Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +94 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +12 -0
- eval_results.json +7 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2065 -0
- train_results.json +8 -0
- trainer_log.jsonl +181 -0
- trainer_state.json +1332 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -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
|
README.md
ADDED
|
@@ -0,0 +1,94 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: unsloth/Llama-3.2-3B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- unsloth
|
| 9 |
+
- generated_from_trainer
|
| 10 |
+
model-index:
|
| 11 |
+
- name: llm3br256-150steps
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# llm3br256-150steps
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the reliance-oneshot-train dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.0129
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0001
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 4
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 8
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- training_steps: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.0468 | 0.1786 | 5 | 0.0408 |
|
| 57 |
+
| 0.0274 | 0.3571 | 10 | 0.0312 |
|
| 58 |
+
| 0.0222 | 0.5357 | 15 | 0.0246 |
|
| 59 |
+
| 0.0253 | 0.7143 | 20 | 0.0221 |
|
| 60 |
+
| 0.0197 | 0.8929 | 25 | 0.0204 |
|
| 61 |
+
| 0.0169 | 1.0714 | 30 | 0.0190 |
|
| 62 |
+
| 0.0152 | 1.25 | 35 | 0.0177 |
|
| 63 |
+
| 0.0169 | 1.4286 | 40 | 0.0168 |
|
| 64 |
+
| 0.0123 | 1.6071 | 45 | 0.0164 |
|
| 65 |
+
| 0.0139 | 1.7857 | 50 | 0.0159 |
|
| 66 |
+
| 0.0105 | 1.9643 | 55 | 0.0153 |
|
| 67 |
+
| 0.0123 | 2.1429 | 60 | 0.0151 |
|
| 68 |
+
| 0.0105 | 2.3214 | 65 | 0.0149 |
|
| 69 |
+
| 0.0103 | 2.5 | 70 | 0.0144 |
|
| 70 |
+
| 0.0097 | 2.6786 | 75 | 0.0139 |
|
| 71 |
+
| 0.0113 | 2.8571 | 80 | 0.0137 |
|
| 72 |
+
| 0.0075 | 3.0357 | 85 | 0.0137 |
|
| 73 |
+
| 0.0084 | 3.2143 | 90 | 0.0137 |
|
| 74 |
+
| 0.0074 | 3.3929 | 95 | 0.0136 |
|
| 75 |
+
| 0.0079 | 3.5714 | 100 | 0.0133 |
|
| 76 |
+
| 0.0078 | 3.75 | 105 | 0.0132 |
|
| 77 |
+
| 0.0084 | 3.9286 | 110 | 0.0130 |
|
| 78 |
+
| 0.0081 | 4.1071 | 115 | 0.0130 |
|
| 79 |
+
| 0.007 | 4.2857 | 120 | 0.0131 |
|
| 80 |
+
| 0.0068 | 4.4643 | 125 | 0.0131 |
|
| 81 |
+
| 0.0069 | 4.6429 | 130 | 0.0131 |
|
| 82 |
+
| 0.0066 | 4.8214 | 135 | 0.0130 |
|
| 83 |
+
| 0.0057 | 5.0 | 140 | 0.0129 |
|
| 84 |
+
| 0.0057 | 5.1786 | 145 | 0.0130 |
|
| 85 |
+
| 0.0057 | 5.3571 | 150 | 0.0129 |
|
| 86 |
+
|
| 87 |
+
|
| 88 |
+
### Framework versions
|
| 89 |
+
|
| 90 |
+
- PEFT 0.12.0
|
| 91 |
+
- Transformers 4.46.1
|
| 92 |
+
- Pytorch 2.4.0+cu121
|
| 93 |
+
- Datasets 3.1.0
|
| 94 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 256,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 256,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"gate_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"o_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:560ed9661da8de3302fa0769b62e38f69c70d73703455c44d973823abac365a3
|
| 3 |
+
size 1556140392
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.357142857142857,
|
| 3 |
+
"eval_loss": 0.012949441559612751,
|
| 4 |
+
"eval_runtime": 9.69,
|
| 5 |
+
"eval_samples_per_second": 5.16,
|
| 6 |
+
"eval_steps_per_second": 1.342,
|
| 7 |
+
"total_flos": 3.292901739866358e+17,
|
| 8 |
+
"train_loss": 0.013509833477437496,
|
| 9 |
+
"train_runtime": 2826.4869,
|
| 10 |
+
"train_samples_per_second": 1.698,
|
| 11 |
+
"train_steps_per_second": 0.053
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.357142857142857,
|
| 3 |
+
"eval_loss": 0.012949441559612751,
|
| 4 |
+
"eval_runtime": 9.69,
|
| 5 |
+
"eval_samples_per_second": 5.16,
|
| 6 |
+
"eval_steps_per_second": 1.342
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin_of_text|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|eot_id|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<|eot_id|>"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 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": "<|eom_id|>",
|
| 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": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- if strftime_now is defined %}\n {%- set date_string = strftime_now(\"%d %b %Y\") %}\n {%- else %}\n {%- set date_string = \"26 Jul 2024\" %}\n {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {{- \"<|eot_id|>\" }}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|eot_id|>",
|
| 2056 |
+
"model_input_names": [
|
| 2057 |
+
"input_ids",
|
| 2058 |
+
"attention_mask"
|
| 2059 |
+
],
|
| 2060 |
+
"model_max_length": 131072,
|
| 2061 |
+
"pad_token": "<|eot_id|>",
|
| 2062 |
+
"padding_side": "right",
|
| 2063 |
+
"split_special_tokens": false,
|
| 2064 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2065 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.357142857142857,
|
| 3 |
+
"total_flos": 3.292901739866358e+17,
|
| 4 |
+
"train_loss": 0.013509833477437496,
|
| 5 |
+
"train_runtime": 2826.4869,
|
| 6 |
+
"train_samples_per_second": 1.698,
|
| 7 |
+
"train_steps_per_second": 0.053
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 150, "loss": 0.0589, "lr": 6.666666666666667e-06, "epoch": 0.03571428571428571, "percentage": 0.67, "elapsed_time": "0:00:19", "remaining_time": "0:48:54"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 150, "loss": 0.0593, "lr": 1.3333333333333333e-05, "epoch": 0.07142857142857142, "percentage": 1.33, "elapsed_time": "0:00:35", "remaining_time": "0:43:40"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 150, "loss": 0.0567, "lr": 2e-05, "epoch": 0.10714285714285714, "percentage": 2.0, "elapsed_time": "0:00:51", "remaining_time": "0:42:02"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 150, "loss": 0.0554, "lr": 2.6666666666666667e-05, "epoch": 0.14285714285714285, "percentage": 2.67, "elapsed_time": "0:01:08", "remaining_time": "0:41:45"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 150, "loss": 0.0468, "lr": 3.3333333333333335e-05, "epoch": 0.17857142857142858, "percentage": 3.33, "elapsed_time": "0:01:25", "remaining_time": "0:41:29"}
|
| 6 |
+
{"current_steps": 5, "total_steps": 150, "eval_loss": 0.040782563388347626, "epoch": 0.17857142857142858, "percentage": 3.33, "elapsed_time": "0:01:35", "remaining_time": "0:46:11"}
|
| 7 |
+
{"current_steps": 6, "total_steps": 150, "loss": 0.0431, "lr": 4e-05, "epoch": 0.21428571428571427, "percentage": 4.0, "elapsed_time": "0:01:52", "remaining_time": "0:45:09"}
|
| 8 |
+
{"current_steps": 7, "total_steps": 150, "loss": 0.0372, "lr": 4.666666666666667e-05, "epoch": 0.25, "percentage": 4.67, "elapsed_time": "0:02:07", "remaining_time": "0:43:31"}
|
| 9 |
+
{"current_steps": 8, "total_steps": 150, "loss": 0.0316, "lr": 5.333333333333333e-05, "epoch": 0.2857142857142857, "percentage": 5.33, "elapsed_time": "0:02:22", "remaining_time": "0:42:09"}
|
| 10 |
+
{"current_steps": 9, "total_steps": 150, "loss": 0.0346, "lr": 6e-05, "epoch": 0.32142857142857145, "percentage": 6.0, "elapsed_time": "0:02:39", "remaining_time": "0:41:35"}
|
| 11 |
+
{"current_steps": 10, "total_steps": 150, "loss": 0.0274, "lr": 6.666666666666667e-05, "epoch": 0.35714285714285715, "percentage": 6.67, "elapsed_time": "0:02:54", "remaining_time": "0:40:48"}
|
| 12 |
+
{"current_steps": 10, "total_steps": 150, "eval_loss": 0.03117537871003151, "epoch": 0.35714285714285715, "percentage": 6.67, "elapsed_time": "0:03:04", "remaining_time": "0:43:04"}
|
| 13 |
+
{"current_steps": 11, "total_steps": 150, "loss": 0.0287, "lr": 7.333333333333333e-05, "epoch": 0.39285714285714285, "percentage": 7.33, "elapsed_time": "0:03:20", "remaining_time": "0:42:12"}
|
| 14 |
+
{"current_steps": 12, "total_steps": 150, "loss": 0.0307, "lr": 8e-05, "epoch": 0.42857142857142855, "percentage": 8.0, "elapsed_time": "0:03:36", "remaining_time": "0:41:32"}
|
| 15 |
+
{"current_steps": 13, "total_steps": 150, "loss": 0.0275, "lr": 8.666666666666667e-05, "epoch": 0.4642857142857143, "percentage": 8.67, "elapsed_time": "0:03:52", "remaining_time": "0:40:49"}
|
| 16 |
+
{"current_steps": 14, "total_steps": 150, "loss": 0.0234, "lr": 9.333333333333334e-05, "epoch": 0.5, "percentage": 9.33, "elapsed_time": "0:04:08", "remaining_time": "0:40:13"}
|
| 17 |
+
{"current_steps": 15, "total_steps": 150, "loss": 0.0222, "lr": 0.0001, "epoch": 0.5357142857142857, "percentage": 10.0, "elapsed_time": "0:04:26", "remaining_time": "0:39:56"}
|
| 18 |
+
{"current_steps": 15, "total_steps": 150, "eval_loss": 0.02460905723273754, "epoch": 0.5357142857142857, "percentage": 10.0, "elapsed_time": "0:04:35", "remaining_time": "0:41:23"}
|
| 19 |
+
{"current_steps": 16, "total_steps": 150, "loss": 0.0222, "lr": 9.998646205897309e-05, "epoch": 0.5714285714285714, "percentage": 10.67, "elapsed_time": "0:04:50", "remaining_time": "0:40:35"}
|
| 20 |
+
{"current_steps": 17, "total_steps": 150, "loss": 0.0235, "lr": 9.994585556692624e-05, "epoch": 0.6071428571428571, "percentage": 11.33, "elapsed_time": "0:05:06", "remaining_time": "0:40:01"}
|
| 21 |
+
{"current_steps": 18, "total_steps": 150, "loss": 0.0203, "lr": 9.987820251299122e-05, "epoch": 0.6428571428571429, "percentage": 12.0, "elapsed_time": "0:05:23", "remaining_time": "0:39:30"}
|
| 22 |
+
{"current_steps": 19, "total_steps": 150, "loss": 0.022, "lr": 9.978353953249022e-05, "epoch": 0.6785714285714286, "percentage": 12.67, "elapsed_time": "0:05:38", "remaining_time": "0:38:52"}
|
| 23 |
+
{"current_steps": 20, "total_steps": 150, "loss": 0.0253, "lr": 9.966191788709716e-05, "epoch": 0.7142857142857143, "percentage": 13.33, "elapsed_time": "0:05:52", "remaining_time": "0:38:12"}
|
| 24 |
+
{"current_steps": 20, "total_steps": 150, "eval_loss": 0.022146690636873245, "epoch": 0.7142857142857143, "percentage": 13.33, "elapsed_time": "0:06:02", "remaining_time": "0:39:15"}
|
| 25 |
+
{"current_steps": 21, "total_steps": 150, "loss": 0.0223, "lr": 9.951340343707852e-05, "epoch": 0.75, "percentage": 14.0, "elapsed_time": "0:06:17", "remaining_time": "0:38:41"}
|
| 26 |
+
{"current_steps": 22, "total_steps": 150, "loss": 0.0206, "lr": 9.933807660562898e-05, "epoch": 0.7857142857142857, "percentage": 14.67, "elapsed_time": "0:06:34", "remaining_time": "0:38:13"}
|
| 27 |
+
{"current_steps": 23, "total_steps": 150, "loss": 0.0179, "lr": 9.913603233532067e-05, "epoch": 0.8214285714285714, "percentage": 15.33, "elapsed_time": "0:06:50", "remaining_time": "0:37:48"}
