Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +5 -0
- .ipynb_checkpoints/README-checkpoint.md +217 -0
- README.md +217 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- checkpoint-540/README.md +202 -0
- checkpoint-540/adapter_config.json +39 -0
- checkpoint-540/adapter_model.safetensors +3 -0
- checkpoint-540/global_step540/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-540/global_step540/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-540/global_step540/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-540/global_step540/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-540/global_step540/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- checkpoint-540/global_step540/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- checkpoint-540/global_step540/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
- checkpoint-540/global_step540/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
- checkpoint-540/latest +1 -0
- checkpoint-540/rng_state_0.pth +3 -0
- checkpoint-540/rng_state_1.pth +3 -0
- checkpoint-540/rng_state_2.pth +3 -0
- checkpoint-540/rng_state_3.pth +3 -0
- checkpoint-540/scheduler.pt +3 -0
- checkpoint-540/special_tokens_map.json +23 -0
- checkpoint-540/tokenizer.json +3 -0
- checkpoint-540/tokenizer_config.json +2064 -0
- checkpoint-540/trainer_state.json +3966 -0
- checkpoint-540/training_args.bin +3 -0
- checkpoint-540/zero_to_fp32.py +760 -0
- checkpoint-600/README.md +202 -0
- checkpoint-600/adapter_config.json +39 -0
- checkpoint-600/adapter_model.safetensors +3 -0
- checkpoint-600/global_step600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-600/global_step600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- checkpoint-600/global_step600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- checkpoint-600/global_step600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- checkpoint-600/global_step600/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- checkpoint-600/global_step600/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
- checkpoint-600/global_step600/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
- checkpoint-600/global_step600/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
- checkpoint-600/latest +1 -0
- checkpoint-600/rng_state_0.pth +3 -0
- checkpoint-600/rng_state_1.pth +3 -0
- checkpoint-600/rng_state_2.pth +3 -0
- checkpoint-600/rng_state_3.pth +3 -0
- checkpoint-600/scheduler.pt +3 -0
- checkpoint-600/special_tokens_map.json +23 -0
- checkpoint-600/tokenizer.json +3 -0
- checkpoint-600/tokenizer_config.json +2064 -0
- checkpoint-600/trainer_state.json +0 -0
- checkpoint-600/training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,8 @@ 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 |
+
checkpoint-540/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-660/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!--
|
| 2 |
+
---
|
| 3 |
+
library_name: peft
|
| 4 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- ./t.json
|
| 10 |
+
- PocketDoc/Dans-Prosemaxx-Adventure
|
| 11 |
+
- PocketDoc/Dans-Failuremaxx-Adventure-3
|
| 12 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
|
| 13 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
|
| 14 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
|
| 15 |
+
- PocketDoc/Dans-Prosemaxx-Instructwriter-Long
|
| 16 |
+
- PocketDoc/Dans-Personamaxx-VN
|
| 17 |
+
model-index:
|
| 18 |
+
- name: Hamanasu-4B-Adventure-V2
|
| 19 |
+
results: []
|
| 20 |
+
---
|
| 21 |
+
-->
|
| 22 |
+
|
| 23 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 24 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 25 |
+
|
| 26 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 27 |
+
<details><summary>See axolotl config</summary>
|
| 28 |
+
|
| 29 |
+
axolotl version: `0.8.0.dev0`
|
| 30 |
+
```yaml
|
| 31 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 32 |
+
model_type: AutoModelForCausalLM
|
| 33 |
+
tokenizer_type: AutoTokenizer
|
| 34 |
+
|
| 35 |
+
hub_model_id: NewEden/Hamanasu-4B-Adventure-V2
|
| 36 |
+
hub_strategy: "end"
|
| 37 |
+
push_dataset_to_hub:
|
| 38 |
+
hf_use_auth_token: true
|
| 39 |
+
|
| 40 |
+
plugins:
|
| 41 |
+
- axolotl.integrations.liger.LigerPlugin
|
| 42 |
+
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
| 43 |
+
liger_rope: true
|
| 44 |
+
liger_rms_norm: true
|
| 45 |
+
liger_layer_norm: true
|
| 46 |
+
liger_glu_activation: true
|
| 47 |
+
liger_fused_linear_cross_entropy: false
|
| 48 |
+
cut_cross_entropy: true
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
load_in_8bit: false
|
| 52 |
+
load_in_4bit: false
|
| 53 |
+
strict: false
|
| 54 |
+
|
| 55 |
+
datasets:
|
| 56 |
+
- path: ./t.json
|
| 57 |
+
type: dan-chat-advanced
|
| 58 |
+
- path: PocketDoc/Dans-Prosemaxx-Adventure
|
| 59 |
+
type: dan-chat-advanced
|
| 60 |
+
- path: PocketDoc/Dans-Failuremaxx-Adventure-3
|
| 61 |
+
type: dan-chat-advanced
|
| 62 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
|
| 63 |
+
type: dan-chat-advanced
|
| 64 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
|
| 65 |
+
type: dan-chat-advanced
|
| 66 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
|
| 67 |
+
type: dan-chat-advanced
|
| 68 |
+
- path: PocketDoc/Dans-Prosemaxx-Instructwriter-Long
|
| 69 |
+
type: dan-chat-advanced
|
| 70 |
+
- path: PocketDoc/Dans-Personamaxx-VN
|
| 71 |
+
type: dan-chat-advanced
|
| 72 |
+
shuffle_merged_datasets: true
|
| 73 |
+
dataset_prepared_path: prepared_data
|
| 74 |
+
val_set_size: 0.01
|
| 75 |
+
output_dir: ./adventure-2
|
| 76 |
+
|
| 77 |
+
sequence_len: 32768
|
| 78 |
+
sample_packing: true
|
| 79 |
+
pad_to_sequence_len: true
|
| 80 |
+
eval_sample_packing: False
|
| 81 |
+
|
| 82 |
+
adapter: lora
|
| 83 |
+
lora_model_dir:
|
| 84 |
+
lora_r: 128
|
| 85 |
+
lora_alpha: 16
|
| 86 |
+
lora_dropout: 0.05
|
| 87 |
+
peft_use_rslora: true
|
| 88 |
+
lora_target_modules:
|
| 89 |
+
- gate_proj
|
| 90 |
+
- down_proj
|
| 91 |
+
- up_proj
|
| 92 |
+
- q_proj
|
| 93 |
+
- v_proj
|
| 94 |
+
- k_proj
|
| 95 |
+
- o_proj
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
wandb_project: tavbussy
|
| 99 |
+
wandb_entity:
|
| 100 |
+
wandb_watch:
|
| 101 |
+
wandb_name: adventure-attempt-v2
|
| 102 |
+
wandb_log_model:
|
| 103 |
+
|
| 104 |
+
gradient_accumulation_steps: 2
|
| 105 |
+
micro_batch_size: 4
|
| 106 |
+
num_epochs: 6
|
| 107 |
+
optimizer: adamw_bnb_8bit
|
| 108 |
+
lr_scheduler: cosine
|
| 109 |
+
learning_rate: 3e-5
|
| 110 |
+
max_grad_norm: 0.2
|
| 111 |
+
|
| 112 |
+
train_on_inputs: false
|
| 113 |
+
group_by_length: false
|
| 114 |
+
bf16: auto
|
| 115 |
+
fp16:
|
| 116 |
+
tf32: false
|
| 117 |
+
|
| 118 |
+
gradient_checkpointing: true
|
| 119 |
+
early_stopping_patience:
|
| 120 |
+
resume_from_checkpoint:
|
| 121 |
+
local_rank:
|
| 122 |
+
logging_steps: 1
|
| 123 |
+
xformers_attention:
|
| 124 |
+
flash_attention: true
|
| 125 |
+
|
| 126 |
+
warmup_steps: 35
|
| 127 |
+
evals_per_epoch: 4
|
| 128 |
+
eval_table_size:
|
| 129 |
+
eval_max_new_tokens: 128
|
| 130 |
+
saves_per_epoch: 2
|
| 131 |
+
debug:
|
| 132 |
+
deepspeed: ./deepspeed_configs/zero3_bf16.json
|
| 133 |
+
weight_decay: 0.03
|
| 134 |
+
fsdp:
|
| 135 |
+
fsdp_config:
|
| 136 |
+
special_tokens:
|
| 137 |
+
pad_token: <|finetune_right_pad_id|>
|
| 138 |
+
|
| 139 |
+
```
|
| 140 |
+
|
| 141 |
+
</details><br>
|
| 142 |
+
|
| 143 |
+
# Hamanasu-4B-Adventure-V2
|
| 144 |
+
|
| 145 |
+
This model is a fine-tuned version of [NewEden/Hamanasu-KTO-V2](https://huggingface.co/NewEden/Hamanasu-KTO-V2) on the ./t.json, the PocketDoc/Dans-Prosemaxx-Adventure, the PocketDoc/Dans-Failuremaxx-Adventure-3, the PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2, the PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3, the PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2, the PocketDoc/Dans-Prosemaxx-Instructwriter-Long and the PocketDoc/Dans-Personamaxx-VN datasets.
