throughput": 1908.97, "total_tokens": 451456}
|
| 271 |
+
{"current_steps": 1350, "total_steps": 25880, "loss": 0.6296, "lr": 0.0005212519319938175, "epoch": 1.0432766615146831, "percentage": 5.22, "elapsed_time": "0:03:57", "remaining_time": "1:11:51", "throughput": 1909.07, "total_tokens": 452992}
|
| 272 |
+
{"current_steps": 1355, "total_steps": 25880, "loss": 0.656, "lr": 0.0005231839258114374, "epoch": 1.0471406491499227, "percentage": 5.24, "elapsed_time": "0:03:58", "remaining_time": "1:11:49", "throughput": 1909.45, "total_tokens": 454688}
|
| 273 |
+
{"current_steps": 1360, "total_steps": 25880, "loss": 0.6032, "lr": 0.0005251159196290573, "epoch": 1.0510046367851622, "percentage": 5.26, "elapsed_time": "0:03:58", "remaining_time": "1:11:47", "throughput": 1909.66, "total_tokens": 456288}
|
| 274 |
+
{"current_steps": 1365, "total_steps": 25880, "loss": 0.5929, "lr": 0.000527047913446677, "epoch": 1.054868624420402, "percentage": 5.27, "elapsed_time": "0:03:59", "remaining_time": "1:11:45", "throughput": 1909.48, "total_tokens": 457728}
|
| 275 |
+
{"current_steps": 1370, "total_steps": 25880, "loss": 0.5458, "lr": 0.0005289799072642967, "epoch": 1.0587326120556415, "percentage": 5.29, "elapsed_time": "0:04:00", "remaining_time": "1:11:42", "throughput": 1909.65, "total_tokens": 459264}
|
| 276 |
+
{"current_steps": 1375, "total_steps": 25880, "loss": 0.8598, "lr": 0.0005309119010819166, "epoch": 1.062596599690881, "percentage": 5.31, "elapsed_time": "0:04:01", "remaining_time": "1:11:40", "throughput": 1909.95, "total_tokens": 460832}
|
| 277 |
+
{"current_steps": 1380, "total_steps": 25880, "loss": 0.5621, "lr": 0.0005328438948995363, "epoch": 1.0664605873261206, "percentage": 5.33, "elapsed_time": "0:04:02", "remaining_time": "1:11:39", "throughput": 1910.18, "total_tokens": 462560}
|
| 278 |
+
{"current_steps": 1385, "total_steps": 25880, "loss": 0.5767, "lr": 0.0005347758887171561, "epoch": 1.0703245749613601, "percentage": 5.35, "elapsed_time": "0:04:03", "remaining_time": "1:11:38", "throughput": 1910.68, "total_tokens": 464352}
|
| 279 |
+
{"current_steps": 1390, "total_steps": 25880, "loss": 0.564, "lr": 0.0005367078825347758, "epoch": 1.0741885625965997, "percentage": 5.37, "elapsed_time": "0:04:03", "remaining_time": "1:11:37", "throughput": 1911.25, "total_tokens": 466176}
|
| 280 |
+
{"current_steps": 1395, "total_steps": 25880, "loss": 0.5483, "lr": 0.0005386398763523956, "epoch": 1.0780525502318392, "percentage": 5.39, "elapsed_time": "0:04:04", "remaining_time": "1:11:35", "throughput": 1911.32, "total_tokens": 467744}
|
| 281 |
+
{"current_steps": 1400, "total_steps": 25880, "loss": 0.472, "lr": 0.0005405718701700154, "epoch": 1.0819165378670788, "percentage": 5.41, "elapsed_time": "0:04:05", "remaining_time": "1:11:33", "throughput": 1911.72, "total_tokens": 469408}
|
| 282 |
+
{"current_steps": 1405, "total_steps": 25880, "loss": 0.6537, "lr": 0.0005425038639876353, "epoch": 1.0857805255023183, "percentage": 5.43, "elapsed_time": "0:04:06", "remaining_time": "1:11:31", "throughput": 1911.63, "total_tokens": 470976}
|
| 283 |
+
{"current_steps": 1410, "total_steps": 25880, "loss": 0.4764, "lr": 0.000544435857805255, "epoch": 1.089644513137558, "percentage": 5.45, "elapsed_time": "0:04:07", "remaining_time": "1:11:29", "throughput": 1911.58, "total_tokens": 472448}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d88462d571808ac256d148efea2f7be26b41de5a9ac9f38fc0ef2c885fd685b7
|
| 3 |
+
size 6289
|