|
| 28 |
+
{"current_steps": 24, "total_steps": 150, "loss": 0.0178, "lr": 9.890738003669029e-05, "epoch": 0.8571428571428571, "percentage": 16.0, "elapsed_time": "0:07:07", "remaining_time": "0:37:25"}
|
| 29 |
+
{"current_steps": 25, "total_steps": 150, "loss": 0.0197, "lr": 9.865224352899119e-05, "epoch": 0.8928571428571429, "percentage": 16.67, "elapsed_time": "0:07:23", "remaining_time": "0:36:57"}
|
| 30 |
+
{"current_steps": 25, "total_steps": 150, "eval_loss": 0.020402779802680016, "epoch": 0.8928571428571429, "percentage": 16.67, "elapsed_time": "0:07:33", "remaining_time": "0:37:45"}
|
| 31 |
+
{"current_steps": 26, "total_steps": 150, "loss": 0.0204, "lr": 9.837076097314319e-05, "epoch": 0.9285714285714286, "percentage": 17.33, "elapsed_time": "0:07:49", "remaining_time": "0:37:17"}
|
| 32 |
+
{"current_steps": 27, "total_steps": 150, "loss": 0.0175, "lr": 9.806308479691595e-05, "epoch": 0.9642857142857143, "percentage": 18.0, "elapsed_time": "0:08:06", "remaining_time": "0:36:54"}
|
| 33 |
+
{"current_steps": 28, "total_steps": 150, "loss": 0.0194, "lr": 9.77293816123866e-05, "epoch": 1.0, "percentage": 18.67, "elapsed_time": "0:08:21", "remaining_time": "0:36:24"}
|
| 34 |
+
{"current_steps": 29, "total_steps": 150, "loss": 0.0162, "lr": 9.736983212571646e-05, "epoch": 1.0357142857142858, "percentage": 19.33, "elapsed_time": "0:08:37", "remaining_time": "0:36:00"}
|
| 35 |
+
{"current_steps": 30, "total_steps": 150, "loss": 0.0169, "lr": 9.698463103929542e-05, "epoch": 1.0714285714285714, "percentage": 20.0, "elapsed_time": "0:08:54", "remaining_time": "0:35:37"}
|
| 36 |
+
{"current_steps": 30, "total_steps": 150, "eval_loss": 0.01902087777853012, "epoch": 1.0714285714285714, "percentage": 20.0, "elapsed_time": "0:09:04", "remaining_time": "0:36:16"}
|
| 37 |
+
{"current_steps": 31, "total_steps": 150, "loss": 0.0174, "lr": 9.657398694630712e-05, "epoch": 1.1071428571428572, "percentage": 20.67, "elapsed_time": "0:09:20", "remaining_time": "0:35:53"}
|
| 38 |
+
{"current_steps": 32, "total_steps": 150, "loss": 0.0183, "lr": 9.613812221777212e-05, "epoch": 1.1428571428571428, "percentage": 21.33, "elapsed_time": "0:09:37", "remaining_time": "0:35:28"}
|
| 39 |
+
{"current_steps": 33, "total_steps": 150, "loss": 0.0179, "lr": 9.567727288213005e-05, "epoch": 1.1785714285714286, "percentage": 22.0, "elapsed_time": "0:09:53", "remaining_time": "0:35:03"}
|
| 40 |
+
{"current_steps": 34, "total_steps": 150, "loss": 0.0168, "lr": 9.519168849742604e-05, "epoch": 1.2142857142857142, "percentage": 22.67, "elapsed_time": "0:10:09", "remaining_time": "0:34:40"}
|
| 41 |
+
{"current_steps": 35, "total_steps": 150, "loss": 0.0152, "lr": 9.468163201617062e-05, "epoch": 1.25, "percentage": 23.33, "elapsed_time": "0:10:24", "remaining_time": "0:34:11"}
|
| 42 |
+
{"current_steps": 35, "total_steps": 150, "eval_loss": 0.017671477049589157, "epoch": 1.25, "percentage": 23.33, "elapsed_time": "0:10:33", "remaining_time": "0:34:43"}
|
| 43 |
+
{"current_steps": 36, "total_steps": 150, "loss": 0.0157, "lr": 9.414737964294636e-05, "epoch": 1.2857142857142856, "percentage": 24.0, "elapsed_time": "0:10:51", "remaining_time": "0:34:21"}
|
| 44 |
+
{"current_steps": 37, "total_steps": 150, "loss": 0.0155, "lr": 9.358922068483812e-05, "epoch": 1.3214285714285714, "percentage": 24.67, "elapsed_time": "0:11:07", "remaining_time": "0:33:58"}
|
| 45 |
+
{"current_steps": 38, "total_steps": 150, "loss": 0.0141, "lr": 9.300745739476829e-05, "epoch": 1.3571428571428572, "percentage": 25.33, "elapsed_time": "0:11:23", "remaining_time": "0:33:34"}
|
| 46 |
+
{"current_steps": 39, "total_steps": 150, "loss": 0.0129, "lr": 9.24024048078213e-05, "epoch": 1.3928571428571428, "percentage": 26.0, "elapsed_time": "0:11:39", "remaining_time": "0:33:11"}
|
| 47 |
+
{"current_steps": 40, "total_steps": 150, "loss": 0.0169, "lr": 9.177439057064683e-05, "epoch": 1.4285714285714286, "percentage": 26.67, "elapsed_time": "0:11:56", "remaining_time": "0:32:50"}
|
| 48 |
+
{"current_steps": 40, "total_steps": 150, "eval_loss": 0.016827059909701347, "epoch": 1.4285714285714286, "percentage": 26.67, "elapsed_time": "0:12:06", "remaining_time": "0:33:17"}
|
| 49 |
+
{"current_steps": 41, "total_steps": 150, "loss": 0.0119, "lr": 9.112375476403312e-05, "epoch": 1.4642857142857144, "percentage": 27.33, "elapsed_time": "0:12:21", "remaining_time": "0:32:52"}
|
| 50 |
+
{"current_steps": 42, "total_steps": 150, "loss": 0.0196, "lr": 9.045084971874738e-05, "epoch": 1.5, "percentage": 28.0, "elapsed_time": "0:12:37", "remaining_time": "0:32:26"}
|
| 51 |
+
{"current_steps": 43, "total_steps": 150, "loss": 0.0146, "lr": 8.97560398247424e-05, "epoch": 1.5357142857142856, "percentage": 28.67, "elapsed_time": "0:12:54", "remaining_time": "0:32:08"}
|
| 52 |
+
{"current_steps": 44, "total_steps": 150, "loss": 0.0138, "lr": 8.903970133383297e-05, "epoch": 1.5714285714285714, "percentage": 29.33, "elapsed_time": "0:13:10", "remaining_time": "0:31:44"}
|
| 53 |
+
{"current_steps": 45, "total_steps": 150, "loss": 0.0123, "lr": 8.83022221559489e-05, "epoch": 1.6071428571428572, "percentage": 30.0, "elapsed_time": "0:13:26", "remaining_time": "0:31:21"}
|
| 54 |
+
{"current_steps": 45, "total_steps": 150, "eval_loss": 0.016407068818807602, "epoch": 1.6071428571428572, "percentage": 30.0, "elapsed_time": "0:13:36", "remaining_time": "0:31:44"}
|
| 55 |
+
{"current_steps": 46, "total_steps": 150, "loss": 0.0131, "lr": 8.754400164907497e-05, "epoch": 1.6428571428571428, "percentage": 30.67, "elapsed_time": "0:13:51", "remaining_time": "0:31:20"}
|
| 56 |
+
{"current_steps": 47, "total_steps": 150, "loss": 0.011, "lr": 8.676545040299145e-05, "epoch": 1.6785714285714286, "percentage": 31.33, "elapsed_time": "0:14:07", "remaining_time": "0:30:56"}
|
| 57 |
+
{"current_steps": 48, "total_steps": 150, "loss": 0.0138, "lr": 8.596699001693255e-05, "epoch": 1.7142857142857144, "percentage": 32.0, "elapsed_time": "0:14:24", "remaining_time": "0:30:37"}
|
| 58 |
+
{"current_steps": 49, "total_steps": 150, "loss": 0.0131, "lr": 8.51490528712831e-05, "epoch": 1.75, "percentage": 32.67, "elapsed_time": "0:14:40", "remaining_time": "0:30:15"}
|
| 59 |
+
{"current_steps": 50, "total_steps": 150, "loss": 0.0139, "lr": 8.43120818934367e-05, "epoch": 1.7857142857142856, "percentage": 33.33, "elapsed_time": "0:14:55", "remaining_time": "0:29:51"}
|
| 60 |
+
{"current_steps": 50, "total_steps": 150, "eval_loss": 0.015894223004579544, "epoch": 1.7857142857142856, "percentage": 33.33, "elapsed_time": "0:15:05", "remaining_time": "0:30:10"}
|
| 61 |
+
{"current_steps": 51, "total_steps": 150, "loss": 0.0123, "lr": 8.345653031794292e-05, "epoch": 1.8214285714285714, "percentage": 34.0, "elapsed_time": "0:15:50", "remaining_time": "0:30:44"}
|
| 62 |
+
{"current_steps": 52, "total_steps": 150, "loss": 0.0124, "lr": 8.258286144107276e-05, "epoch": 1.8571428571428572, "percentage": 34.67, "elapsed_time": "0:16:06", "remaining_time": "0:30:22"}
|
| 63 |
+
{"current_steps": 53, "total_steps": 150, "loss": 0.014, "lr": 8.169154836993551e-05, "epoch": 1.8928571428571428, "percentage": 35.33, "elapsed_time": "0:16:22", "remaining_time": "0:29:58"}
|
| 64 |
+
{"current_steps": 54, "total_steps": 150, "loss": 0.0125, "lr": 8.07830737662829e-05, "epoch": 1.9285714285714286, "percentage": 36.0, "elapsed_time": "0:16:39", "remaining_time": "0:29:37"}
|
| 65 |
+
{"current_steps": 55, "total_steps": 150, "loss": 0.0105, "lr": 7.985792958513931e-05, "epoch": 1.9642857142857144, "percentage": 36.67, "elapsed_time": "0:16:55", "remaining_time": "0:29:14"}
|
| 66 |
+
{"current_steps": 55, "total_steps": 150, "eval_loss": 0.015282765030860901, "epoch": 1.9642857142857144, "percentage": 36.67, "elapsed_time": "0:17:05", "remaining_time": "0:29:31"}
|
| 67 |
+
{"current_steps": 56, "total_steps": 150, "loss": 0.0133, "lr": 7.891661680839932e-05, "epoch": 2.0, "percentage": 37.33, "elapsed_time": "0:17:20", "remaining_time": "0:29:05"}
|
| 68 |
+
{"current_steps": 57, "total_steps": 150, "loss": 0.0108, "lr": 7.795964517353735e-05, "epoch": 2.0357142857142856, "percentage": 38.0, "elapsed_time": "0:17:36", "remaining_time": "0:28:44"}
|
| 69 |
+
{"current_steps": 58, "total_steps": 150, "loss": 0.0104, "lr": 7.698753289757565e-05, "epoch": 2.0714285714285716, "percentage": 38.67, "elapsed_time": "0:17:53", "remaining_time": "0:28:23"}
|
| 70 |
+
{"current_steps": 59, "total_steps": 150, "loss": 0.0118, "lr": 7.600080639646077e-05, "epoch": 2.107142857142857, "percentage": 39.33, "elapsed_time": "0:18:09", "remaining_time": "0:27:59"}
|
| 71 |
+
{"current_steps": 60, "total_steps": 150, "loss": 0.0123, "lr": 7.500000000000001e-05, "epoch": 2.142857142857143, "percentage": 40.0, "elapsed_time": "0:18:25", "remaining_time": "0:27:38"}
|
| 72 |
+
{"current_steps": 60, "total_steps": 150, "eval_loss": 0.01509407814592123, "epoch": 2.142857142857143, "percentage": 40.0, "elapsed_time": "0:18:35", "remaining_time": "0:27:53"}
|
| 73 |
+
{"current_steps": 61, "total_steps": 150, "loss": 0.0093, "lr": 7.398565566251232e-05, "epoch": 2.1785714285714284, "percentage": 40.67, "elapsed_time": "0:18:52", "remaining_time": "0:27:31"}
|
| 74 |
+
{"current_steps": 62, "total_steps": 150, "loss": 0.0104, "lr": 7.295832266935059e-05, "epoch": 2.2142857142857144, "percentage": 41.33, "elapsed_time": "0:19:08", "remaining_time": "0:27:10"}
|
| 75 |
+
{"current_steps": 63, "total_steps": 150, "loss": 0.0126, "lr": 7.191855733945387e-05, "epoch": 2.25, "percentage": 42.0, "elapsed_time": "0:19:24", "remaining_time": "0:26:48"}
|
| 76 |
+
{"current_steps": 64, "total_steps": 150, "loss": 0.0112, "lr": 7.08669227240909e-05, "epoch": 2.2857142857142856, "percentage": 42.67, "elapsed_time": "0:19:40", "remaining_time": "0:26:26"}
|
| 77 |
+
{"current_steps": 65, "total_steps": 150, "loss": 0.0105, "lr": 6.980398830195785e-05, "epoch": 2.3214285714285716, "percentage": 43.33, "elapsed_time": "0:19:57", "remaining_time": "0:26:06"}
|
| 78 |
+
{"current_steps": 65, "total_steps": 150, "eval_loss": 0.014879303053021431, "epoch": 2.3214285714285716, "percentage": 43.33, "elapsed_time": "0:20:07", "remaining_time": "0:26:19"}
|
| 79 |
+
{"current_steps": 66, "total_steps": 150, "loss": 0.0092, "lr": 6.873032967079561e-05, "epoch": 2.357142857142857, "percentage": 44.0, "elapsed_time": "0:20:23", "remaining_time": "0:25:57"}