|
| 146 |
+
It achieves the following results on the evaluation set:
|
| 147 |
+
- Loss: 2.3770
|
| 148 |
+
|
| 149 |
+
## Model description
|
| 150 |
+
|
| 151 |
+
More information needed
|
| 152 |
+
|
| 153 |
+
## Intended uses & limitations
|
| 154 |
+
|
| 155 |
+
More information needed
|
| 156 |
+
|
| 157 |
+
## Training and evaluation data
|
| 158 |
+
|
| 159 |
+
More information needed
|
| 160 |
+
|
| 161 |
+
## Training procedure
|
| 162 |
+
|
| 163 |
+
### Training hyperparameters
|
| 164 |
+
|
| 165 |
+
The following hyperparameters were used during training:
|
| 166 |
+
- learning_rate: 3e-05
|
| 167 |
+
- train_batch_size: 4
|
| 168 |
+
- eval_batch_size: 4
|
| 169 |
+
- seed: 42
|
| 170 |
+
- distributed_type: multi-GPU
|
| 171 |
+
- num_devices: 4
|
| 172 |
+
- gradient_accumulation_steps: 2
|
| 173 |
+
- total_train_batch_size: 32
|
| 174 |
+
- total_eval_batch_size: 16
|
| 175 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 176 |
+
- lr_scheduler_type: cosine
|
| 177 |
+
- lr_scheduler_warmup_steps: 35
|
| 178 |
+
- num_epochs: 6.0
|
| 179 |
+
|
| 180 |
+
### Training results
|
| 181 |
+
|
| 182 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 183 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 184 |
+
| 2.5443 | 0.0083 | 1 | 2.5896 |
|
| 185 |
+
| 2.3222 | 0.25 | 30 | 2.4448 |
|
| 186 |
+
| 2.3768 | 0.5 | 60 | 2.4210 |
|
| 187 |
+
| 2.3336 | 0.75 | 90 | 2.4106 |
|
| 188 |
+
| 2.3595 | 1.0 | 120 | 2.4039 |
|
| 189 |
+
| 2.3078 | 1.25 | 150 | 2.3991 |
|
| 190 |
+
| 2.3111 | 1.5 | 180 | 2.3952 |
|
| 191 |
+
| 2.3331 | 1.75 | 210 | 2.3916 |
|
| 192 |
+
| 2.2758 | 2.0 | 240 | 2.3889 |
|
| 193 |
+
| 2.3227 | 2.25 | 270 | 2.3869 |
|
| 194 |
+
| 2.335 | 2.5 | 300 | 2.3851 |
|
| 195 |
+
| 2.349 | 2.75 | 330 | 2.3835 |
|
| 196 |
+
| 2.2828 | 3.0 | 360 | 2.3818 |
|
| 197 |
+
| 2.2632 | 3.25 | 390 | 2.3811 |
|
| 198 |
+
| 2.3254 | 3.5 | 420 | 2.3801 |
|
| 199 |
+
| 2.3073 | 3.75 | 450 | 2.3791 |
|
| 200 |
+
| 2.337 | 4.0 | 480 | 2.3783 |
|
| 201 |
+
| 2.2319 | 4.25 | 510 | 2.3782 |
|
| 202 |
+
| 2.3044 | 4.5 | 540 | 2.3778 |
|
| 203 |
+
| 2.2948 | 4.75 | 570 | 2.3773 |
|
| 204 |
+
| 2.2625 | 5.0 | 600 | 2.3771 |
|
| 205 |
+
| 2.3194 | 5.25 | 630 | 2.3771 |
|
| 206 |
+
| 2.2457 | 5.5 | 660 | 2.3771 |
|
| 207 |
+
| 2.2746 | 5.75 | 690 | 2.3769 |
|
| 208 |
+
| 2.2496 | 6.0 | 720 | 2.3770 |
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
### Framework versions
|
| 212 |
+
|
| 213 |
+
- PEFT 0.15.0
|
| 214 |
+
- Transformers 4.50.0
|
| 215 |
+
- Pytorch 2.5.1+cu124
|
| 216 |
+
- Datasets 3.5.0
|
| 217 |
+
- Tokenizers 0.21.1
|
README.md
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<!--
|
| 2 |
+
---
|
| 3 |
+
library_name: peft
|
| 4 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- ./t.json
|
| 10 |
+
- PocketDoc/Dans-Prosemaxx-Adventure
|
| 11 |
+
- PocketDoc/Dans-Failuremaxx-Adventure-3
|
| 12 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
|
| 13 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
|
| 14 |
+
- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
|
| 15 |
+
- PocketDoc/Dans-Prosemaxx-Instructwriter-Long
|
| 16 |
+
- PocketDoc/Dans-Personamaxx-VN
|
| 17 |
+
model-index:
|
| 18 |
+
- name: Hamanasu-4B-Adventure-V2
|
| 19 |
+
results: []
|
| 20 |
+
---
|
| 21 |
+
-->
|
| 22 |
+
|
| 23 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 24 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 25 |
+
|
| 26 |
+
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 27 |
+
<details><summary>See axolotl config</summary>
|
| 28 |
+
|
| 29 |
+
axolotl version: `0.8.0.dev0`
|
| 30 |
+
```yaml
|
| 31 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 32 |
+
model_type: AutoModelForCausalLM
|
| 33 |
+
tokenizer_type: AutoTokenizer
|
| 34 |
+
|
| 35 |
+
hub_model_id: NewEden/Hamanasu-4B-Adventure-V2
|
| 36 |
+
hub_strategy: "end"
|
| 37 |
+
push_dataset_to_hub:
|
| 38 |
+
hf_use_auth_token: true
|
| 39 |
+
|
| 40 |
+
plugins:
|
| 41 |
+
- axolotl.integrations.liger.LigerPlugin
|
| 42 |
+
- axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
|
| 43 |
+
liger_rope: true
|
| 44 |
+
liger_rms_norm: true
|
| 45 |
+
liger_layer_norm: true
|
| 46 |
+
liger_glu_activation: true
|
| 47 |
+
liger_fused_linear_cross_entropy: false
|
| 48 |
+
cut_cross_entropy: true
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
load_in_8bit: false
|
| 52 |
+
load_in_4bit: false
|
| 53 |
+
strict: false
|
| 54 |
+
|
| 55 |
+
datasets:
|
| 56 |
+
- path: ./t.json
|
| 57 |
+
type: dan-chat-advanced
|
| 58 |
+
- path: PocketDoc/Dans-Prosemaxx-Adventure
|
| 59 |
+
type: dan-chat-advanced
|
| 60 |
+
- path: PocketDoc/Dans-Failuremaxx-Adventure-3
|
| 61 |
+
type: dan-chat-advanced
|
| 62 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
|
| 63 |
+
type: dan-chat-advanced
|
| 64 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3
|
| 65 |
+
type: dan-chat-advanced
|
| 66 |
+
- path: PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
|
| 67 |
+
type: dan-chat-advanced
|
| 68 |
+
- path: PocketDoc/Dans-Prosemaxx-Instructwriter-Long
|
| 69 |
+
type: dan-chat-advanced
|
| 70 |
+
- path: PocketDoc/Dans-Personamaxx-VN
|
| 71 |
+
type: dan-chat-advanced
|
| 72 |
+
shuffle_merged_datasets: true
|
| 73 |
+
dataset_prepared_path: prepared_data
|
| 74 |
+
val_set_size: 0.01
|
| 75 |
+
output_dir: ./adventure-2
|
| 76 |
+
|
| 77 |
+
sequence_len: 32768
|
| 78 |
+
sample_packing: true
|
| 79 |
+
pad_to_sequence_len: true
|
| 80 |
+
eval_sample_packing: False
|
| 81 |
+
|
| 82 |
+
adapter: lora
|
| 83 |
+
lora_model_dir:
|
| 84 |
+
lora_r: 128
|
| 85 |
+
lora_alpha: 16
|
| 86 |
+
lora_dropout: 0.05
|
| 87 |
+
peft_use_rslora: true
|
| 88 |
+
lora_target_modules:
|
| 89 |
+
- gate_proj
|
| 90 |
+
- down_proj
|
| 91 |
+
- up_proj
|
| 92 |
+
- q_proj
|
| 93 |
+
- v_proj
|
| 94 |
+
- k_proj
|
| 95 |
+
- o_proj
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
wandb_project: tavbussy
|
| 99 |
+
wandb_entity:
|
| 100 |
+
wandb_watch:
|
| 101 |
+
wandb_name: adventure-attempt-v2
|
| 102 |
+
wandb_log_model:
|
| 103 |
+
|
| 104 |
+
gradient_accumulation_steps: 2
|
| 105 |
+
micro_batch_size: 4
|
| 106 |
+
num_epochs: 6
|
| 107 |
+
optimizer: adamw_bnb_8bit
|
| 108 |
+
lr_scheduler: cosine
|
| 109 |
+
learning_rate: 3e-5
|
| 110 |
+
max_grad_norm: 0.2
|
| 111 |
+
|
| 112 |
+
train_on_inputs: false
|
| 113 |
+
group_by_length: false
|
| 114 |
+
bf16: auto
|
| 115 |
+
fp16:
|
| 116 |
+
tf32: false
|
| 117 |
+
|
| 118 |
+
gradient_checkpointing: true
|
| 119 |
+
early_stopping_patience:
|
| 120 |
+
resume_from_checkpoint:
|
| 121 |
+
local_rank:
|
| 122 |
+
logging_steps: 1
|
| 123 |
+
xformers_attention:
|
| 124 |
+
flash_attention: true
|
| 125 |
+
|
| 126 |
+
warmup_steps: 35
|
| 127 |
+
evals_per_epoch: 4
|
| 128 |
+
eval_table_size:
|
| 129 |
+
eval_max_new_tokens: 128
|
| 130 |
+
saves_per_epoch: 2
|
| 131 |
+
debug:
|
| 132 |
+
deepspeed: ./deepspeed_configs/zero3_bf16.json
|
| 133 |
+
weight_decay: 0.03
|
| 134 |
+
fsdp:
|
| 135 |
+
fsdp_config:
|
| 136 |
+
special_tokens:
|
| 137 |
+
pad_token: <|finetune_right_pad_id|>
|
| 138 |
+
|
| 139 |
+
```
|
| 140 |
+
|
| 141 |
+
</details><br>
|
| 142 |
+
|
| 143 |
+
# Hamanasu-4B-Adventure-V2
|
| 144 |
+
|
| 145 |
+
This model is a fine-tuned version of [NewEden/Hamanasu-KTO-V2](https://huggingface.co/NewEden/Hamanasu-KTO-V2) on the ./t.json, the PocketDoc/Dans-Prosemaxx-Adventure, the PocketDoc/Dans-Failuremaxx-Adventure-3, the PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2, the PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-3, the PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2, the PocketDoc/Dans-Prosemaxx-Instructwriter-Long and the PocketDoc/Dans-Personamaxx-VN datasets.