|
| 80 |
+
{"current_steps": 67, "total_steps": 150, "loss": 0.0112, "lr": 6.764652823569344e-05, "epoch": 2.392857142857143, "percentage": 44.67, "elapsed_time": "0:20:41", "remaining_time": "0:25:38"}
|
| 81 |
+
{"current_steps": 68, "total_steps": 150, "loss": 0.0104, "lr": 6.65531708942479e-05, "epoch": 2.4285714285714284, "percentage": 45.33, "elapsed_time": "0:20:57", "remaining_time": "0:25:16"}
|
| 82 |
+
{"current_steps": 69, "total_steps": 150, "loss": 0.0103, "lr": 6.545084971874738e-05, "epoch": 2.4642857142857144, "percentage": 46.0, "elapsed_time": "0:21:14", "remaining_time": "0:24:55"}
|
| 83 |
+
{"current_steps": 70, "total_steps": 150, "loss": 0.0103, "lr": 6.434016163555452e-05, "epoch": 2.5, "percentage": 46.67, "elapsed_time": "0:21:30", "remaining_time": "0:24:34"}
|
| 84 |
+
{"current_steps": 70, "total_steps": 150, "eval_loss": 0.014439661055803299, "epoch": 2.5, "percentage": 46.67, "elapsed_time": "0:21:40", "remaining_time": "0:24:45"}
|
| 85 |
+
{"current_steps": 71, "total_steps": 150, "loss": 0.0094, "lr": 6.322170810186012e-05, "epoch": 2.5357142857142856, "percentage": 47.33, "elapsed_time": "0:21:55", "remaining_time": "0:24:23"}
|
| 86 |
+
{"current_steps": 72, "total_steps": 150, "loss": 0.0104, "lr": 6.209609477998338e-05, "epoch": 2.571428571428571, "percentage": 48.0, "elapsed_time": "0:22:13", "remaining_time": "0:24:04"}
|
| 87 |
+
{"current_steps": 73, "total_steps": 150, "loss": 0.0099, "lr": 6.096393120939516e-05, "epoch": 2.607142857142857, "percentage": 48.67, "elapsed_time": "0:22:29", "remaining_time": "0:23:43"}
|
| 88 |
+
{"current_steps": 74, "total_steps": 150, "loss": 0.0122, "lr": 5.982583047664151e-05, "epoch": 2.642857142857143, "percentage": 49.33, "elapsed_time": "0:22:44", "remaining_time": "0:23:21"}
|
| 89 |
+
{"current_steps": 75, "total_steps": 150, "loss": 0.0097, "lr": 5.868240888334653e-05, "epoch": 2.678571428571429, "percentage": 50.0, "elapsed_time": "0:22:59", "remaining_time": "0:22:59"}
|
| 90 |
+
{"current_steps": 75, "total_steps": 150, "eval_loss": 0.013924479484558105, "epoch": 2.678571428571429, "percentage": 50.0, "elapsed_time": "0:23:09", "remaining_time": "0:23:09"}
|
| 91 |
+
{"current_steps": 76, "total_steps": 150, "loss": 0.0093, "lr": 5.753428561247416e-05, "epoch": 2.7142857142857144, "percentage": 50.67, "elapsed_time": "0:23:25", "remaining_time": "0:22:48"}
|
| 92 |
+
{"current_steps": 77, "total_steps": 150, "loss": 0.0106, "lr": 5.6382082393029746e-05, "epoch": 2.75, "percentage": 51.33, "elapsed_time": "0:23:41", "remaining_time": "0:22:27"}
|
| 93 |
+
{"current_steps": 78, "total_steps": 150, "loss": 0.011, "lr": 5.522642316338268e-05, "epoch": 2.7857142857142856, "percentage": 52.0, "elapsed_time": "0:23:56", "remaining_time": "0:22:05"}
|
| 94 |
+
{"current_steps": 79, "total_steps": 150, "loss": 0.0102, "lr": 5.4067933733392915e-05, "epoch": 2.821428571428571, "percentage": 52.67, "elapsed_time": "0:24:12", "remaining_time": "0:21:45"}
|
| 95 |
+
{"current_steps": 80, "total_steps": 150, "loss": 0.0113, "lr": 5.290724144552379e-05, "epoch": 2.857142857142857, "percentage": 53.33, "elapsed_time": "0:24:28", "remaining_time": "0:21:24"}
|
| 96 |
+
{"current_steps": 80, "total_steps": 150, "eval_loss": 0.013650600798428059, "epoch": 2.857142857142857, "percentage": 53.33, "elapsed_time": "0:24:38", "remaining_time": "0:21:33"}
|
| 97 |
+
{"current_steps": 81, "total_steps": 150, "loss": 0.01, "lr": 5.174497483512506e-05, "epoch": 2.892857142857143, "percentage": 54.0, "elapsed_time": "0:24:52", "remaining_time": "0:21:11"}
|
| 98 |
+
{"current_steps": 82, "total_steps": 150, "loss": 0.009, "lr": 5.0581763290069865e-05, "epoch": 2.928571428571429, "percentage": 54.67, "elapsed_time": "0:25:07", "remaining_time": "0:20:50"}
|
| 99 |
+
{"current_steps": 83, "total_steps": 150, "loss": 0.0094, "lr": 4.941823670993016e-05, "epoch": 2.9642857142857144, "percentage": 55.33, "elapsed_time": "0:25:24", "remaining_time": "0:20:30"}
|
| 100 |
+
{"current_steps": 84, "total_steps": 150, "loss": 0.0099, "lr": 4.825502516487497e-05, "epoch": 3.0, "percentage": 56.0, "elapsed_time": "0:25:41", "remaining_time": "0:20:11"}
|
| 101 |
+
{"current_steps": 85, "total_steps": 150, "loss": 0.0075, "lr": 4.709275855447621e-05, "epoch": 3.0357142857142856, "percentage": 56.67, "elapsed_time": "0:25:57", "remaining_time": "0:19:51"}
|
| 102 |
+
{"current_steps": 85, "total_steps": 150, "eval_loss": 0.013672297820448875, "epoch": 3.0357142857142856, "percentage": 56.67, "elapsed_time": "0:26:07", "remaining_time": "0:19:58"}
|
| 103 |
+
{"current_steps": 86, "total_steps": 150, "loss": 0.0086, "lr": 4.593206626660709e-05, "epoch": 3.0714285714285716, "percentage": 57.33, "elapsed_time": "0:26:23", "remaining_time": "0:19:38"}
|
| 104 |
+
{"current_steps": 87, "total_steps": 150, "loss": 0.0102, "lr": 4.477357683661734e-05, "epoch": 3.107142857142857, "percentage": 58.0, "elapsed_time": "0:26:39", "remaining_time": "0:19:18"}
|
| 105 |
+
{"current_steps": 88, "total_steps": 150, "loss": 0.0075, "lr": 4.361791760697027e-05, "epoch": 3.142857142857143, "percentage": 58.67, "elapsed_time": "0:26:56", "remaining_time": "0:18:58"}
|
| 106 |
+
{"current_steps": 89, "total_steps": 150, "loss": 0.0084, "lr": 4.246571438752585e-05, "epoch": 3.1785714285714284, "percentage": 59.33, "elapsed_time": "0:27:11", "remaining_time": "0:18:38"}
|
| 107 |
+
{"current_steps": 90, "total_steps": 150, "loss": 0.0084, "lr": 4.131759111665349e-05, "epoch": 3.2142857142857144, "percentage": 60.0, "elapsed_time": "0:27:29", "remaining_time": "0:18:19"}
|
| 108 |
+
{"current_steps": 90, "total_steps": 150, "eval_loss": 0.013722319155931473, "epoch": 3.2142857142857144, "percentage": 60.0, "elapsed_time": "0:27:39", "remaining_time": "0:18:26"}
|
| 109 |
+
{"current_steps": 91, "total_steps": 150, "loss": 0.0072, "lr": 4.017416952335849e-05, "epoch": 3.25, "percentage": 60.67, "elapsed_time": "0:27:55", "remaining_time": "0:18:06"}
|
| 110 |
+
{"current_steps": 92, "total_steps": 150, "loss": 0.0091, "lr": 3.903606879060483e-05, "epoch": 3.2857142857142856, "percentage": 61.33, "elapsed_time": "0:28:09", "remaining_time": "0:17:45"}
|
| 111 |
+
{"current_steps": 93, "total_steps": 150, "loss": 0.0084, "lr": 3.790390522001662e-05, "epoch": 3.3214285714285716, "percentage": 62.0, "elapsed_time": "0:28:26", "remaining_time": "0:17:25"}
|
| 112 |
+
{"current_steps": 94, "total_steps": 150, "loss": 0.0082, "lr": 3.67782918981399e-05, "epoch": 3.357142857142857, "percentage": 62.67, "elapsed_time": "0:28:41", "remaining_time": "0:17:05"}
|
| 113 |
+
{"current_steps": 95, "total_steps": 150, "loss": 0.0074, "lr": 3.5659838364445505e-05, "epoch": 3.392857142857143, "percentage": 63.33, "elapsed_time": "0:28:56", "remaining_time": "0:16:45"}
|
| 114 |
+
{"current_steps": 95, "total_steps": 150, "eval_loss": 0.01360101904720068, "epoch": 3.392857142857143, "percentage": 63.33, "elapsed_time": "0:29:06", "remaining_time": "0:16:51"}
|
| 115 |
+
{"current_steps": 96, "total_steps": 150, "loss": 0.0068, "lr": 3.4549150281252636e-05, "epoch": 3.4285714285714284, "percentage": 64.0, "elapsed_time": "0:29:23", "remaining_time": "0:16:31"}
|
| 116 |
+
{"current_steps": 97, "total_steps": 150, "loss": 0.0079, "lr": 3.34468291057521e-05, "epoch": 3.4642857142857144, "percentage": 64.67, "elapsed_time": "0:29:40", "remaining_time": "0:16:12"}
|
| 117 |
+
{"current_steps": 98, "total_steps": 150, "loss": 0.0086, "lr": 3.235347176430656e-05, "epoch": 3.5, "percentage": 65.33, "elapsed_time": "0:29:56", "remaining_time": "0:15:53"}
|
| 118 |
+
{"current_steps": 99, "total_steps": 150, "loss": 0.0087, "lr": 3.12696703292044e-05, "epoch": 3.5357142857142856, "percentage": 66.0, "elapsed_time": "0:30:14", "remaining_time": "0:15:34"}
|
| 119 |
+
{"current_steps": 100, "total_steps": 150, "loss": 0.0079, "lr": 3.019601169804216e-05, "epoch": 3.571428571428571, "percentage": 66.67, "elapsed_time": "0:30:30", "remaining_time": "0:15:15"}
|
| 120 |
+
{"current_steps": 100, "total_steps": 150, "eval_loss": 0.013337756507098675, "epoch": 3.571428571428571, "percentage": 66.67, "elapsed_time": "0:30:39", "remaining_time": "0:15:19"}
|
| 121 |
+
{"current_steps": 101, "total_steps": 150, "loss": 0.0074, "lr": 2.9133077275909108e-05, "epoch": 3.607142857142857, "percentage": 67.33, "elapsed_time": "0:31:38", "remaining_time": "0:15:21"}
|
| 122 |
+
{"current_steps": 102, "total_steps": 150, "loss": 0.009, "lr": 2.8081442660546125e-05, "epoch": 3.642857142857143, "percentage": 68.0, "elapsed_time": "0:31:56", "remaining_time": "0:15:01"}
|
| 123 |
+
{"current_steps": 103, "total_steps": 150, "loss": 0.0082, "lr": 2.7041677330649407e-05, "epoch": 3.678571428571429, "percentage": 68.67, "elapsed_time": "0:32:12", "remaining_time": "0:14:42"}
|
| 124 |
+
{"current_steps": 104, "total_steps": 150, "loss": 0.0089, "lr": 2.6014344337487707e-05, "epoch": 3.7142857142857144, "percentage": 69.33, "elapsed_time": "0:32:27", "remaining_time": "0:14:21"}
|
| 125 |
+
{"current_steps": 105, "total_steps": 150, "loss": 0.0078, "lr": 2.500000000000001e-05, "epoch": 3.75, "percentage": 70.0, "elapsed_time": "0:32:44", "remaining_time": "0:14:01"}
|
| 126 |
+
{"current_steps": 105, "total_steps": 150, "eval_loss": 0.013194898143410683, "epoch": 3.75, "percentage": 70.0, "elapsed_time": "0:32:54", "remaining_time": "0:14:06"}
|
| 127 |
+
{"current_steps": 106, "total_steps": 150, "loss": 0.0075, "lr": 2.399919360353923e-05, "epoch": 3.7857142857142856, "percentage": 70.67, "elapsed_time": "0:33:10", "remaining_time": "0:13:46"}
|
| 128 |
+
{"current_steps": 107, "total_steps": 150, "loss": 0.0095, "lr": 2.3012467102424373e-05, "epoch": 3.821428571428571, "percentage": 71.33, "elapsed_time": "0:33:26", "remaining_time": "0:13:26"}
|
| 129 |
+
{"current_steps": 108, "total_steps": 150, "loss": 0.0069, "lr": 2.2040354826462668e-05, "epoch": 3.857142857142857, "percentage": 72.0, "elapsed_time": "0:33:43", "remaining_time": "0:13:07"}
|
| 130 |
+
{"current_steps": 109, "total_steps": 150, "loss": 0.0086, "lr": 2.1083383191600674e-05, "epoch": 3.892857142857143, "percentage": 72.67, "elapsed_time": "0:33:59", "remaining_time": "0:12:47"}
|
| 131 |
+
{"current_steps": 110, "total_steps": 150, "loss": 0.0084, "lr": 2.0142070414860704e-05, "epoch": 3.928571428571429, "percentage": 73.33, "elapsed_time": "0:34:15", "remaining_time": "0:12:27"}