|
| 146 |
+
It achieves the following results on the evaluation set:
|
| 147 |
+
- Loss: 2.3770
|
| 148 |
+
|
| 149 |
+
## Model description
|
| 150 |
+
|
| 151 |
+
More information needed
|
| 152 |
+
|
| 153 |
+
## Intended uses & limitations
|
| 154 |
+
|
| 155 |
+
More information needed
|
| 156 |
+
|
| 157 |
+
## Training and evaluation data
|
| 158 |
+
|
| 159 |
+
More information needed
|
| 160 |
+
|
| 161 |
+
## Training procedure
|
| 162 |
+
|
| 163 |
+
### Training hyperparameters
|
| 164 |
+
|
| 165 |
+
The following hyperparameters were used during training:
|
| 166 |
+
- learning_rate: 3e-05
|
| 167 |
+
- train_batch_size: 4
|
| 168 |
+
- eval_batch_size: 4
|
| 169 |
+
- seed: 42
|
| 170 |
+
- distributed_type: multi-GPU
|
| 171 |
+
- num_devices: 4
|
| 172 |
+
- gradient_accumulation_steps: 2
|
| 173 |
+
- total_train_batch_size: 32
|
| 174 |
+
- total_eval_batch_size: 16
|
| 175 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 176 |
+
- lr_scheduler_type: cosine
|
| 177 |
+
- lr_scheduler_warmup_steps: 35
|
| 178 |
+
- num_epochs: 6.0
|
| 179 |
+
|
| 180 |
+
### Training results
|
| 181 |
+
|
| 182 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 183 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 184 |
+
| 2.5443 | 0.0083 | 1 | 2.5896 |
|
| 185 |
+
| 2.3222 | 0.25 | 30 | 2.4448 |
|
| 186 |
+
| 2.3768 | 0.5 | 60 | 2.4210 |
|
| 187 |
+
| 2.3336 | 0.75 | 90 | 2.4106 |
|
| 188 |
+
| 2.3595 | 1.0 | 120 | 2.4039 |
|
| 189 |
+
| 2.3078 | 1.25 | 150 | 2.3991 |
|
| 190 |
+
| 2.3111 | 1.5 | 180 | 2.3952 |
|
| 191 |
+
| 2.3331 | 1.75 | 210 | 2.3916 |
|
| 192 |
+
| 2.2758 | 2.0 | 240 | 2.3889 |
|
| 193 |
+
| 2.3227 | 2.25 | 270 | 2.3869 |
|
| 194 |
+
| 2.335 | 2.5 | 300 | 2.3851 |
|
| 195 |
+
| 2.349 | 2.75 | 330 | 2.3835 |
|
| 196 |
+
| 2.2828 | 3.0 | 360 | 2.3818 |
|
| 197 |
+
| 2.2632 | 3.25 | 390 | 2.3811 |
|
| 198 |
+
| 2.3254 | 3.5 | 420 | 2.3801 |
|
| 199 |
+
| 2.3073 | 3.75 | 450 | 2.3791 |
|
| 200 |
+
| 2.337 | 4.0 | 480 | 2.3783 |
|
| 201 |
+
| 2.2319 | 4.25 | 510 | 2.3782 |
|
| 202 |
+
| 2.3044 | 4.5 | 540 | 2.3778 |
|
| 203 |
+
| 2.2948 | 4.75 | 570 | 2.3773 |
|
| 204 |
+
| 2.2625 | 5.0 | 600 | 2.3771 |
|
| 205 |
+
| 2.3194 | 5.25 | 630 | 2.3771 |
|
| 206 |
+
| 2.2457 | 5.5 | 660 | 2.3771 |
|
| 207 |
+
| 2.2746 | 5.75 | 690 | 2.3769 |
|
| 208 |
+
| 2.2496 | 6.0 | 720 | 2.3770 |
|
| 209 |
+
|
| 210 |
+
|
| 211 |
+
### Framework versions
|
| 212 |
+
|
| 213 |
+
- PEFT 0.15.0
|
| 214 |
+
- Transformers 4.50.0
|
| 215 |
+
- Pytorch 2.5.1+cu124
|
| 216 |
+
- Datasets 3.5.0
|
| 217 |
+
- Tokenizers 0.21.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"q_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": true
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:147e6fc9c7df4b177be0efa498df0ee2545c9ae936c6c87697838e9d7727657f
|
| 3 |
+
size 486600536
|
checkpoint-540/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.0
|
checkpoint-540/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"q_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": true
|
| 39 |
+
}
|
checkpoint-540/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80c7a8a7a75b123d24ad8a7218f94d231edf9ea8c771bb05cd72e0ac858de69e
|
| 3 |
+
size 486600536
|
checkpoint-540/global_step540/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21e3c4578a1444aeb1bf8e0132d15248d006fc944356e0f130552ee2d148c462
|
| 3 |
+
size 367555424
|
checkpoint-540/global_step540/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c31cee12e8d8b8bfc5243a4eb69f216672d6f51fb77e31fa1fcea55c14a32b4
|
| 3 |
+
size 367555424
|
checkpoint-540/global_step540/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72885e600e361572158cb77005f8ee419fe498c85d87062ec6e3a505a8fb21d4
|
| 3 |
+
size 367555424
|
checkpoint-540/global_step540/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eaa92649e6d605e68ac3a625420642cd3c25f56c492a26cfbfd50066e6fa3c2
|
| 3 |
+
size 367555424
|
checkpoint-540/global_step540/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:846d4aebc501929c1c4a59e791b9382994054efa267ebae03810f22ea5028c76
|
| 3 |
+
size 445742
|
checkpoint-540/global_step540/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:887d91d3cd5293c032aef6e5eb85a7e821451f7f49c84e8ac47aec923137659e
|
| 3 |
+
size 445742
|
checkpoint-540/global_step540/zero_pp_rank_2_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f65ab1c6510cd31c44deefe3871a0f0cc1f3a5719a3ebaedb09eed0e74eccbd8
|
| 3 |
+
size 445742
|
checkpoint-540/global_step540/zero_pp_rank_3_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b120d3669f720fa66982c2f2cfe70252856c3d221ad247bb555e0eff6be1d72
|
| 3 |
+
size 445742
|
checkpoint-540/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step540
|
checkpoint-540/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53c4dc1925fe71ee89db7b4dcb1582a61b7cadc4e5456ba8bf87dcf122d93dbe
|
| 3 |
+
size 15024
|
checkpoint-540/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15b0838fcbe3ede37c975b0c0f4c1aea7395520f9f9fe3c3ac6423bd88357334
|
| 3 |
+
size 15024
|
checkpoint-540/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20b5f250d8af142d1ee60b0bb79053f51b69902116deb2aa76d8c2c35c0f45de
|
| 3 |
+
size 15024
|
checkpoint-540/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e5316de67b41beb31e47fcfd61a5924b8099cbdb2ea4301d283ecc3ccdb2d9a
|
| 3 |
+
size 15024
|
checkpoint-540/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f0b84eb718a04b965b7ae46607af6450272ab0026242b9e5960864cdc4a2c57
|
| 3 |
+
size 1064
|
checkpoint-540/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-540/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
|
| 3 |
+
size 17209884
|
checkpoint-540/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_start|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|im_end|>",
|
| 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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|im_end|>",
|
| 2056 |
+
"extra_special_tokens": {},
|
| 2057 |
+
"model_input_names": [
|
| 2058 |
+
"input_ids",
|
| 2059 |
+
"attention_mask"
|
| 2060 |
+
],
|
| 2061 |
+
"model_max_length": 131072,
|
| 2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2063 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2064 |
+
}
|
checkpoint-540/trainer_state.json
ADDED
|
@@ -0,0 +1,3966 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.5,
|
| 6 |
+
"eval_steps": 30,
|
| 7 |
+
"global_step": 540,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008333333333333333,
|
| 14 |
+
"grad_norm": 0.9360410277242142,
|
| 15 |
+
"learning_rate": 8.571428571428571e-07,
|
| 16 |
+
"loss": 2.5443,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008333333333333333,
|
| 21 |
+
"eval_loss": 2.5896365642547607,
|
| 22 |
+
"eval_runtime": 82.612,
|
| 23 |
+
"eval_samples_per_second": 4.963,
|
| 24 |
+
"eval_steps_per_second": 0.315,
|
| 25 |
+
"step": 1
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.016666666666666666,
|
| 29 |
+
"grad_norm": 0.9508560449534389,
|
| 30 |
+
"learning_rate": 1.7142857142857143e-06,
|
| 31 |
+
"loss": 2.5524,
|
| 32 |
+
"step": 2
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.025,
|
| 36 |
+
"grad_norm": 0.9146058934097653,
|
| 37 |
+
"learning_rate": 2.5714285714285716e-06,
|
| 38 |
+
"loss": 2.5411,
|
| 39 |
+
"step": 3
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03333333333333333,
|
| 43 |
+
"grad_norm": 0.973225491135029,
|
| 44 |
+
"learning_rate": 3.4285714285714285e-06,
|
| 45 |
+
"loss": 2.5517,
|
| 46 |
+
"step": 4
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.041666666666666664,
|
| 50 |
+
"grad_norm": 0.8939783540255565,
|
| 51 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 52 |
+
"loss": 2.4919,
|
| 53 |
+
"step": 5
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.05,
|
| 57 |
+
"grad_norm": 0.901037701703779,
|
| 58 |
+
"learning_rate": 5.142857142857143e-06,
|
| 59 |
+
"loss": 2.5707,
|
| 60 |
+
"step": 6
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.058333333333333334,
|
| 64 |
+
"grad_norm": 0.8188196758761533,
|
| 65 |
+
"learning_rate": 6e-06,
|
| 66 |
+
"loss": 2.495,
|
| 67 |
+
"step": 7
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.06666666666666667,
|
| 71 |
+
"grad_norm": 0.7923776565864661,
|
| 72 |
+
"learning_rate": 6.857142857142857e-06,
|
| 73 |
+
"loss": 2.4928,
|
| 74 |
+
"step": 8
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.075,
|
| 78 |
+
"grad_norm": 0.6772553900416157,
|
| 79 |
+
"learning_rate": 7.714285714285714e-06,
|
| 80 |
+
"loss": 2.5002,
|
| 81 |
+
"step": 9
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.08333333333333333,
|
| 85 |
+
"grad_norm": 0.570249341697236,
|
| 86 |
+
"learning_rate": 8.571428571428571e-06,
|
| 87 |
+
"loss": 2.4658,
|
| 88 |
+
"step": 10
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.09166666666666666,
|
| 92 |
+
"grad_norm": 0.5182511162697805,
|
| 93 |
+
"learning_rate": 9.428571428571428e-06,
|
| 94 |
+
"loss": 2.5166,
|
| 95 |
+
"step": 11
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.1,
|
| 99 |
+
"grad_norm": 0.38804895110127413,
|
| 100 |
+
"learning_rate": 1.0285714285714286e-05,
|
| 101 |
+
"loss": 2.4883,
|
| 102 |
+
"step": 12
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.10833333333333334,
|
| 106 |
+
"grad_norm": 0.3311832915799773,
|
| 107 |
+
"learning_rate": 1.1142857142857143e-05,
|
| 108 |
+
"loss": 2.4436,
|
| 109 |
+
"step": 13
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.11666666666666667,
|
| 113 |
+
"grad_norm": 0.258295171244105,
|
| 114 |
+
"learning_rate": 1.2e-05,
|
| 115 |
+
"loss": 2.4574,
|
| 116 |
+
"step": 14
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.125,
|
| 120 |
+
"grad_norm": 0.21715876810815016,
|
| 121 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 122 |
+
"loss": 2.4336,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.13333333333333333,
|
| 127 |
+
"grad_norm": 0.22216516761581057,
|
| 128 |
+
"learning_rate": 1.3714285714285714e-05,
|
| 129 |
+
"loss": 2.3664,
|
| 130 |
+
"step": 16
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.14166666666666666,
|
| 134 |
+
"grad_norm": 0.24546192056617316,
|
| 135 |
+
"learning_rate": 1.4571428571428571e-05,
|
| 136 |
+
"loss": 2.4041,
|
| 137 |
+
"step": 17
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.15,
|
| 141 |
+
"grad_norm": 0.23071398791633685,
|
| 142 |
+
"learning_rate": 1.5428571428571428e-05,
|
| 143 |
+
"loss": 2.4152,
|
| 144 |
+
"step": 18
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.15833333333333333,
|
| 148 |
+
"grad_norm": 0.2455226896443164,
|
| 149 |
+
"learning_rate": 1.6285714285714283e-05,
|
| 150 |
+
"loss": 2.4099,
|
| 151 |
+
"step": 19
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.16666666666666666,
|
| 155 |
+
"grad_norm": 0.21298444680868547,
|
| 156 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 157 |
+
"loss": 2.4334,
|
| 158 |
+
"step": 20
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.175,
|
| 162 |
+
"grad_norm": 0.20533327114223276,
|
| 163 |
+
"learning_rate": 1.8e-05,
|
| 164 |
+
"loss": 2.4519,
|
| 165 |
+
"step": 21
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.18333333333333332,
|
| 169 |
+
"grad_norm": 0.16870069179876526,
|
| 170 |
+
"learning_rate": 1.8857142857142856e-05,
|
| 171 |
+
"loss": 2.4385,
|
| 172 |
+
"step": 22
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19166666666666668,
|
| 176 |
+
"grad_norm": 0.14402205430547502,
|
| 177 |
+
"learning_rate": 1.9714285714285714e-05,
|
| 178 |
+
"loss": 2.4263,
|
| 179 |
+
"step": 23
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.2,
|
| 183 |
+
"grad_norm": 0.12172082974236817,
|
| 184 |
+
"learning_rate": 2.0571428571428573e-05,
|
| 185 |
+
"loss": 2.3845,
|
| 186 |
+
"step": 24
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.20833333333333334,
|
| 190 |
+
"grad_norm": 0.12458423334628936,
|
| 191 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 192 |
+
"loss": 2.3999,
|
| 193 |
+
"step": 25
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.21666666666666667,
|
| 197 |
+
"grad_norm": 0.12534806192043724,
|
| 198 |
+
"learning_rate": 2.2285714285714287e-05,
|
| 199 |
+
"loss": 2.4081,
|
| 200 |
+
"step": 26
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.225,
|
| 204 |
+
"grad_norm": 0.13741644272287978,
|
| 205 |
+
"learning_rate": 2.3142857142857145e-05,
|
| 206 |
+
"loss": 2.3635,
|
| 207 |
+
"step": 27
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.23333333333333334,
|
| 211 |
+
"grad_norm": 0.12252487251666222,
|
| 212 |
+
"learning_rate": 2.4e-05,
|
| 213 |
+
"loss": 2.4161,
|
| 214 |
+
"step": 28
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.24166666666666667,
|
| 218 |
+
"grad_norm": 0.1192741596813014,
|
| 219 |
+
"learning_rate": 2.485714285714286e-05,
|
| 220 |
+
"loss": 2.3494,
|
| 221 |
+
"step": 29
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.25,
|
| 225 |
+
"grad_norm": 0.1072101207827042,
|
| 226 |
+
"learning_rate": 2.5714285714285714e-05,
|
| 227 |
+
"loss": 2.3222,
|
| 228 |
+
"step": 30
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.25,
|
| 232 |
+
"eval_loss": 2.444800615310669,
|
| 233 |
+
"eval_runtime": 84.2568,
|
| 234 |
+
"eval_samples_per_second": 4.866,
|
| 235 |
+
"eval_steps_per_second": 0.309,
|
| 236 |
+
"step": 30
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.25833333333333336,
|
| 240 |
+
"grad_norm": 0.10212088304260515,
|
| 241 |
+
"learning_rate": 2.657142857142857e-05,
|
| 242 |
+
"loss": 2.3999,
|
| 243 |
+
"step": 31
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.26666666666666666,
|
| 247 |
+
"grad_norm": 0.09564286178695633,
|
| 248 |
+
"learning_rate": 2.7428571428571428e-05,
|
| 249 |
+
"loss": 2.408,
|
| 250 |
+
"step": 32
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.275,
|
| 254 |
+
"grad_norm": 0.09307121023694089,
|
| 255 |
+
"learning_rate": 2.8285714285714287e-05,
|
| 256 |
+
"loss": 2.3897,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.2833333333333333,
|
| 261 |
+
"grad_norm": 0.08997413119128918,
|
| 262 |
+
"learning_rate": 2.9142857142857142e-05,
|
| 263 |
+
"loss": 2.4058,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.2916666666666667,
|
| 268 |
+
"grad_norm": 0.09472974956869049,
|
| 269 |
+
"learning_rate": 3e-05,
|
| 270 |
+
"loss": 2.3692,
|
| 271 |
+
"step": 35
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3,
|
| 275 |
+
"grad_norm": 0.09590933887075358,
|
| 276 |
+
"learning_rate": 2.9999842246463293e-05,
|
| 277 |
+
"loss": 2.358,
|
| 278 |
+
"step": 36
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.30833333333333335,
|
| 282 |
+
"grad_norm": 0.09016959739831318,
|
| 283 |
+
"learning_rate": 2.9999368989171332e-05,
|
| 284 |
+
"loss": 2.4251,
|
| 285 |
+
"step": 37
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.31666666666666665,
|
| 289 |
+
"grad_norm": 0.09263473987284757,
|
| 290 |
+
"learning_rate": 2.9998580238078518e-05,
|
| 291 |
+
"loss": 2.3223,
|
| 292 |
+
"step": 38
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.325,
|
| 296 |
+
"grad_norm": 0.08933219467342407,
|
| 297 |
+
"learning_rate": 2.9997476009775285e-05,
|
| 298 |
+
"loss": 2.4019,
|
| 299 |
+
"step": 39
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.3333333333333333,
|
| 303 |
+
"grad_norm": 0.08625244619052558,
|
| 304 |
+
"learning_rate": 2.999605632748776e-05,
|
| 305 |
+
"loss": 2.3818,
|
| 306 |
+
"step": 40
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.3416666666666667,
|
| 310 |
+
"grad_norm": 0.08233766840669011,
|
| 311 |
+
"learning_rate": 2.999432122107726e-05,
|
| 312 |
+
"loss": 2.3521,
|
| 313 |
+
"step": 41
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.35,
|
| 317 |
+
"grad_norm": 0.08142227096247721,
|
| 318 |
+
"learning_rate": 2.9992270727039674e-05,
|
| 319 |
+
"loss": 2.3511,
|
| 320 |
+
"step": 42
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.35833333333333334,
|
| 324 |
+
"grad_norm": 0.08018903995286845,
|
| 325 |
+
"learning_rate": 2.9989904888504697e-05,
|
| 326 |
+
"loss": 2.37,
|
| 327 |
+
"step": 43
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.36666666666666664,
|
| 331 |
+
"grad_norm": 0.07330862837022564,
|
| 332 |
+
"learning_rate": 2.998722375523491e-05,
|
| 333 |
+
"loss": 2.3873,
|
| 334 |
+
"step": 44
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.375,
|
| 338 |
+
"grad_norm": 0.07352041223526255,
|
| 339 |
+
"learning_rate": 2.9984227383624753e-05,
|
| 340 |
+
"loss": 2.3578,
|
| 341 |
+
"step": 45