|
| 132 |
+
{"current_steps": 110, "total_steps": 150, "eval_loss": 0.013033830560743809, "epoch": 3.928571428571429, "percentage": 73.33, "elapsed_time": "0:34:24", "remaining_time": "0:12:30"}
|
| 133 |
+
{"current_steps": 111, "total_steps": 150, "loss": 0.0072, "lr": 1.9216926233717085e-05, "epoch": 3.9642857142857144, "percentage": 74.0, "elapsed_time": "0:34:41", "remaining_time": "0:12:11"}
|
| 134 |
+
{"current_steps": 112, "total_steps": 150, "loss": 0.0079, "lr": 1.8308451630064484e-05, "epoch": 4.0, "percentage": 74.67, "elapsed_time": "0:34:57", "remaining_time": "0:11:51"}
|
| 135 |
+
{"current_steps": 113, "total_steps": 150, "loss": 0.0067, "lr": 1.7417138558927244e-05, "epoch": 4.035714285714286, "percentage": 75.33, "elapsed_time": "0:35:13", "remaining_time": "0:11:32"}
|
| 136 |
+
{"current_steps": 114, "total_steps": 150, "loss": 0.0069, "lr": 1.6543469682057106e-05, "epoch": 4.071428571428571, "percentage": 76.0, "elapsed_time": "0:35:29", "remaining_time": "0:11:12"}
|
| 137 |
+
{"current_steps": 115, "total_steps": 150, "loss": 0.0081, "lr": 1.5687918106563326e-05, "epoch": 4.107142857142857, "percentage": 76.67, "elapsed_time": "0:35:45", "remaining_time": "0:10:53"}
|
| 138 |
+
{"current_steps": 115, "total_steps": 150, "eval_loss": 0.012972795404493809, "epoch": 4.107142857142857, "percentage": 76.67, "elapsed_time": "0:35:55", "remaining_time": "0:10:56"}
|
| 139 |
+
{"current_steps": 116, "total_steps": 150, "loss": 0.0064, "lr": 1.4850947128716913e-05, "epoch": 4.142857142857143, "percentage": 77.33, "elapsed_time": "0:36:12", "remaining_time": "0:10:36"}
|
| 140 |
+
{"current_steps": 117, "total_steps": 150, "loss": 0.0066, "lr": 1.4033009983067452e-05, "epoch": 4.178571428571429, "percentage": 78.0, "elapsed_time": "0:36:28", "remaining_time": "0:10:17"}
|
| 141 |
+
{"current_steps": 118, "total_steps": 150, "loss": 0.0071, "lr": 1.3234549597008571e-05, "epoch": 4.214285714285714, "percentage": 78.67, "elapsed_time": "0:36:44", "remaining_time": "0:09:57"}
|
| 142 |
+
{"current_steps": 119, "total_steps": 150, "loss": 0.0063, "lr": 1.245599835092504e-05, "epoch": 4.25, "percentage": 79.33, "elapsed_time": "0:37:02", "remaining_time": "0:09:38"}
|
| 143 |
+
{"current_steps": 120, "total_steps": 150, "loss": 0.007, "lr": 1.1697777844051105e-05, "epoch": 4.285714285714286, "percentage": 80.0, "elapsed_time": "0:37:18", "remaining_time": "0:09:19"}
|
| 144 |
+
{"current_steps": 120, "total_steps": 150, "eval_loss": 0.013091979548335075, "epoch": 4.285714285714286, "percentage": 80.0, "elapsed_time": "0:37:28", "remaining_time": "0:09:22"}
|
| 145 |
+
{"current_steps": 121, "total_steps": 150, "loss": 0.0058, "lr": 1.096029866616704e-05, "epoch": 4.321428571428571, "percentage": 80.67, "elapsed_time": "0:37:43", "remaining_time": "0:09:02"}
|
| 146 |
+
{"current_steps": 122, "total_steps": 150, "loss": 0.0069, "lr": 1.0243960175257606e-05, "epoch": 4.357142857142857, "percentage": 81.33, "elapsed_time": "0:38:00", "remaining_time": "0:08:43"}
|
| 147 |
+
{"current_steps": 123, "total_steps": 150, "loss": 0.0087, "lr": 9.549150281252633e-06, "epoch": 4.392857142857143, "percentage": 82.0, "elapsed_time": "0:38:17", "remaining_time": "0:08:24"}
|
| 148 |
+
{"current_steps": 124, "total_steps": 150, "loss": 0.0061, "lr": 8.876245235966885e-06, "epoch": 4.428571428571429, "percentage": 82.67, "elapsed_time": "0:38:35", "remaining_time": "0:08:05"}
|
| 149 |
+
{"current_steps": 125, "total_steps": 150, "loss": 0.0068, "lr": 8.225609429353187e-06, "epoch": 4.464285714285714, "percentage": 83.33, "elapsed_time": "0:38:50", "remaining_time": "0:07:46"}
|
| 150 |
+
{"current_steps": 125, "total_steps": 150, "eval_loss": 0.013120167888700962, "epoch": 4.464285714285714, "percentage": 83.33, "elapsed_time": "0:39:00", "remaining_time": "0:07:48"}
|
| 151 |
+
{"current_steps": 126, "total_steps": 150, "loss": 0.007, "lr": 7.597595192178702e-06, "epoch": 4.5, "percentage": 84.0, "elapsed_time": "0:39:15", "remaining_time": "0:07:28"}
|
| 152 |
+
{"current_steps": 127, "total_steps": 150, "loss": 0.0067, "lr": 6.992542605231739e-06, "epoch": 4.535714285714286, "percentage": 84.67, "elapsed_time": "0:39:31", "remaining_time": "0:07:09"}
|
| 153 |
+
{"current_steps": 128, "total_steps": 150, "loss": 0.0064, "lr": 6.410779315161886e-06, "epoch": 4.571428571428571, "percentage": 85.33, "elapsed_time": "0:39:49", "remaining_time": "0:06:50"}
|
| 154 |
+
{"current_steps": 129, "total_steps": 150, "loss": 0.0057, "lr": 5.852620357053651e-06, "epoch": 4.607142857142857, "percentage": 86.0, "elapsed_time": "0:40:04", "remaining_time": "0:06:31"}
|
| 155 |
+
{"current_steps": 130, "total_steps": 150, "loss": 0.0069, "lr": 5.318367983829392e-06, "epoch": 4.642857142857143, "percentage": 86.67, "elapsed_time": "0:40:19", "remaining_time": "0:06:12"}
|
| 156 |
+
{"current_steps": 130, "total_steps": 150, "eval_loss": 0.01305928360670805, "epoch": 4.642857142857143, "percentage": 86.67, "elapsed_time": "0:40:29", "remaining_time": "0:06:13"}
|
| 157 |
+
{"current_steps": 131, "total_steps": 150, "loss": 0.0064, "lr": 4.8083115025739756e-06, "epoch": 4.678571428571429, "percentage": 87.33, "elapsed_time": "0:40:47", "remaining_time": "0:05:54"}
|
| 158 |
+
{"current_steps": 132, "total_steps": 150, "loss": 0.0056, "lr": 4.322727117869951e-06, "epoch": 4.714285714285714, "percentage": 88.0, "elapsed_time": "0:41:05", "remaining_time": "0:05:36"}
|
| 159 |
+
{"current_steps": 133, "total_steps": 150, "loss": 0.0067, "lr": 3.861877782227885e-06, "epoch": 4.75, "percentage": 88.67, "elapsed_time": "0:41:21", "remaining_time": "0:05:17"}
|
| 160 |
+
{"current_steps": 134, "total_steps": 150, "loss": 0.0064, "lr": 3.426013053692878e-06, "epoch": 4.785714285714286, "percentage": 89.33, "elapsed_time": "0:41:38", "remaining_time": "0:04:58"}
|
| 161 |
+
{"current_steps": 135, "total_steps": 150, "loss": 0.0066, "lr": 3.0153689607045845e-06, "epoch": 4.821428571428571, "percentage": 90.0, "elapsed_time": "0:41:55", "remaining_time": "0:04:39"}
|
| 162 |
+
{"current_steps": 135, "total_steps": 150, "eval_loss": 0.012971566058695316, "epoch": 4.821428571428571, "percentage": 90.0, "elapsed_time": "0:42:05", "remaining_time": "0:04:40"}
|
| 163 |
+
{"current_steps": 136, "total_steps": 150, "loss": 0.0059, "lr": 2.63016787428354e-06, "epoch": 4.857142857142857, "percentage": 90.67, "elapsed_time": "0:42:19", "remaining_time": "0:04:21"}
|
| 164 |
+
{"current_steps": 137, "total_steps": 150, "loss": 0.0063, "lr": 2.2706183876134045e-06, "epoch": 4.892857142857143, "percentage": 91.33, "elapsed_time": "0:42:34", "remaining_time": "0:04:02"}
|
| 165 |
+
{"current_steps": 138, "total_steps": 150, "loss": 0.0063, "lr": 1.9369152030840556e-06, "epoch": 4.928571428571429, "percentage": 92.0, "elapsed_time": "0:42:50", "remaining_time": "0:03:43"}
|
| 166 |
+
{"current_steps": 139, "total_steps": 150, "loss": 0.0064, "lr": 1.6292390268568104e-06, "epoch": 4.964285714285714, "percentage": 92.67, "elapsed_time": "0:43:07", "remaining_time": "0:03:24"}
|
| 167 |
+
{"current_steps": 140, "total_steps": 150, "loss": 0.0057, "lr": 1.3477564710088098e-06, "epoch": 5.0, "percentage": 93.33, "elapsed_time": "0:43:23", "remaining_time": "0:03:05"}
|
| 168 |
+
{"current_steps": 140, "total_steps": 150, "eval_loss": 0.012948555871844292, "epoch": 5.0, "percentage": 93.33, "elapsed_time": "0:43:33", "remaining_time": "0:03:06"}
|
| 169 |
+
{"current_steps": 141, "total_steps": 150, "loss": 0.0067, "lr": 1.0926199633097157e-06, "epoch": 5.035714285714286, "percentage": 94.0, "elapsed_time": "0:43:49", "remaining_time": "0:02:47"}
|
| 170 |
+
{"current_steps": 142, "total_steps": 150, "loss": 0.0064, "lr": 8.639676646793382e-07, "epoch": 5.071428571428571, "percentage": 94.67, "elapsed_time": "0:44:05", "remaining_time": "0:02:29"}
|
| 171 |
+
{"current_steps": 143, "total_steps": 150, "loss": 0.0061, "lr": 6.61923394371039e-07, "epoch": 5.107142857142857, "percentage": 95.33, "elapsed_time": "0:44:22", "remaining_time": "0:02:10"}
|
| 172 |
+
{"current_steps": 144, "total_steps": 150, "loss": 0.0061, "lr": 4.865965629214819e-07, "epoch": 5.142857142857143, "percentage": 96.0, "elapsed_time": "0:44:37", "remaining_time": "0:01:51"}
|
| 173 |
+
{"current_steps": 145, "total_steps": 150, "loss": 0.0057, "lr": 3.380821129028489e-07, "epoch": 5.178571428571429, "percentage": 96.67, "elapsed_time": "0:44:54", "remaining_time": "0:01:32"}
|
| 174 |
+
{"current_steps": 145, "total_steps": 150, "eval_loss": 0.012967634946107864, "epoch": 5.178571428571429, "percentage": 96.67, "elapsed_time": "0:45:04", "remaining_time": "0:01:33"}
|
| 175 |
+
{"current_steps": 146, "total_steps": 150, "loss": 0.0074, "lr": 2.1646046750978254e-07, "epoch": 5.214285714285714, "percentage": 97.33, "elapsed_time": "0:45:21", "remaining_time": "0:01:14"}
|
| 176 |
+
{"current_steps": 147, "total_steps": 150, "loss": 0.007, "lr": 1.2179748700879012e-07, "epoch": 5.25, "percentage": 98.0, "elapsed_time": "0:45:39", "remaining_time": "0:00:55"}
|
| 177 |
+
{"current_steps": 148, "total_steps": 150, "loss": 0.0064, "lr": 5.4144433073771707e-08, "epoch": 5.285714285714286, "percentage": 98.67, "elapsed_time": "0:45:54", "remaining_time": "0:00:37"}
|
| 178 |
+
{"current_steps": 149, "total_steps": 150, "loss": 0.005, "lr": 1.3537941026914303e-08, "epoch": 5.321428571428571, "percentage": 99.33, "elapsed_time": "0:46:11", "remaining_time": "0:00:18"}
|
| 179 |
+
{"current_steps": 150, "total_steps": 150, "loss": 0.0057, "lr": 0.0, "epoch": 5.357142857142857, "percentage": 100.0, "elapsed_time": "0:46:28", "remaining_time": "0:00:00"}
|
| 180 |
+
{"current_steps": 150, "total_steps": 150, "eval_loss": 0.012949441559612751, "epoch": 5.357142857142857, "percentage": 100.0, "elapsed_time": "0:46:38", "remaining_time": "0:00:00"}
|
| 181 |
+
{"current_steps": 150, "total_steps": 150, "epoch": 5.357142857142857, "percentage": 100.0, "elapsed_time": "0:47:05", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.012949441559612751,
|
| 3 |
+
"best_model_checkpoint": "saves/reliance/llm3br256-150steps/checkpoint-150",
|
| 4 |
+
"epoch": 5.357142857142857,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 150,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03571428571428571,
|
| 13 |
+
"grad_norm": 0.1307915449142456,
|
| 14 |
+
"learning_rate": 6.666666666666667e-06,