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.38333333333333336,
|
| 345 |
+
"grad_norm": 0.07722674724130721,
|
| 346 |
+
"learning_rate": 2.9980915836699322e-05,
|
| 347 |
+
"loss": 2.3985,
|
| 348 |
+
"step": 46
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.39166666666666666,
|
| 352 |
+
"grad_norm": 0.07804098073998368,
|
| 353 |
+
"learning_rate": 2.9977289184113038e-05,
|
| 354 |
+
"loss": 2.3829,
|
| 355 |
+
"step": 47
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 0.4,
|
| 359 |
+
"grad_norm": 0.08054438685981385,
|
| 360 |
+
"learning_rate": 2.997334750214822e-05,
|
| 361 |
+
"loss": 2.362,
|
| 362 |
+
"step": 48
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.4083333333333333,
|
| 366 |
+
"grad_norm": 0.07110517922067144,
|
| 367 |
+
"learning_rate": 2.9969090873713425e-05,
|
| 368 |
+
"loss": 2.3602,
|
| 369 |
+
"step": 49
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.4166666666666667,
|
| 373 |
+
"grad_norm": 0.0688101984554574,
|
| 374 |
+
"learning_rate": 2.9964519388341753e-05,
|
| 375 |
+
"loss": 2.4384,
|
| 376 |
+
"step": 50
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.425,
|
| 380 |
+
"grad_norm": 0.07002559414264917,
|
| 381 |
+
"learning_rate": 2.9959633142188928e-05,
|
| 382 |
+
"loss": 2.351,
|
| 383 |
+
"step": 51
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.43333333333333335,
|
| 387 |
+
"grad_norm": 0.07117883774757176,
|
| 388 |
+
"learning_rate": 2.99544322380313e-05,
|
| 389 |
+
"loss": 2.3974,
|
| 390 |
+
"step": 52
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.44166666666666665,
|
| 394 |
+
"grad_norm": 0.07001361672749891,
|
| 395 |
+
"learning_rate": 2.994891678526368e-05,
|
| 396 |
+
"loss": 2.3543,
|
| 397 |
+
"step": 53
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.45,
|
| 401 |
+
"grad_norm": 0.07035813493300362,
|
| 402 |
+
"learning_rate": 2.994308689989702e-05,
|
| 403 |
+
"loss": 2.3786,
|
| 404 |
+
"step": 54
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.4583333333333333,
|
| 408 |
+
"grad_norm": 0.07044999453738358,
|
| 409 |
+
"learning_rate": 2.9936942704555988e-05,
|
| 410 |
+
"loss": 2.4267,
|
| 411 |
+
"step": 55
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.4666666666666667,
|
| 415 |
+
"grad_norm": 0.06965904966911632,
|
| 416 |
+
"learning_rate": 2.9930484328476392e-05,
|
| 417 |
+
"loss": 2.3314,
|
| 418 |
+
"step": 56
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.475,
|
| 422 |
+
"grad_norm": 0.06791684466469557,
|
| 423 |
+
"learning_rate": 2.992371190750246e-05,
|
| 424 |
+
"loss": 2.3875,
|
| 425 |
+
"step": 57
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.48333333333333334,
|
| 429 |
+
"grad_norm": 0.07216126684861118,
|
| 430 |
+
"learning_rate": 2.9916625584083965e-05,
|
| 431 |
+
"loss": 2.329,
|
| 432 |
+
"step": 58
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.49166666666666664,
|
| 436 |
+
"grad_norm": 0.0702185022867809,
|
| 437 |
+
"learning_rate": 2.990922550727326e-05,
|
| 438 |
+
"loss": 2.3301,
|
| 439 |
+
"step": 59
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.5,
|
| 443 |
+
"grad_norm": 0.06812334850285051,
|
| 444 |
+
"learning_rate": 2.9901511832722107e-05,
|
| 445 |
+
"loss": 2.3768,
|
| 446 |
+
"step": 60
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.5,
|
| 450 |
+
"eval_loss": 2.420956611633301,
|
| 451 |
+
"eval_runtime": 82.0789,
|
| 452 |
+
"eval_samples_per_second": 4.995,
|
| 453 |
+
"eval_steps_per_second": 0.317,
|
| 454 |
+
"step": 60
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.5083333333333333,
|
| 458 |
+
"grad_norm": 0.06977788943398308,
|
| 459 |
+
"learning_rate": 2.989348472267844e-05,
|
| 460 |
+
"loss": 2.3311,
|
| 461 |
+
"step": 61
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.5166666666666667,
|
| 465 |
+
"grad_norm": 0.07206045445309828,
|
| 466 |
+
"learning_rate": 2.988514434598292e-05,
|
| 467 |
+
"loss": 2.364,
|
| 468 |
+
"step": 62
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.525,
|
| 472 |
+
"grad_norm": 0.0686132670382019,
|
| 473 |
+
"learning_rate": 2.9876490878065402e-05,
|
| 474 |
+
"loss": 2.396,
|
| 475 |
+
"step": 63
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5333333333333333,
|
| 479 |
+
"grad_norm": 0.0662695861354406,
|
| 480 |
+
"learning_rate": 2.9867524500941255e-05,
|
| 481 |
+
"loss": 2.3855,
|
| 482 |
+
"step": 64
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5416666666666666,
|
| 486 |
+
"grad_norm": 0.07150818390300492,
|
| 487 |
+
"learning_rate": 2.9858245403207488e-05,
|
| 488 |
+
"loss": 2.3814,
|
| 489 |
+
"step": 65
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.55,
|
| 493 |
+
"grad_norm": 0.0688955126726483,
|
| 494 |
+
"learning_rate": 2.9848653780038844e-05,
|
| 495 |
+
"loss": 2.3231,
|
| 496 |
+
"step": 66
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.5583333333333333,
|
| 500 |
+
"grad_norm": 0.08689626076791215,
|
| 501 |
+
"learning_rate": 2.9838749833183647e-05,
|
| 502 |
+
"loss": 2.3496,
|
| 503 |
+
"step": 67
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.5666666666666667,
|
| 507 |
+
"grad_norm": 0.06919653831851563,
|
| 508 |
+
"learning_rate": 2.9828533770959584e-05,
|
| 509 |
+
"loss": 2.3754,
|
| 510 |
+
"step": 68
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.575,
|
| 514 |
+
"grad_norm": 0.0686359152840503,
|
| 515 |
+
"learning_rate": 2.9818005808249323e-05,
|
| 516 |
+
"loss": 2.3194,
|
| 517 |
+
"step": 69
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.5833333333333334,
|
| 521 |
+
"grad_norm": 0.06420348702388212,
|
| 522 |
+
"learning_rate": 2.9807166166495966e-05,
|
| 523 |
+
"loss": 2.4109,
|
| 524 |
+
"step": 70
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.5916666666666667,
|
| 528 |
+
"grad_norm": 0.06763129881807128,
|
| 529 |
+
"learning_rate": 2.979601507369843e-05,
|
| 530 |
+
"loss": 2.4226,
|
| 531 |
+
"step": 71
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6,
|
| 535 |
+
"grad_norm": 0.07805776727073946,
|
| 536 |
+
"learning_rate": 2.978455276440662e-05,
|
| 537 |
+
"loss": 2.3606,
|
| 538 |
+
"step": 72
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.6083333333333333,
|
| 542 |
+
"grad_norm": 0.07118702812706623,
|
| 543 |
+
"learning_rate": 2.977277947971652e-05,
|
| 544 |
+
"loss": 2.3261,
|
| 545 |
+
"step": 73
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.6166666666666667,
|
| 549 |
+
"grad_norm": 0.06672990667439338,
|
| 550 |
+
"learning_rate": 2.9760695467265096e-05,
|
| 551 |
+
"loss": 2.3597,
|
| 552 |
+
"step": 74
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.625,
|
| 556 |
+
"grad_norm": 0.07069779975327012,
|
| 557 |
+
"learning_rate": 2.9748300981225112e-05,
|
| 558 |
+
"loss": 2.386,
|
| 559 |
+
"step": 75
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 0.6333333333333333,
|
| 563 |
+
"grad_norm": 0.07219821307129556,
|
| 564 |
+
"learning_rate": 2.9735596282299767e-05,
|
| 565 |
+
"loss": 2.3966,
|
| 566 |
+
"step": 76
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.6416666666666667,
|
| 570 |
+
"grad_norm": 0.07410097496341012,
|
| 571 |
+
"learning_rate": 2.9722581637717225e-05,
|
| 572 |
+
"loss": 2.3967,
|
| 573 |
+
"step": 77
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.65,
|
| 577 |
+
"grad_norm": 0.0689700729031345,
|
| 578 |
+
"learning_rate": 2.9709257321224973e-05,
|
| 579 |
+
"loss": 2.3716,
|
| 580 |
+
"step": 78
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.6583333333333333,
|
| 584 |
+
"grad_norm": 0.06672921198595727,
|
| 585 |
+
"learning_rate": 2.9695623613084094e-05,
|
| 586 |
+
"loss": 2.3985,
|
| 587 |
+
"step": 79
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.6666666666666666,
|
| 591 |
+
"grad_norm": 0.07134050468764856,
|
| 592 |
+
"learning_rate": 2.9681680800063333e-05,
|
| 593 |
+
"loss": 2.3438,
|
| 594 |
+
"step": 80
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.675,
|
| 598 |
+
"grad_norm": 0.07182936816116632,
|
| 599 |
+
"learning_rate": 2.966742917543311e-05,
|
| 600 |
+
"loss": 2.2975,
|
| 601 |
+
"step": 81
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.6833333333333333,
|
| 605 |
+
"grad_norm": 0.07465679904272592,
|
| 606 |
+
"learning_rate": 2.9652869038959308e-05,
|
| 607 |
+