|
| 15 |
+
"loss": 0.0589,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07142857142857142,
|
| 20 |
+
"grad_norm": 0.1408260017633438,
|
| 21 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 22 |
+
"loss": 0.0593,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.10714285714285714,
|
| 27 |
+
"grad_norm": 0.1269747018814087,
|
| 28 |
+
"learning_rate": 2e-05,
|
| 29 |
+
"loss": 0.0567,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.14285714285714285,
|
| 34 |
+
"grad_norm": 0.11240039020776749,
|
| 35 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 36 |
+
"loss": 0.0554,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.17857142857142858,
|
| 41 |
+
"grad_norm": 0.0858268290758133,
|
| 42 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 43 |
+
"loss": 0.0468,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17857142857142858,
|
| 48 |
+
"eval_loss": 0.040782563388347626,
|
| 49 |
+
"eval_runtime": 9.7192,
|
| 50 |
+
"eval_samples_per_second": 5.144,
|
| 51 |
+
"eval_steps_per_second": 1.338,
|
| 52 |
+
"step": 5
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.21428571428571427,
|
| 56 |
+
"grad_norm": 0.06239774078130722,
|
| 57 |
+
"learning_rate": 4e-05,
|
| 58 |
+
"loss": 0.0431,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.25,
|
| 63 |
+
"grad_norm": 0.07012197375297546,
|
| 64 |
+
"learning_rate": 4.666666666666667e-05,
|
| 65 |
+
"loss": 0.0372,
|
| 66 |
+
"step": 7
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.2857142857142857,
|
| 70 |
+
"grad_norm": 0.05583757534623146,
|
| 71 |
+
"learning_rate": 5.333333333333333e-05,
|
| 72 |
+
"loss": 0.0316,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.32142857142857145,
|
| 77 |
+
"grad_norm": 0.05181620642542839,
|
| 78 |
+
"learning_rate": 6e-05,
|
| 79 |
+
"loss": 0.0346,
|
| 80 |
+
"step": 9
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.35714285714285715,
|
| 84 |
+
"grad_norm": 0.04640357941389084,
|
| 85 |
+
"learning_rate": 6.666666666666667e-05,
|
| 86 |
+
"loss": 0.0274,
|
| 87 |
+
"step": 10
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.35714285714285715,
|
| 91 |
+
"eval_loss": 0.03117537871003151,
|
| 92 |
+
"eval_runtime": 9.7086,
|
| 93 |
+
"eval_samples_per_second": 5.15,
|
| 94 |
+
"eval_steps_per_second": 1.339,
|
| 95 |
+
"step": 10
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.39285714285714285,
|
| 99 |
+
"grad_norm": 0.04249609634280205,
|
| 100 |
+
"learning_rate": 7.333333333333333e-05,
|
| 101 |
+
"loss": 0.0287,
|
| 102 |
+
"step": 11
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.42857142857142855,
|
| 106 |
+
"grad_norm": 0.035397086292505264,
|
| 107 |
+
"learning_rate": 8e-05,
|
| 108 |
+
"loss": 0.0307,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.4642857142857143,
|
| 113 |
+
"grad_norm": 0.03084222413599491,
|
| 114 |
+
"learning_rate": 8.666666666666667e-05,
|
| 115 |
+
"loss": 0.0275,
|
| 116 |
+
"step": 13
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.5,
|
| 120 |
+
"grad_norm": 0.029749521985650063,
|
| 121 |
+
"learning_rate": 9.333333333333334e-05,
|
| 122 |
+
"loss": 0.0234,
|
| 123 |
+
"step": 14
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.5357142857142857,
|
| 127 |
+
"grad_norm": 0.027493193745613098,
|
| 128 |
+
"learning_rate": 0.0001,
|
| 129 |
+
"loss": 0.0222,
|
| 130 |
+
"step": 15
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5357142857142857,
|
| 134 |
+
"eval_loss": 0.02460905723273754,
|
| 135 |
+
"eval_runtime": 9.6981,
|
| 136 |
+
"eval_samples_per_second": 5.156,
|
| 137 |
+
"eval_steps_per_second": 1.34,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.5714285714285714,
|
| 142 |
+
"grad_norm": 0.023510940372943878,
|
| 143 |
+
"learning_rate": 9.998646205897309e-05,
|
| 144 |
+
"loss": 0.0222,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.6071428571428571,
|
| 149 |
+
"grad_norm": 0.025213753804564476,
|
| 150 |
+
"learning_rate": 9.994585556692624e-05,
|
| 151 |
+
"loss": 0.0235,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.6428571428571429,
|
| 156 |
+
"grad_norm": 0.02702331356704235,
|
| 157 |
+
"learning_rate": 9.987820251299122e-05,
|
| 158 |
+
"loss": 0.0203,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.6785714285714286,
|
| 163 |
+
"grad_norm": 0.023405319079756737,
|
| 164 |
+
"learning_rate": 9.978353953249022e-05,
|
| 165 |
+
"loss": 0.022,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.7142857142857143,
|
| 170 |
+
"grad_norm": 0.025470519438385963,
|
| 171 |
+
"learning_rate": 9.966191788709716e-05,
|
| 172 |
+
"loss": 0.0253,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.7142857142857143,
|
| 177 |
+
"eval_loss": 0.022146690636873245,
|
| 178 |
+
"eval_runtime": 9.7055,
|
| 179 |
+
"eval_samples_per_second": 5.152,
|
| 180 |
+
"eval_steps_per_second": 1.339,
|
| 181 |
+
"step": 20
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.75,
|
| 185 |
+
"grad_norm": 0.02303362265229225,
|
| 186 |
+
"learning_rate": 9.951340343707852e-05,
|
| 187 |
+
"loss": 0.0223,
|
| 188 |
+
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7857142857142857,
|
| 192 |
+
"grad_norm": 0.021010441705584526,
|
| 193 |
+
"learning_rate": 9.933807660562898e-05,
|
| 194 |
+
"loss": 0.0206,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.8214285714285714,
|
| 199 |
+
"grad_norm": 0.017238620668649673,
|
| 200 |
+
"learning_rate": 9.913603233532067e-05,
|
| 201 |
+
"loss": 0.0179,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.8571428571428571,
|
| 206 |
+
"grad_norm": 0.017723187804222107,
|
| 207 |
+
"learning_rate": 9.890738003669029e-05,
|
| 208 |
+
"loss": 0.0178,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.8928571428571429,
|
| 213 |
+
"grad_norm": 0.01911439187824726,
|
| 214 |
+
"learning_rate": 9.865224352899119e-05,
|
| 215 |
+
"loss": 0.0197,
|
| 216 |
+
"step": 25
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.8928571428571429,
|
| 220 |
+
"eval_loss": 0.020402779802680016,
|
| 221 |
+
"eval_runtime": 9.7024,
|
| 222 |
+
"eval_samples_per_second": 5.153,
|
| 223 |
+
"eval_steps_per_second": 1.34,
|
| 224 |
+
"step": 25
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.9285714285714286,
|
| 228 |
+
"grad_norm": 0.02038487419486046,
|
| 229 |
+
"learning_rate": 9.837076097314319e-05,
|
| 230 |
+
"loss": 0.0204,
|
| 231 |
+
"step": 26
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.9642857142857143,
|
| 235 |
+
"grad_norm": 0.017658425495028496,
|
| 236 |
+
"learning_rate": 9.806308479691595e-05,
|
| 237 |
+
"loss": 0.0175,
|
| 238 |
+
"step": 27
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.0,
|
| 242 |
+
"grad_norm": 0.019513733685016632,
|
| 243 |
+
"learning_rate": 9.77293816123866e-05,
|
| 244 |
+
"loss": 0.0194,
|
| 245 |
+
"step": 28
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.0357142857142858,
|
| 249 |
+
"grad_norm": 0.01571977138519287,
|
| 250 |
+
"learning_rate": 9.736983212571646e-05,
|
| 251 |
+
"loss": 0.0162,
|
| 252 |
+
"step": 29
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.0714285714285714,
|
| 256 |
+
"grad_norm": 0.015432390384376049,
|
| 257 |
+
"learning_rate": 9.698463103929542e-05,
|
| 258 |
+
"loss": 0.0169,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.0714285714285714,
|
| 263 |
+
"eval_loss": 0.01902087777853012,
|
| 264 |
+
"eval_runtime": 9.7062,
|
| 265 |
+
"eval_samples_per_second": 5.151,
|
| 266 |
+
"eval_steps_per_second": 1.339,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.1071428571428572,
|
| 271 |
+
"grad_norm": 0.016625680029392242,
|
| 272 |
+
"learning_rate": 9.657398694630712e-05,
|
| 273 |
+
"loss": 0.0174,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.1428571428571428,
|
| 278 |
+
"grad_norm": 0.017280418425798416,
|
| 279 |
+
"learning_rate": 9.613812221777212e-05,
|
| 280 |
+
"loss": 0.0183,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.1785714285714286,
|
| 285 |
+
"grad_norm": 0.01627461425960064,
|
| 286 |
+
"learning_rate": 9.567727288213005e-05,
|
| 287 |
+
"loss": 0.0179,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.2142857142857142,
|
| 292 |
+
"grad_norm": 0.0157009270042181,
|
| 293 |
+
"learning_rate": 9.519168849742604e-05,
|
| 294 |
+
"loss": 0.0168,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.25,
|
| 299 |
+
"grad_norm": 0.016017138957977295,
|
| 300 |
+
"learning_rate": 9.468163201617062e-05,
|
| 301 |
+
"loss": 0.0152,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.25,
|
| 306 |
+
"eval_loss": 0.017671477049589157,
|
| 307 |
+
"eval_runtime": 9.7159,
|
| 308 |
+
"eval_samples_per_second": 5.146,
|
| 309 |
+
"eval_steps_per_second": 1.338,
|
| 310 |
+
"step": 35
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.2857142857142856,
|
| 314 |
+
"grad_norm": 0.015069089829921722,
|
| 315 |
+
"learning_rate": 9.414737964294636e-05,
|
| 316 |
+
"loss": 0.0157,
|
| 317 |
+
"step": 36
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.3214285714285714,
|
| 321 |
+
"grad_norm": 0.01685360074043274,
|
| 322 |
+
"learning_rate": 9.358922068483812e-05,
|
| 323 |
+
"loss": 0.0155,
|
| 324 |
+
"step": 37
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.3571428571428572,
|
| 328 |
+
"grad_norm": 0.013408282771706581,
|
| 329 |
+
"learning_rate": 9.300745739476829e-05,
|
| 330 |
+
"loss": 0.0141,
|
| 331 |
+
"step": 38
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.3928571428571428,
|
| 335 |
+
"grad_norm": 0.016533726826310158,
|
| 336 |
+
"learning_rate": 9.24024048078213e-05,
|
| 337 |
+
"loss": 0.0129,
|
| 338 |
+
"step": 39
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.4285714285714286,
|
| 342 |
+
"grad_norm": 0.019688880071043968,
|
| 343 |
+
"learning_rate": 9.177439057064683e-05,
|
| 344 |
+
"loss": 0.0169,
|
| 345 |
+
"step": 40
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.4285714285714286,
|
| 349 |
+
"eval_loss": 0.016827059909701347,
|
| 350 |
+
"eval_runtime": 9.7297,
|
| 351 |
+
"eval_samples_per_second": 5.139,
|
| 352 |
+
"eval_steps_per_second": 1.336,
|
| 353 |
+
"step": 40
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4642857142857144,
|
| 357 |
+
"grad_norm": 0.014212379232048988,
|
| 358 |
+
"learning_rate": 9.112375476403312e-05,
|
| 359 |
+
"loss": 0.0119,
|
| 360 |
+
"step": 41
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5,
|
| 364 |
+
"grad_norm": 0.01729738339781761,
|
| 365 |
+