"loss": 2.3688,
|
| 608 |
+
"step": 82
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.6916666666666667,
|
| 612 |
+
"grad_norm": 0.07264390487872555,
|
| 613 |
+
"learning_rate": 2.9638000696897004e-05,
|
| 614 |
+
"loss": 2.3427,
|
| 615 |
+
"step": 83
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.7,
|
| 619 |
+
"grad_norm": 0.06952115231660631,
|
| 620 |
+
"learning_rate": 2.9622824461984e-05,
|
| 621 |
+
"loss": 2.3848,
|
| 622 |
+
"step": 84
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.7083333333333334,
|
| 626 |
+
"grad_norm": 0.07052293359277144,
|
| 627 |
+
"learning_rate": 2.9607340653434263e-05,
|
| 628 |
+
"loss": 2.3842,
|
| 629 |
+
"step": 85
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.7166666666666667,
|
| 633 |
+
"grad_norm": 0.07215231844162684,
|
| 634 |
+
"learning_rate": 2.9591549596931196e-05,
|
| 635 |
+
"loss": 2.3825,
|
| 636 |
+
"step": 86
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.725,
|
| 640 |
+
"grad_norm": 0.06993868056954115,
|
| 641 |
+
"learning_rate": 2.957545162462081e-05,
|
| 642 |
+
"loss": 2.3564,
|
| 643 |
+
"step": 87
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.7333333333333333,
|
| 647 |
+
"grad_norm": 0.07435507338492273,
|
| 648 |
+
"learning_rate": 2.95590470751047e-05,
|
| 649 |
+
"loss": 2.3152,
|
| 650 |
+
"step": 88
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.7416666666666667,
|
| 654 |
+
"grad_norm": 0.07329267507546385,
|
| 655 |
+
"learning_rate": 2.954233629343297e-05,
|
| 656 |
+
"loss": 2.3842,
|
| 657 |
+
"step": 89
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.75,
|
| 661 |
+
"grad_norm": 0.07062791878125828,
|
| 662 |
+
"learning_rate": 2.9525319631096936e-05,
|
| 663 |
+
"loss": 2.3336,
|
| 664 |
+
"step": 90
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.75,
|
| 668 |
+
"eval_loss": 2.4106247425079346,
|
| 669 |
+
"eval_runtime": 82.7637,
|
| 670 |
+
"eval_samples_per_second": 4.954,
|
| 671 |
+
"eval_steps_per_second": 0.314,
|
| 672 |
+
"step": 90
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.7583333333333333,
|
| 676 |
+
"grad_norm": 0.06686149540343819,
|
| 677 |
+
"learning_rate": 2.950799744602176e-05,
|
| 678 |
+
"loss": 2.344,
|
| 679 |
+
"step": 91
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.7666666666666667,
|
| 683 |
+
"grad_norm": 0.07315321410788929,
|
| 684 |
+
"learning_rate": 2.94903701025589e-05,
|
| 685 |
+
"loss": 2.3439,
|
| 686 |
+
"step": 92
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.775,
|
| 690 |
+
"grad_norm": 0.07387581694456348,
|
| 691 |
+
"learning_rate": 2.9472437971478456e-05,
|
| 692 |
+
"loss": 2.3207,
|
| 693 |
+
"step": 93
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.7833333333333333,
|
| 697 |
+
"grad_norm": 0.07489655701047354,
|
| 698 |
+
"learning_rate": 2.9454201429961377e-05,
|
| 699 |
+
"loss": 2.332,
|
| 700 |
+
"step": 94
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 0.7916666666666666,
|
| 704 |
+
"grad_norm": 0.07257848830631401,
|
| 705 |
+
"learning_rate": 2.9435660861591523e-05,
|
| 706 |
+
"loss": 2.32,
|
| 707 |
+
"step": 95
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.8,
|
| 711 |
+
"grad_norm": 0.07343958275400869,
|
| 712 |
+
"learning_rate": 2.9416816656347585e-05,
|
| 713 |
+
"loss": 2.3474,
|
| 714 |
+
"step": 96
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.8083333333333333,
|
| 718 |
+
"grad_norm": 0.06737876227380284,
|
| 719 |
+
"learning_rate": 2.9397669210594905e-05,
|
| 720 |
+
"loss": 2.4118,
|
| 721 |
+
"step": 97
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 0.8166666666666667,
|
| 725 |
+
"grad_norm": 0.07053321403511485,
|
| 726 |
+
"learning_rate": 2.9378218927077116e-05,
|
| 727 |
+
"loss": 2.3824,
|
| 728 |
+
"step": 98
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.825,
|
| 732 |
+
"grad_norm": 0.07673123567620053,
|
| 733 |
+
"learning_rate": 2.9358466214907692e-05,
|
| 734 |
+
"loss": 2.3296,
|
| 735 |
+
"step": 99
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.8333333333333334,
|
| 739 |
+
"grad_norm": 0.07372803957962162,
|
| 740 |
+
"learning_rate": 2.9338411489561327e-05,
|
| 741 |
+
"loss": 2.3245,
|
| 742 |
+
"step": 100
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.8416666666666667,
|
| 746 |
+
"grad_norm": 0.07336979504832328,
|
| 747 |
+
"learning_rate": 2.931805517286519e-05,
|
| 748 |
+
"loss": 2.3957,
|
| 749 |
+
"step": 101
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.85,
|
| 753 |
+
"grad_norm": 0.07103643078368066,
|
| 754 |
+
"learning_rate": 2.929739769299009e-05,
|
| 755 |
+
"loss": 2.3336,
|
| 756 |
+
"step": 102
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.8583333333333333,
|
| 760 |
+
"grad_norm": 0.07718497388969756,
|
| 761 |
+
"learning_rate": 2.927643948444142e-05,
|
| 762 |
+
"loss": 2.3326,
|
| 763 |
+
"step": 103
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 0.8666666666666667,
|
| 767 |
+
"grad_norm": 0.07693440422410756,
|
| 768 |
+
"learning_rate": 2.925518098805005e-05,
|
| 769 |
+
"loss": 2.3303,
|
| 770 |
+
"step": 104
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.875,
|
| 774 |
+
"grad_norm": 0.0794426183938342,
|
| 775 |
+
"learning_rate": 2.9233622650963046e-05,
|
| 776 |
+
"loss": 2.3997,
|
| 777 |
+
"step": 105
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.8833333333333333,
|
| 781 |
+
"grad_norm": 0.07596664220631637,
|
| 782 |
+
"learning_rate": 2.921176492663426e-05,
|
| 783 |
+
"loss": 2.3413,
|
| 784 |
+
"step": 106
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.8916666666666667,
|
| 788 |
+
"grad_norm": 0.06996553326833363,
|
| 789 |
+
"learning_rate": 2.9189608274814813e-05,
|
| 790 |
+
"loss": 2.3341,
|
| 791 |
+
"step": 107
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.9,
|
| 795 |
+
"grad_norm": 0.07228734113486272,
|
| 796 |
+
"learning_rate": 2.916715316154339e-05,
|
| 797 |
+
"loss": 2.3782,
|
| 798 |
+
"step": 108
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.9083333333333333,
|
| 802 |
+
"grad_norm": 0.07539741887897378,
|
| 803 |
+
"learning_rate": 2.9144400059136457e-05,
|
| 804 |
+
"loss": 2.3674,
|
| 805 |
+
"step": 109
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 0.9166666666666666,
|
| 809 |
+
"grad_norm": 0.07429144145946807,
|
| 810 |
+
"learning_rate": 2.9121349446178338e-05,
|
| 811 |
+
"loss": 2.3026,
|
| 812 |
+
"step": 110
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.925,
|
| 816 |
+
"grad_norm": 0.0716306685459669,
|
| 817 |
+
"learning_rate": 2.909800180751112e-05,
|
| 818 |
+
"loss": 2.3672,
|
| 819 |
+
"step": 111
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.9333333333333333,
|
| 823 |
+
"grad_norm": 0.07659700418644584,
|
| 824 |
+
"learning_rate": 2.907435763422449e-05,
|
| 825 |
+
"loss": 2.3336,
|
| 826 |
+
"step": 112
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.9416666666666667,
|
| 830 |
+
"grad_norm": 0.0707479576055371,
|
| 831 |
+
"learning_rate": 2.9050417423645374e-05,
|
| 832 |
+
"loss": 2.3492,
|
| 833 |
+
"step": 113
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.95,
|
| 837 |
+
"grad_norm": 0.0763387966295892,
|
| 838 |
+
"learning_rate": 2.9026181679327483e-05,
|
| 839 |
+
"loss": 2.37,
|
| 840 |
+
"step": 114
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.9583333333333334,
|
| 844 |
+
"grad_norm": 0.06970035658866476,
|
| 845 |
+
"learning_rate": 2.9001650911040744e-05,
|
| 846 |
+
"loss": 2.3806,
|
| 847 |
+
"step": 115
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.9666666666666667,
|
| 851 |
+
"grad_norm": 0.0700682953812373,
|
| 852 |
+
"learning_rate": 2.897682563476054e-05,
|
| 853 |
+
"loss": 2.2947,
|
| 854 |
+
"step": 116
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.975,
|
| 858 |
+
"grad_norm": 0.0754085979262008,
|
| 859 |
+
"learning_rate": 2.8951706372656898e-05,
|
| 860 |
+
"loss": 2.3268,
|
| 861 |
+
"step": 117
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.9833333333333333,
|
| 865 |
+
"grad_norm": 0.0683345804710695,
|
| 866 |
+
"learning_rate": 2.8926293653083475e-05,
|
| 867 |
+
"loss": 2.4107,
|
| 868 |
+
"step": 118
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 0.9916666666666667,
|
| 872 |
+
"grad_norm": 0.07675942594210501,
|
| 873 |