"learning_rate": 9.045084971874738e-05,
|
| 366 |
+
"loss": 0.0196,
|
| 367 |
+
"step": 42
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5357142857142856,
|
| 371 |
+
"grad_norm": 0.017516475170850754,
|
| 372 |
+
"learning_rate": 8.97560398247424e-05,
|
| 373 |
+
"loss": 0.0146,
|
| 374 |
+
"step": 43
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5714285714285714,
|
| 378 |
+
"grad_norm": 0.01964387111365795,
|
| 379 |
+
"learning_rate": 8.903970133383297e-05,
|
| 380 |
+
"loss": 0.0138,
|
| 381 |
+
"step": 44
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6071428571428572,
|
| 385 |
+
"grad_norm": 0.02011696994304657,
|
| 386 |
+
"learning_rate": 8.83022221559489e-05,
|
| 387 |
+
"loss": 0.0123,
|
| 388 |
+
"step": 45
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6071428571428572,
|
| 392 |
+
"eval_loss": 0.016407068818807602,
|
| 393 |
+
"eval_runtime": 9.7044,
|
| 394 |
+
"eval_samples_per_second": 5.152,
|
| 395 |
+
"eval_steps_per_second": 1.34,
|
| 396 |
+
"step": 45
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.6428571428571428,
|
| 400 |
+
"grad_norm": 0.014331546612083912,
|
| 401 |
+
"learning_rate": 8.754400164907497e-05,
|
| 402 |
+
"loss": 0.0131,
|
| 403 |
+
"step": 46
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.6785714285714286,
|
| 407 |
+
"grad_norm": 0.015035141259431839,
|
| 408 |
+
"learning_rate": 8.676545040299145e-05,
|
| 409 |
+
"loss": 0.011,
|
| 410 |
+
"step": 47
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.7142857142857144,
|
| 414 |
+
"grad_norm": 0.01644822023808956,
|
| 415 |
+
"learning_rate": 8.596699001693255e-05,
|
| 416 |
+
"loss": 0.0138,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.75,
|
| 421 |
+
"grad_norm": 0.01929084025323391,
|
| 422 |
+
"learning_rate": 8.51490528712831e-05,
|
| 423 |
+
"loss": 0.0131,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.7857142857142856,
|
| 428 |
+
"grad_norm": 0.020783884450793266,
|
| 429 |
+
"learning_rate": 8.43120818934367e-05,
|
| 430 |
+
"loss": 0.0139,
|
| 431 |
+
"step": 50
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.7857142857142856,
|
| 435 |
+
"eval_loss": 0.015894223004579544,
|
| 436 |
+
"eval_runtime": 9.7077,
|
| 437 |
+
"eval_samples_per_second": 5.151,
|
| 438 |
+
"eval_steps_per_second": 1.339,
|
| 439 |
+
"step": 50
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.8214285714285714,
|
| 443 |
+
"grad_norm": 0.016066597774624825,
|
| 444 |
+
"learning_rate": 8.345653031794292e-05,
|
| 445 |
+
"loss": 0.0123,
|
| 446 |
+
"step": 51
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.8571428571428572,
|
| 450 |
+
"grad_norm": 0.01717841811478138,
|
| 451 |
+
"learning_rate": 8.258286144107276e-05,
|
| 452 |
+
"loss": 0.0124,
|
| 453 |
+
"step": 52
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.8928571428571428,
|
| 457 |
+
"grad_norm": 0.016235852614045143,
|
| 458 |
+
"learning_rate": 8.169154836993551e-05,
|
| 459 |
+
"loss": 0.014,
|
| 460 |
+
"step": 53
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.9285714285714286,
|
| 464 |
+
"grad_norm": 0.015112782828509808,
|
| 465 |
+
"learning_rate": 8.07830737662829e-05,
|
| 466 |
+
"loss": 0.0125,
|
| 467 |
+
"step": 54
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.9642857142857144,
|
| 471 |
+
"grad_norm": 0.013856356032192707,
|
| 472 |
+
"learning_rate": 7.985792958513931e-05,
|
| 473 |
+
"loss": 0.0105,
|
| 474 |
+
"step": 55
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.9642857142857144,
|
| 478 |
+
"eval_loss": 0.015282765030860901,
|
| 479 |
+
"eval_runtime": 9.7021,
|
| 480 |
+
"eval_samples_per_second": 5.154,
|
| 481 |
+
"eval_steps_per_second": 1.34,
|
| 482 |
+
"step": 55
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.0,
|
| 486 |
+
"grad_norm": 0.018656069412827492,
|
| 487 |
+
"learning_rate": 7.891661680839932e-05,
|
| 488 |
+
"loss": 0.0133,
|
| 489 |
+
"step": 56
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.0357142857142856,
|
| 493 |
+
"grad_norm": 0.012934373691678047,
|
| 494 |
+
"learning_rate": 7.795964517353735e-05,
|
| 495 |
+
"loss": 0.0108,
|
| 496 |
+
"step": 57
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.0714285714285716,
|
| 500 |
+
"grad_norm": 0.013511372730135918,
|
| 501 |
+
"learning_rate": 7.698753289757565e-05,
|
| 502 |
+
"loss": 0.0104,
|
| 503 |
+
"step": 58
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.107142857142857,
|
| 507 |
+
"grad_norm": 0.018246950581669807,
|
| 508 |
+
"learning_rate": 7.600080639646077e-05,
|
| 509 |
+
"loss": 0.0118,
|
| 510 |
+
"step": 59
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 2.142857142857143,
|
| 514 |
+
"grad_norm": 0.014242120087146759,
|
| 515 |
+
"learning_rate": 7.500000000000001e-05,
|
| 516 |
+
"loss": 0.0123,
|
| 517 |
+
"step": 60
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.142857142857143,
|
| 521 |
+
"eval_loss": 0.01509407814592123,
|
| 522 |
+
"eval_runtime": 9.7051,
|
| 523 |
+
"eval_samples_per_second": 5.152,
|
| 524 |
+
"eval_steps_per_second": 1.339,
|
| 525 |
+
"step": 60
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.1785714285714284,
|
| 529 |
+
"grad_norm": 0.01346555631607771,
|
| 530 |
+
"learning_rate": 7.398565566251232e-05,
|
| 531 |
+
"loss": 0.0093,
|
| 532 |
+
"step": 61
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.2142857142857144,
|
| 536 |
+
"grad_norm": 0.01607862487435341,
|
| 537 |
+
"learning_rate": 7.295832266935059e-05,
|
| 538 |
+
"loss": 0.0104,
|
| 539 |
+
"step": 62
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.25,
|
| 543 |
+
"grad_norm": 0.018394531682133675,
|
| 544 |
+
"learning_rate": 7.191855733945387e-05,
|
| 545 |
+
"loss": 0.0126,
|
| 546 |
+
"step": 63
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.2857142857142856,
|
| 550 |
+
"grad_norm": 0.0137100238353014,
|
| 551 |
+
"learning_rate": 7.08669227240909e-05,
|
| 552 |
+
"loss": 0.0112,
|
| 553 |
+
"step": 64
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.3214285714285716,
|
| 557 |
+
"grad_norm": 0.015522747300565243,
|
| 558 |
+
"learning_rate": 6.980398830195785e-05,
|
| 559 |
+
"loss": 0.0105,
|
| 560 |
+
"step": 65
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.3214285714285716,
|
| 564 |
+
"eval_loss": 0.014879303053021431,
|
| 565 |
+
"eval_runtime": 9.7097,
|
| 566 |
+
"eval_samples_per_second": 5.15,
|
| 567 |
+
"eval_steps_per_second": 1.339,
|
| 568 |
+
"step": 65
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.357142857142857,
|
| 572 |
+
"grad_norm": 0.01642751693725586,
|
| 573 |
+
"learning_rate": 6.873032967079561e-05,
|
| 574 |
+
"loss": 0.0092,
|
| 575 |
+
"step": 66
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.392857142857143,
|
| 579 |
+
"grad_norm": 0.02026839181780815,
|
| 580 |
+
"learning_rate": 6.764652823569344e-05,
|
| 581 |
+
"loss": 0.0112,
|
| 582 |
+
"step": 67
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.4285714285714284,
|
| 586 |
+
"grad_norm": 0.018269985914230347,
|
| 587 |
+
"learning_rate": 6.65531708942479e-05,
|
| 588 |
+
"loss": 0.0104,
|
| 589 |
+
"step": 68
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 2.4642857142857144,
|
| 593 |
+
"grad_norm": 0.01534950640052557,
|
| 594 |
+
"learning_rate": 6.545084971874738e-05,
|
| 595 |
+
"loss": 0.0103,
|
| 596 |
+
"step": 69
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.5,
|
| 600 |
+
"grad_norm": 0.016070786863565445,
|
| 601 |
+
"learning_rate": 6.434016163555452e-05,
|
| 602 |
+
"loss": 0.0103,
|
| 603 |
+
"step": 70
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.5,
|
| 607 |
+
"eval_loss": 0.014439661055803299,
|
| 608 |
+
"eval_runtime": 9.7065,
|
| 609 |
+
"eval_samples_per_second": 5.151,
|
| 610 |
+
"eval_steps_per_second": 1.339,
|
| 611 |
+
"step": 70
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.5357142857142856,
|
| 615 |
+
"grad_norm": 0.016268271952867508,
|
| 616 |
+
"learning_rate": 6.322170810186012e-05,
|
| 617 |
+
"loss": 0.0094,
|
| 618 |
+
"step": 71
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.571428571428571,
|
| 622 |
+
"grad_norm": 0.017330510541796684,
|
| 623 |
+
"learning_rate": 6.209609477998338e-05,
|
| 624 |
+
"loss": 0.0104,
|
| 625 |
+
"step": 72
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.607142857142857,
|
| 629 |
+
"grad_norm": 0.015134909190237522,
|
| 630 |
+
"learning_rate": 6.096393120939516e-05,
|
| 631 |
+
"loss": 0.0099,
|
| 632 |
+
"step": 73
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.642857142857143,
|
| 636 |
+
"grad_norm": 0.01841241866350174,
|
| 637 |
+
"learning_rate": 5.982583047664151e-05,
|
| 638 |
+
"loss": 0.0122,
|
| 639 |
+
"step": 74
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.678571428571429,
|
| 643 |
+
"grad_norm": 0.014500053599476814,
|
| 644 |
+
"learning_rate": 5.868240888334653e-05,
|
| 645 |
+
"loss": 0.0097,
|
| 646 |
+
"step": 75
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.678571428571429,
|
| 650 |
+
"eval_loss": 0.013924479484558105,
|
| 651 |
+
"eval_runtime": 9.7024,
|
| 652 |
+
"eval_samples_per_second": 5.153,
|
| 653 |
+
"eval_steps_per_second": 1.34,
|
| 654 |
+
"step": 75
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.7142857142857144,
|
| 658 |
+
"grad_norm": 0.014019549824297428,
|
| 659 |
+
"learning_rate": 5.753428561247416e-05,
|
| 660 |
+
"loss": 0.0093,
|
| 661 |
+
"step": 76
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 2.75,
|
| 665 |
+
"grad_norm": 0.01768059842288494,
|
| 666 |
+
"learning_rate": 5.6382082393029746e-05,
|
| 667 |
+
"loss": 0.0106,
|
| 668 |
+
"step": 77
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.7857142857142856,
|
| 672 |
+
"grad_norm": 0.017852406948804855,
|
| 673 |
+
"learning_rate": 5.522642316338268e-05,
|
| 674 |
+
"loss": 0.011,
|
| 675 |
+
"step": 78
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.821428571428571,
|
| 679 |
+
"grad_norm": 0.015101013705134392,
|
| 680 |
+
"learning_rate": 5.4067933733392915e-05,
|
| 681 |
+
"loss": 0.0102,
|
| 682 |
+
"step": 79
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.857142857142857,
|
| 686 |
+
"grad_norm": 0.018193189054727554,
|
| 687 |
+
"learning_rate": 5.290724144552379e-05,
|
| 688 |
+
"loss": 0.0113,
|
| 689 |
+
"step": 80
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 2.857142857142857,
|
| 693 |
+
"eval_loss": 0.013650600798428059,
|
| 694 |
+
"eval_runtime": 9.7114,
|
| 695 |
+