+
"learning_rate": 2.890058801056645e-05,
|
| 874 |
+
"loss": 2.3019,
|
| 875 |
+
"step": 119
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 1.0,
|
| 879 |
+
"grad_norm": 0.07264812367438842,
|
| 880 |
+
"learning_rate": 2.8874589985793298e-05,
|
| 881 |
+
"loss": 2.3595,
|
| 882 |
+
"step": 120
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.0,
|
| 886 |
+
"eval_loss": 2.403914213180542,
|
| 887 |
+
"eval_runtime": 83.7377,
|
| 888 |
+
"eval_samples_per_second": 4.896,
|
| 889 |
+
"eval_steps_per_second": 0.31,
|
| 890 |
+
"step": 120
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 1.0083333333333333,
|
| 894 |
+
"grad_norm": 0.07480896711633409,
|
| 895 |
+
"learning_rate": 2.88483001256014e-05,
|
| 896 |
+
"loss": 2.317,
|
| 897 |
+
"step": 121
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.0166666666666666,
|
| 901 |
+
"grad_norm": 0.0778248987787842,
|
| 902 |
+
"learning_rate": 2.8821718982966544e-05,
|
| 903 |
+
"loss": 2.2862,
|
| 904 |
+
"step": 122
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.025,
|
| 908 |
+
"grad_norm": 0.07340098729165756,
|
| 909 |
+
"learning_rate": 2.87948471169913e-05,
|
| 910 |
+
"loss": 2.2822,
|
| 911 |
+
"step": 123
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 1.0333333333333334,
|
| 915 |
+
"grad_norm": 0.07287013757284508,
|
| 916 |
+
"learning_rate": 2.8767685092893244e-05,
|
| 917 |
+
"loss": 2.342,
|
| 918 |
+
"step": 124
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.0416666666666667,
|
| 922 |
+
"grad_norm": 0.07030809184951914,
|
| 923 |
+
"learning_rate": 2.874023348199311e-05,
|
| 924 |
+
"loss": 2.3806,
|
| 925 |
+
"step": 125
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 1.05,
|
| 929 |
+
"grad_norm": 0.0733645423823853,
|
| 930 |
+
"learning_rate": 2.8712492861702712e-05,
|
| 931 |
+
"loss": 2.2692,
|
| 932 |
+
"step": 126
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 1.0583333333333333,
|
| 936 |
+
"grad_norm": 0.07287825367685795,
|
| 937 |
+
"learning_rate": 2.868446381551285e-05,
|
| 938 |
+
"loss": 2.3364,
|
| 939 |
+
"step": 127
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.0666666666666667,
|
| 943 |
+
"grad_norm": 0.07473650904660553,
|
| 944 |
+
"learning_rate": 2.865614693298101e-05,
|
| 945 |
+
"loss": 2.3502,
|
| 946 |
+
"step": 128
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.075,
|
| 950 |
+
"grad_norm": 0.07321912360621033,
|
| 951 |
+
"learning_rate": 2.8627542809718972e-05,
|
| 952 |
+
"loss": 2.3626,
|
| 953 |
+
"step": 129
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.0833333333333333,
|
| 957 |
+
"grad_norm": 0.07448062787949941,
|
| 958 |
+
"learning_rate": 2.8598652047380292e-05,
|
| 959 |
+
"loss": 2.337,
|
| 960 |
+
"step": 130
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.0916666666666666,
|
| 964 |
+
"grad_norm": 0.07065756005819214,
|
| 965 |
+
"learning_rate": 2.8569475253647624e-05,
|
| 966 |
+
"loss": 2.3204,
|
| 967 |
+
"step": 131
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 1.1,
|
| 971 |
+
"grad_norm": 0.0766194683444267,
|
| 972 |
+
"learning_rate": 2.854001304221995e-05,
|
| 973 |
+
"loss": 2.3167,
|
| 974 |
+
"step": 132
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 1.1083333333333334,
|
| 978 |
+
"grad_norm": 0.07557760418231135,
|
| 979 |
+
"learning_rate": 2.8510266032799688e-05,
|
| 980 |
+
"loss": 2.368,
|
| 981 |
+
"step": 133
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 1.1166666666666667,
|
| 985 |
+
"grad_norm": 0.07643475971713251,
|
| 986 |
+
"learning_rate": 2.8480234851079622e-05,
|
| 987 |
+
"loss": 2.3513,
|
| 988 |
+
"step": 134
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.125,
|
| 992 |
+
"grad_norm": 0.07714909609902056,
|
| 993 |
+
"learning_rate": 2.8449920128729772e-05,
|
| 994 |
+
"loss": 2.319,
|
| 995 |
+
"step": 135
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.1333333333333333,
|
| 999 |
+
"grad_norm": 0.07811716801982814,
|
| 1000 |
+
"learning_rate": 2.841932250338409e-05,
|
| 1001 |
+
"loss": 2.3433,
|
| 1002 |
+
"step": 136
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.1416666666666666,
|
| 1006 |
+
"grad_norm": 0.07508100256442016,
|
| 1007 |
+
"learning_rate": 2.8388442618627063e-05,
|
| 1008 |
+
"loss": 2.3416,
|
| 1009 |
+
"step": 137
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.15,
|
| 1013 |
+
"grad_norm": 0.0756775152631437,
|
| 1014 |
+
"learning_rate": 2.8357281123980153e-05,
|
| 1015 |
+
"loss": 2.3981,
|
| 1016 |
+
"step": 138
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.1583333333333332,
|
| 1020 |
+
"grad_norm": 0.07358822605664081,
|
| 1021 |
+
"learning_rate": 2.8325838674888168e-05,
|
| 1022 |
+
"loss": 2.3167,
|
| 1023 |
+
"step": 139
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 1.1666666666666667,
|
| 1027 |
+
"grad_norm": 0.0720109732701513,
|
| 1028 |
+
"learning_rate": 2.829411593270545e-05,
|
| 1029 |
+
"loss": 2.2876,
|
| 1030 |
+
"step": 140
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.175,
|
| 1034 |
+
"grad_norm": 0.0725580802145492,
|
| 1035 |
+
"learning_rate": 2.826211356468196e-05,
|
| 1036 |
+
"loss": 2.3034,
|
| 1037 |
+
"step": 141
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.1833333333333333,
|
| 1041 |
+
"grad_norm": 0.07621163506022388,
|
| 1042 |
+
"learning_rate": 2.822983224394926e-05,
|
| 1043 |
+
"loss": 2.3539,
|
| 1044 |
+
"step": 142
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.1916666666666667,
|
| 1048 |
+
"grad_norm": 0.0771855916894155,
|
| 1049 |
+
"learning_rate": 2.8197272649506363e-05,
|
| 1050 |
+
"loss": 2.2996,
|
| 1051 |
+
"step": 143
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 1.2,
|
| 1055 |
+
"grad_norm": 0.08066719007957443,
|
| 1056 |
+
"learning_rate": 2.8164435466205423e-05,
|
| 1057 |
+
"loss": 2.3202,
|
| 1058 |
+
"step": 144
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.2083333333333333,
|
| 1062 |
+
"grad_norm": 0.07696986682658112,
|
| 1063 |
+
"learning_rate": 2.8131321384737344e-05,
|
| 1064 |
+
"loss": 2.3665,
|
| 1065 |
+
"step": 145
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 1.2166666666666668,
|
| 1069 |
+
"grad_norm": 0.0797897360414332,
|
| 1070 |
+
"learning_rate": 2.809793110161725e-05,
|
| 1071 |
+
"loss": 2.2993,
|
| 1072 |
+
"step": 146
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.225,
|
| 1076 |
+
"grad_norm": 0.07683343920053876,
|
| 1077 |
+
"learning_rate": 2.8064265319169854e-05,
|
| 1078 |
+
"loss": 2.349,
|
| 1079 |
+
"step": 147
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.2333333333333334,
|
| 1083 |
+
"grad_norm": 0.07241754893718985,
|
| 1084 |
+
"learning_rate": 2.803032474551465e-05,
|
| 1085 |
+
"loss": 2.3785,
|
| 1086 |
+
"step": 148
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.2416666666666667,
|
| 1090 |
+
"grad_norm": 0.07487824121705405,
|
| 1091 |
+
"learning_rate": 2.799611009455104e-05,
|
| 1092 |
+
"loss": 2.334,
|
| 1093 |
+
"step": 149
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 1.25,
|
| 1097 |
+
"grad_norm": 0.08111734533681639,
|
| 1098 |
+
"learning_rate": 2.7961622085943317e-05,
|
| 1099 |
+
"loss": 2.3078,
|
| 1100 |
+
"step": 150
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.25,
|
| 1104 |
+
"eval_loss": 2.3990862369537354,
|
| 1105 |
+
"eval_runtime": 82.2028,
|
| 1106 |
+
"eval_samples_per_second": 4.988,
|
| 1107 |
+
"eval_steps_per_second": 0.316,
|
| 1108 |
+
"step": 150
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.2583333333333333,
|
| 1112 |
+
"grad_norm": 0.07410680960635908,
|
| 1113 |
+
"learning_rate": 2.792686144510553e-05,
|
| 1114 |
+
"loss": 2.3399,
|
| 1115 |
+
"step": 151
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.2666666666666666,
|
| 1119 |
+
"grad_norm": 0.07919176088565466,
|
| 1120 |
+
"learning_rate": 2.789182890318621e-05,
|
| 1121 |
+
"loss": 2.2759,
|
| 1122 |
+
"step": 152
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.275,
|
| 1126 |
+
"grad_norm": 0.0773107719699692,
|
| 1127 |
+
"learning_rate": 2.785652519705301e-05,
|
| 1128 |
+
"loss": 2.3227,
|
| 1129 |
+
"step": 153
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.2833333333333332,
|
| 1133 |
+
"grad_norm": 0.07673682296386927,
|
| 1134 |
+
"learning_rate": 2.78209510692772e-05,