"eval_samples_per_second": 5.149,
|
| 696 |
+
"eval_steps_per_second": 1.339,
|
| 697 |
+
"step": 80
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.892857142857143,
|
| 701 |
+
"grad_norm": 0.014319472946226597,
|
| 702 |
+
"learning_rate": 5.174497483512506e-05,
|
| 703 |
+
"loss": 0.01,
|
| 704 |
+
"step": 81
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.928571428571429,
|
| 708 |
+
"grad_norm": 0.014334422536194324,
|
| 709 |
+
"learning_rate": 5.0581763290069865e-05,
|
| 710 |
+
"loss": 0.009,
|
| 711 |
+
"step": 82
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.9642857142857144,
|
| 715 |
+
"grad_norm": 0.014601991511881351,
|
| 716 |
+
"learning_rate": 4.941823670993016e-05,
|
| 717 |
+
"loss": 0.0094,
|
| 718 |
+
"step": 83
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 3.0,
|
| 722 |
+
"grad_norm": 0.016180802136659622,
|
| 723 |
+
"learning_rate": 4.825502516487497e-05,
|
| 724 |
+
"loss": 0.0099,
|
| 725 |
+
"step": 84
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 3.0357142857142856,
|
| 729 |
+
"grad_norm": 0.01579074002802372,
|
| 730 |
+
"learning_rate": 4.709275855447621e-05,
|
| 731 |
+
"loss": 0.0075,
|
| 732 |
+
"step": 85
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 3.0357142857142856,
|
| 736 |
+
"eval_loss": 0.013672297820448875,
|
| 737 |
+
"eval_runtime": 9.7098,
|
| 738 |
+
"eval_samples_per_second": 5.149,
|
| 739 |
+
"eval_steps_per_second": 1.339,
|
| 740 |
+
"step": 85
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 3.0714285714285716,
|
| 744 |
+
"grad_norm": 0.015207303687930107,
|
| 745 |
+
"learning_rate": 4.593206626660709e-05,
|
| 746 |
+
"loss": 0.0086,
|
| 747 |
+
"step": 86
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 3.107142857142857,
|
| 751 |
+
"grad_norm": 0.015469847247004509,
|
| 752 |
+
"learning_rate": 4.477357683661734e-05,
|
| 753 |
+
"loss": 0.0102,
|
| 754 |
+
"step": 87
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 3.142857142857143,
|
| 758 |
+
"grad_norm": 0.014714378863573074,
|
| 759 |
+
"learning_rate": 4.361791760697027e-05,
|
| 760 |
+
"loss": 0.0075,
|
| 761 |
+
"step": 88
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 3.1785714285714284,
|
| 765 |
+
"grad_norm": 0.01793627254664898,
|
| 766 |
+
"learning_rate": 4.246571438752585e-05,
|
| 767 |
+
"loss": 0.0084,
|
| 768 |
+
"step": 89
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.2142857142857144,
|
| 772 |
+
"grad_norm": 0.018511932343244553,
|
| 773 |
+
"learning_rate": 4.131759111665349e-05,
|
| 774 |
+
"loss": 0.0084,
|
| 775 |
+
"step": 90
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.2142857142857144,
|
| 779 |
+
"eval_loss": 0.013722319155931473,
|
| 780 |
+
"eval_runtime": 9.7113,
|
| 781 |
+
"eval_samples_per_second": 5.149,
|
| 782 |
+
"eval_steps_per_second": 1.339,
|
| 783 |
+
"step": 90
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.25,
|
| 787 |
+
"grad_norm": 0.017314689233899117,
|
| 788 |
+
"learning_rate": 4.017416952335849e-05,
|
| 789 |
+
"loss": 0.0072,
|
| 790 |
+
"step": 91
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 3.2857142857142856,
|
| 794 |
+
"grad_norm": 0.019009340554475784,
|
| 795 |
+
"learning_rate": 3.903606879060483e-05,
|
| 796 |
+
"loss": 0.0091,
|
| 797 |
+
"step": 92
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 3.3214285714285716,
|
| 801 |
+
"grad_norm": 0.021889163181185722,
|
| 802 |
+
"learning_rate": 3.790390522001662e-05,
|
| 803 |
+
"loss": 0.0084,
|
| 804 |
+
"step": 93
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.357142857142857,
|
| 808 |
+
"grad_norm": 0.024208620190620422,
|
| 809 |
+
"learning_rate": 3.67782918981399e-05,
|
| 810 |
+
"loss": 0.0082,
|
| 811 |
+
"step": 94
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 3.392857142857143,
|
| 815 |
+
"grad_norm": 0.020253879949450493,
|
| 816 |
+
"learning_rate": 3.5659838364445505e-05,
|
| 817 |
+
"loss": 0.0074,
|
| 818 |
+
"step": 95
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.392857142857143,
|
| 822 |
+
"eval_loss": 0.01360101904720068,
|
| 823 |
+
"eval_runtime": 9.7063,
|
| 824 |
+
"eval_samples_per_second": 5.151,
|
| 825 |
+
"eval_steps_per_second": 1.339,
|
| 826 |
+
"step": 95
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 3.4285714285714284,
|
| 830 |
+
"grad_norm": 0.0191811490803957,
|
| 831 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 832 |
+
"loss": 0.0068,
|
| 833 |
+
"step": 96
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.4642857142857144,
|
| 837 |
+
"grad_norm": 0.02651781029999256,
|
| 838 |
+
"learning_rate": 3.34468291057521e-05,
|
| 839 |
+
"loss": 0.0079,
|
| 840 |
+
"step": 97
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.5,
|
| 844 |
+
"grad_norm": 0.019155073910951614,
|
| 845 |
+
"learning_rate": 3.235347176430656e-05,
|
| 846 |
+
"loss": 0.0086,
|
| 847 |
+
"step": 98
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 3.5357142857142856,
|
| 851 |
+
"grad_norm": 0.01815451681613922,
|
| 852 |
+
"learning_rate": 3.12696703292044e-05,
|
| 853 |
+
"loss": 0.0087,
|
| 854 |
+
"step": 99
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.571428571428571,
|
| 858 |
+
"grad_norm": 0.019341563805937767,
|
| 859 |
+
"learning_rate": 3.019601169804216e-05,
|
| 860 |
+
"loss": 0.0079,
|
| 861 |
+
"step": 100
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 3.571428571428571,
|
| 865 |
+
"eval_loss": 0.013337756507098675,
|
| 866 |
+
"eval_runtime": 9.7213,
|
| 867 |
+
"eval_samples_per_second": 5.143,
|
| 868 |
+
"eval_steps_per_second": 1.337,
|
| 869 |
+
"step": 100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.607142857142857,
|
| 873 |
+
"grad_norm": 0.016623245552182198,
|
| 874 |
+
"learning_rate": 2.9133077275909108e-05,
|
| 875 |
+
"loss": 0.0074,
|
| 876 |
+
"step": 101
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.642857142857143,
|
| 880 |
+
"grad_norm": 0.019026493653655052,
|
| 881 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 882 |
+
"loss": 0.009,
|
| 883 |
+
"step": 102
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 3.678571428571429,
|
| 887 |
+
"grad_norm": 0.016850460320711136,
|
| 888 |
+
"learning_rate": 2.7041677330649407e-05,
|
| 889 |
+
"loss": 0.0082,
|
| 890 |
+
"step": 103
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.7142857142857144,
|
| 894 |
+
"grad_norm": 0.017526159062981606,
|
| 895 |
+
"learning_rate": 2.6014344337487707e-05,
|
| 896 |
+
"loss": 0.0089,
|
| 897 |
+
"step": 104
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 3.75,
|
| 901 |
+
"grad_norm": 0.015158770605921745,
|
| 902 |
+
"learning_rate": 2.500000000000001e-05,
|
| 903 |
+
"loss": 0.0078,
|
| 904 |
+
"step": 105
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 3.75,
|
| 908 |
+
"eval_loss": 0.013194898143410683,
|
| 909 |
+
"eval_runtime": 9.7156,
|
| 910 |
+
"eval_samples_per_second": 5.146,
|
| 911 |
+
"eval_steps_per_second": 1.338,
|
| 912 |
+
"step": 105
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 3.7857142857142856,
|
| 916 |
+
"grad_norm": 0.017768317833542824,
|
| 917 |
+
"learning_rate": 2.399919360353923e-05,
|
| 918 |
+
"loss": 0.0075,
|
| 919 |
+
"step": 106
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.821428571428571,
|
| 923 |
+
"grad_norm": 0.01880650967359543,
|
| 924 |
+
"learning_rate": 2.3012467102424373e-05,
|
| 925 |
+
"loss": 0.0095,
|
| 926 |
+
"step": 107
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.857142857142857,
|
| 930 |
+
"grad_norm": 0.016439756378531456,
|
| 931 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 932 |
+
"loss": 0.0069,
|
| 933 |
+
"step": 108
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 3.892857142857143,
|
| 937 |
+
"grad_norm": 0.0158089566975832,
|
| 938 |
+
"learning_rate": 2.1083383191600674e-05,
|
| 939 |
+
"loss": 0.0086,
|
| 940 |
+
"step": 109
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 3.928571428571429,
|
| 944 |
+
"grad_norm": 0.0163241196423769,
|
| 945 |
+
"learning_rate": 2.0142070414860704e-05,
|
| 946 |
+
"loss": 0.0084,
|
| 947 |
+
"step": 110
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 3.928571428571429,
|
| 951 |
+
"eval_loss": 0.013033830560743809,
|
| 952 |
+
"eval_runtime": 9.7137,
|
| 953 |
+
"eval_samples_per_second": 5.147,
|
| 954 |
+
"eval_steps_per_second": 1.338,
|
| 955 |
+
"step": 110
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 3.9642857142857144,
|
| 959 |
+
"grad_norm": 0.016290636733174324,
|
| 960 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 961 |
+
"loss": 0.0072,
|
| 962 |
+
"step": 111
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 4.0,
|
| 966 |
+
"grad_norm": 0.019113833084702492,
|
| 967 |
+
"learning_rate": 1.8308451630064484e-05,
|
| 968 |
+
"loss": 0.0079,
|
| 969 |
+
"step": 112
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.035714285714286,
|
| 973 |
+
"grad_norm": 0.016058726236224174,
|
| 974 |
+
"learning_rate": 1.7417138558927244e-05,
|
| 975 |
+
"loss": 0.0067,
|
| 976 |
+
"step": 113
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 4.071428571428571,
|
| 980 |
+
"grad_norm": 0.015682850033044815,
|
| 981 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 982 |
+
"loss": 0.0069,
|
| 983 |
+
"step": 114
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 4.107142857142857,
|
| 987 |
+
"grad_norm": 0.014876119792461395,
|
| 988 |
+
"learning_rate": 1.5687918106563326e-05,
|
| 989 |
+
"loss": 0.0081,
|
| 990 |
+
"step": 115
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.107142857142857,
|
| 994 |
+
"eval_loss": 0.012972795404493809,
|
| 995 |
+
"eval_runtime": 9.7061,
|
| 996 |
+
"eval_samples_per_second": 5.151,
|
| 997 |
+
"eval_steps_per_second": 1.339,
|
| 998 |
+
"step": 115
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 4.142857142857143,
|
| 1002 |
+
"grad_norm": 0.01374531164765358,
|
| 1003 |
+
"learning_rate": 1.4850947128716913e-05,
|
| 1004 |
+
"loss": 0.0064,
|
| 1005 |
+
"step": 116
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.178571428571429,
|
| 1009 |
+
"grad_norm": 0.01570560783147812,
|
| 1010 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1011 |
+
"loss": 0.0066,
|
| 1012 |
+
"step": 117
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 4.214285714285714,
|
| 1016 |
+
"grad_norm": 0.01956205815076828,
|
| 1017 |
+
"learning_rate": 1.3234549597008571e-05,
|
| 1018 |
+
"loss": 0.0071,
|
| 1019 |
+
"step": 118
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 4.25,
|
| 1023 |
+
"grad_norm": 0.014442876912653446,
|
| 1024 |
+
"learning_rate": 1.245599835092504e-05,
|
| 1025 |
+
"loss": 0.0063,
|
| 1026 |
+
"step": 119
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 4.285714285714286,
|
| 1030 |
+
"grad_norm": 0.01939442940056324,
|
| 1031 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1032 |
+
"loss": 0.007,
|
| 1033 |
+
"step": 120
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.285714285714286,
|
| 1037 |
+
"eval_loss": 0.013091979548335075,
|
| 1038 |
+
"eval_runtime": 9.7151,
|
| 1039 |
+
"eval_samples_per_second": 5.147,
|
| 1040 |
+
"eval_steps_per_second": 1.338,
|
| 1041 |
+
"step": 120
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 4.321428571428571,
|
| 1045 |
+
"grad_norm": 0.017249030992388725,
|
| 1046 |
+
"learning_rate": 1.096029866616704e-05,
|
| 1047 |
+
"loss": 0.0058,
|
| 1048 |
+
"step": 121
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 4.357142857142857,
|
| 1052 |
+
"grad_norm": 0.016970176249742508,
|
| 1053 |
+
"learning_rate": 1.0243960175257606e-05,
|
| 1054 |
+
"loss": 0.0069,
|
| 1055 |
+
"step": 122
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 4.392857142857143,
|
| 1059 |
+
"grad_norm": 0.016214648261666298,
|
| 1060 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1061 |
+
"loss": 0.0087,
|
| 1062 |
+
"step": 123
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 4.428571428571429,
|
| 1066 |
+
"grad_norm": 0.014185045845806599,
|
| 1067 |
+
"learning_rate": 8.876245235966885e-06,
|
| 1068 |
+
"loss": 0.0061,
|
| 1069 |
+
"step": 124
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 4.464285714285714,
|
| 1073 |
+
"grad_norm": 0.018804052844643593,
|
| 1074 |
+
"learning_rate": 8.225609429353187e-06,
|
| 1075 |
+
"loss": 0.0068,
|
| 1076 |
+
"step": 125
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 4.464285714285714,
|
| 1080 |
+
"eval_loss": 0.013120167888700962,
|
| 1081 |
+
"eval_runtime": 9.7397,
|
| 1082 |
+
"eval_samples_per_second": 5.134,
|
| 1083 |
+
"eval_steps_per_second": 1.335,
|
| 1084 |
+
"step": 125
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 4.5,
|
| 1088 |
+
"grad_norm": 0.016952916979789734,
|
| 1089 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1090 |
+
"loss": 0.007,
|
| 1091 |
+
"step": 126
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 4.535714285714286,
|
| 1095 |
+
"grad_norm": 0.018581125885248184,
|
| 1096 |
+
"learning_rate": 6.992542605231739e-06,
|
| 1097 |
+
"loss": 0.0067,
|
| 1098 |
+
"step": 127
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 4.571428571428571,
|
| 1102 |
+
"grad_norm": 0.01575946994125843,
|
| 1103 |
+
"learning_rate": 6.410779315161886e-06,
|
| 1104 |
+
"loss": 0.0064,
|
| 1105 |
+
"step": 128
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 4.607142857142857,
|
| 1109 |
+
"grad_norm": 0.015804851427674294,
|
| 1110 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1111 |
+
"loss": 0.0057,
|
| 1112 |
+
"step": 129
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.642857142857143,
|
| 1116 |
+
"grad_norm": 0.016620276495814323,
|
| 1117 |
+
"learning_rate": 5.318367983829392e-06,
|
| 1118 |
+
"loss": 0.0069,
|
| 1119 |
+
"step": 130
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 4.642857142857143,
|
| 1123 |
+
"eval_loss": 0.01305928360670805,
|
| 1124 |
+
"eval_runtime": 9.7038,
|
| 1125 |
+
"eval_samples_per_second": 5.153,
|
| 1126 |
+
"eval_steps_per_second": 1.34,
|
| 1127 |
+
"step": 130
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 4.678571428571429,
|
| 1131 |
+
"grad_norm": 0.016047867015004158,
|
| 1132 |
+
"learning_rate": 4.8083115025739756e-06,
|
| 1133 |
+
"loss": 0.0064,
|
| 1134 |
+
"step": 131
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 4.714285714285714,
|
| 1138 |
+
"grad_norm": 0.017862636595964432,
|
| 1139 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1140 |
+
"loss": 0.0056,
|
| 1141 |
+
"step": 132
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 4.75,
|
| 1145 |
+
"grad_norm": 0.01711735874414444,
|
| 1146 |
+
"learning_rate": 3.861877782227885e-06,
|
| 1147 |
+
"loss": 0.0067,
|
| 1148 |
+
"step": 133
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.785714285714286,
|
| 1152 |
+
"grad_norm": 0.017451371997594833,
|
| 1153 |
+
"learning_rate": 3.426013053692878e-06,
|
| 1154 |
+
"loss": 0.0064,
|
| 1155 |
+
"step": 134
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 4.821428571428571,
|
| 1159 |
+
"grad_norm": 0.016627250239253044,
|
| 1160 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1161 |
+
"loss": 0.0066,
|
| 1162 |
+
"step": 135
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 4.821428571428571,
|
| 1166 |
+
"eval_loss": 0.012971566058695316,
|
| 1167 |
+
"eval_runtime": 9.7115,
|
| 1168 |
+
"eval_samples_per_second": 5.149,
|
| 1169 |
+
"eval_steps_per_second": 1.339,
|
| 1170 |
+
"step": 135
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 4.857142857142857,
|
| 1174 |
+
"grad_norm": 0.01802762597799301,
|
| 1175 |
+
"learning_rate": 2.63016787428354e-06,
|
| 1176 |
+
"loss": 0.0059,
|
| 1177 |
+
"step": 136
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 4.892857142857143,
|
| 1181 |
+
"grad_norm": 0.014754877425730228,
|
| 1182 |
+
"learning_rate": 2.2706183876134045e-06,
|
| 1183 |
+
"loss": 0.0063,
|
| 1184 |
+
"step": 137
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.928571428571429,
|
| 1188 |
+
"grad_norm": 0.0169619619846344,
|
| 1189 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1190 |
+
"loss": 0.0063,
|
| 1191 |
+
"step": 138
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 4.964285714285714,
|
| 1195 |
+
"grad_norm": 0.016004588454961777,
|
| 1196 |
+
"learning_rate": 1.6292390268568104e-06,
|
| 1197 |
+
"loss": 0.0064,
|
| 1198 |
+
"step": 139
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 5.0,
|
| 1202 |
+
"grad_norm": 0.014701365493237972,
|
| 1203 |
+
"learning_rate": 1.3477564710088098e-06,
|
| 1204 |
+
"loss": 0.0057,
|
| 1205 |
+
"step": 140
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 5.0,
|
| 1209 |
+
"eval_loss": 0.012948555871844292,
|
| 1210 |
+
"eval_runtime": 9.7173,
|
| 1211 |
+
"eval_samples_per_second": 5.145,
|
| 1212 |
+
"eval_steps_per_second": 1.338,
|
| 1213 |
+
"step": 140
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 5.035714285714286,
|
| 1217 |
+
"grad_norm": 0.013614133931696415,
|
| 1218 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1219 |
+
"loss": 0.0067,
|
| 1220 |
+
"step": 141
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 5.071428571428571,
|
| 1224 |
+
"grad_norm": 0.013580002821981907,
|
| 1225 |
+
"learning_rate": 8.639676646793382e-07,
|
| 1226 |
+
"loss": 0.0064,
|
| 1227 |
+
"step": 142
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 5.107142857142857,
|
| 1231 |
+
"grad_norm": 0.014799501746892929,
|
| 1232 |
+
"learning_rate": 6.61923394371039e-07,
|
| 1233 |
+
"loss": 0.0061,
|
| 1234 |
+
"step": 143
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 5.142857142857143,
|
| 1238 |
+
"grad_norm": 0.0145066874101758,
|
| 1239 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1240 |
+
"loss": 0.0061,
|
| 1241 |
+
"step": 144
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 5.178571428571429,
|
| 1245 |
+
"grad_norm": 0.01296368706971407,
|
| 1246 |
+
"learning_rate": 3.380821129028489e-07,
|
| 1247 |
+
"loss": 0.0057,
|
| 1248 |
+
"step": 145
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 5.178571428571429,
|
| 1252 |
+
"eval_loss": 0.012967634946107864,
|
| 1253 |
+
"eval_runtime": 9.7053,
|
| 1254 |
+
"eval_samples_per_second": 5.152,
|
| 1255 |
+
"eval_steps_per_second": 1.339,
|
| 1256 |
+
"step": 145
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 5.214285714285714,
|
| 1260 |
+
"grad_norm": 0.015401339158415794,
|
| 1261 |
+
"learning_rate": 2.1646046750978254e-07,
|
| 1262 |
+
"loss": 0.0074,
|
| 1263 |
+
"step": 146
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 5.25,
|
| 1267 |
+
"grad_norm": 0.01774049550294876,
|
| 1268 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1269 |
+
"loss": 0.007,
|
| 1270 |
+
"step": 147
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 5.285714285714286,
|
| 1274 |
+
"grad_norm": 0.014818909578025341,
|
| 1275 |
+
"learning_rate": 5.4144433073771707e-08,
|
| 1276 |
+
"loss": 0.0064,
|
| 1277 |
+
"step": 148
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 5.321428571428571,
|
| 1281 |
+
"grad_norm": 0.013709980994462967,
|
| 1282 |
+
"learning_rate": 1.3537941026914303e-08,
|
| 1283 |
+
"loss": 0.005,
|
| 1284 |
+
"step": 149
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 5.357142857142857,
|
| 1288 |
+
"grad_norm": 0.016515277326107025,
|
| 1289 |
+
"learning_rate": 0.0,
|
| 1290 |
+
"loss": 0.0057,
|
| 1291 |
+
"step": 150
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 5.357142857142857,
|
| 1295 |
+
"eval_loss": 0.012949441559612751,
|
| 1296 |
+
"eval_runtime": 9.7697,
|
| 1297 |
+
"eval_samples_per_second": 5.118,
|
| 1298 |
+
"eval_steps_per_second": 1.331,
|
| 1299 |
+
"step": 150
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 5.357142857142857,
|
| 1303 |
+
"step": 150,
|
| 1304 |
+
"total_flos": 3.292901739866358e+17,
|
| 1305 |
+
"train_loss": 0.013509833477437496,
|
| 1306 |
+
"train_runtime": 2826.4869,
|
| 1307 |
+
"train_samples_per_second": 1.698,
|
| 1308 |
+
"train_steps_per_second": 0.053
|
| 1309 |
+
}
|
| 1310 |
+
],
|
| 1311 |
+
"logging_steps": 1,
|
| 1312 |
+
"max_steps": 150,
|
| 1313 |
+
"num_input_tokens_seen": 0,
|
| 1314 |
+
"num_train_epochs": 6,
|
| 1315 |
+
"save_steps": 50,
|
| 1316 |
+
"stateful_callbacks": {
|
| 1317 |
+
"TrainerControl": {
|
| 1318 |
+
"args": {
|
| 1319 |
+
"should_epoch_stop": false,
|
| 1320 |
+
"should_evaluate": false,
|
| 1321 |
+
"should_log": false,
|
| 1322 |
+
"should_save": true,
|
| 1323 |
+
"should_training_stop": true
|
| 1324 |
+
},
|
| 1325 |
+
"attributes": {}
|
| 1326 |
+
}
|
| 1327 |
+
},
|
| 1328 |
+
"total_flos": 3.292901739866358e+17,
|
| 1329 |
+
"train_batch_size": 4,
|
| 1330 |
+
"trial_name": null,
|
| 1331 |
+
"trial_params": null
|
| 1332 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54183cc334c5d9197816bbb5d1df3aa0089c0bd6caa69f177ce11f19a439faf4
|
| 3 |
+
size 5432
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|