|
| 1135 |
+
"loss": 2.3764,
|
| 1136 |
+
"step": 154
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.2916666666666667,
|
| 1140 |
+
"grad_norm": 0.07494906306802604,
|
| 1141 |
+
"learning_rate": 2.778510726811804e-05,
|
| 1142 |
+
"loss": 2.3748,
|
| 1143 |
+
"step": 155
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.3,
|
| 1147 |
+
"grad_norm": 0.07829386850229311,
|
| 1148 |
+
"learning_rate": 2.7748994547507052e-05,
|
| 1149 |
+
"loss": 2.3942,
|
| 1150 |
+
"step": 156
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.3083333333333333,
|
| 1154 |
+
"grad_norm": 0.08779084724549921,
|
| 1155 |
+
"learning_rate": 2.7712613667032156e-05,
|
| 1156 |
+
"loss": 2.3463,
|
| 1157 |
+
"step": 157
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.3166666666666667,
|
| 1161 |
+
"grad_norm": 0.07517053471363216,
|
| 1162 |
+
"learning_rate": 2.7675965391921692e-05,
|
| 1163 |
+
"loss": 2.3492,
|
| 1164 |
+
"step": 158
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.325,
|
| 1168 |
+
"grad_norm": 0.0800585974142145,
|
| 1169 |
+
"learning_rate": 2.763905049302833e-05,
|
| 1170 |
+
"loss": 2.3737,
|
| 1171 |
+
"step": 159
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.3333333333333333,
|
| 1175 |
+
"grad_norm": 0.08334597499532556,
|
| 1176 |
+
"learning_rate": 2.7601869746812855e-05,
|
| 1177 |
+
"loss": 2.4046,
|
| 1178 |
+
"step": 160
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.3416666666666668,
|
| 1182 |
+
"grad_norm": 0.08071110969898845,
|
| 1183 |
+
"learning_rate": 2.7564423935327817e-05,
|
| 1184 |
+
"loss": 2.3333,
|
| 1185 |
+
"step": 161
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.35,
|
| 1189 |
+
"grad_norm": 0.08294979244502722,
|
| 1190 |
+
"learning_rate": 2.7526713846201118e-05,
|
| 1191 |
+
"loss": 2.3102,
|
| 1192 |
+
"step": 162
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.3583333333333334,
|
| 1196 |
+
"grad_norm": 0.0802439928020502,
|
| 1197 |
+
"learning_rate": 2.7488740272619413e-05,
|
| 1198 |
+
"loss": 2.353,
|
| 1199 |
+
"step": 163
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.3666666666666667,
|
| 1203 |
+
"grad_norm": 0.08806208048762097,
|
| 1204 |
+
"learning_rate": 2.7450504013311443e-05,
|
| 1205 |
+
"loss": 2.3369,
|
| 1206 |
+
"step": 164
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.375,
|
| 1210 |
+
"grad_norm": 0.08212138080706365,
|
| 1211 |
+
"learning_rate": 2.7412005872531222e-05,
|
| 1212 |
+
"loss": 2.3758,
|
| 1213 |
+
"step": 165
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.3833333333333333,
|
| 1217 |
+
"grad_norm": 0.08189281417532208,
|
| 1218 |
+
"learning_rate": 2.737324666004113e-05,
|
| 1219 |
+
"loss": 2.3641,
|
| 1220 |
+
"step": 166
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.3916666666666666,
|
| 1224 |
+
"grad_norm": 0.0762698736915918,
|
| 1225 |
+
"learning_rate": 2.7334227191094885e-05,
|
| 1226 |
+
"loss": 2.3554,
|
| 1227 |
+
"step": 167
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.4,
|
| 1231 |
+
"grad_norm": 0.07699984398440281,
|
| 1232 |
+
"learning_rate": 2.729494828642038e-05,
|
| 1233 |
+
"loss": 2.2807,
|
| 1234 |
+
"step": 168
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.4083333333333332,
|
| 1238 |
+
"grad_norm": 0.08654873437940762,
|
| 1239 |
+
"learning_rate": 2.7255410772202435e-05,
|
| 1240 |
+
"loss": 2.2587,
|
| 1241 |
+
"step": 169
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.4166666666666667,
|
| 1245 |
+
"grad_norm": 0.07862334895836863,
|
| 1246 |
+
"learning_rate": 2.7215615480065415e-05,
|
| 1247 |
+
"loss": 2.305,
|
| 1248 |
+
"step": 170
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.425,
|
| 1252 |
+
"grad_norm": 0.09636306747120471,
|
| 1253 |
+
"learning_rate": 2.7175563247055723e-05,
|
| 1254 |
+
"loss": 2.2845,
|
| 1255 |
+
"step": 171
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.4333333333333333,
|
| 1259 |
+
"grad_norm": 0.08121423059528599,
|
| 1260 |
+
"learning_rate": 2.7135254915624213e-05,
|
| 1261 |
+
"loss": 2.3014,
|
| 1262 |
+
"step": 172
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.4416666666666667,
|
| 1266 |
+
"grad_norm": 0.08240895710232157,
|
| 1267 |
+
"learning_rate": 2.709469133360847e-05,
|
| 1268 |
+
"loss": 2.3146,
|
| 1269 |
+
"step": 173
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.45,
|
| 1273 |
+
"grad_norm": 0.09590313378847529,
|
| 1274 |
+
"learning_rate": 2.7053873354214957e-05,
|
| 1275 |
+
"loss": 2.385,
|
| 1276 |
+
"step": 174
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.4583333333333333,
|
| 1280 |
+
"grad_norm": 0.07646920461728485,
|
| 1281 |
+
"learning_rate": 2.7012801836001098e-05,
|
| 1282 |
+
"loss": 2.3091,
|
| 1283 |
+
"step": 175
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.4666666666666668,
|
| 1287 |
+
"grad_norm": 0.085281063563692,
|
| 1288 |
+
"learning_rate": 2.6971477642857185e-05,
|
| 1289 |
+
"loss": 2.3367,
|
| 1290 |
+
"step": 176
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.475,
|
| 1294 |
+
"grad_norm": 0.083396061500332,
|
| 1295 |
+
"learning_rate": 2.6929901643988237e-05,
|
| 1296 |
+
"loss": 2.3087,
|
| 1297 |
+
"step": 177
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 1.4833333333333334,
|
| 1301 |
+
"grad_norm": 0.08117328159675918,
|
| 1302 |
+
"learning_rate": 2.6888074713895705e-05,
|
| 1303 |
+
"loss": 2.3476,
|
| 1304 |
+
"step": 178
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.4916666666666667,
|
| 1308 |
+
"grad_norm": 0.08724201561764477,
|
| 1309 |
+
"learning_rate": 2.6845997732359074e-05,
|
| 1310 |
+
"loss": 2.3273,
|
| 1311 |
+
"step": 179
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 1.5,
|
| 1315 |
+
"grad_norm": 0.09378887412660228,
|
| 1316 |
+
"learning_rate": 2.680367158441736e-05,
|
| 1317 |
+
"loss": 2.3111,
|
| 1318 |
+
"step": 180
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.5,
|
| 1322 |
+
"eval_loss": 2.395205497741699,
|
| 1323 |
+
"eval_runtime": 83.2768,
|
| 1324 |
+
"eval_samples_per_second": 4.923,
|
| 1325 |
+
"eval_steps_per_second": 0.312,
|
| 1326 |
+
"step": 180
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.5083333333333333,
|
| 1330 |
+
"grad_norm": 0.07954334072363729,
|
| 1331 |
+
"learning_rate": 2.676109716035051e-05,
|
| 1332 |
+
"loss": 2.3557,
|
| 1333 |
+
"step": 181
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.5166666666666666,
|
| 1337 |
+
"grad_norm": 0.07924563318720515,
|
| 1338 |
+
"learning_rate": 2.6718275355660643e-05,
|
| 1339 |
+
"loss": 2.3211,
|
| 1340 |
+
"step": 182
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.525,
|
| 1344 |
+
"grad_norm": 0.08323935887429414,
|
| 1345 |
+
"learning_rate": 2.667520707105325e-05,
|
| 1346 |
+
"loss": 2.3736,
|
| 1347 |
+
"step": 183
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.5333333333333332,
|
| 1351 |
+
"grad_norm": 0.08811426671935672,
|
| 1352 |
+
"learning_rate": 2.6631893212418227e-05,
|
| 1353 |
+
"loss": 2.3516,
|
| 1354 |
+
"step": 184
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.5416666666666665,
|
| 1358 |
+
"grad_norm": 0.0888384867597831,
|
| 1359 |
+
"learning_rate": 2.6588334690810826e-05,
|
| 1360 |
+
"loss": 2.35,
|
| 1361 |
+
"step": 185
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.55,
|
| 1365 |
+
"grad_norm": 0.0889928409338763,
|
| 1366 |
+
"learning_rate": 2.654453242243249e-05,
|
| 1367 |
+
"loss": 2.3909,
|
| 1368 |
+
"step": 186
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.5583333333333333,
|
| 1372 |
+
"grad_norm": 0.08110387583744016,
|
| 1373 |
+
"learning_rate": 2.6500487328611584e-05,
|
| 1374 |
+
"loss": 2.3173,
|
| 1375 |
+
"step": 187
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.5666666666666667,
|
| 1379 |
+
"grad_norm": 0.09467045149191018,
|
| 1380 |
+
"learning_rate": 2.645620033578402e-05,
|
| 1381 |
+
"loss": 2.3113,
|
| 1382 |
+
"step": 188
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.575,
|
| 1386 |
+
"grad_norm": 0.08469896453007436,
|
| 1387 |
+
"learning_rate": 2.6411672375473768e-05,
|
| 1388 |
+
"loss": 2.3217,
|
| 1389 |
+
"step": 189
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.5833333333333335,
|
| 1393 |
+
"grad_norm": 0.07945600872115115,
|
| 1394 |
+
"learning_rate": 2.6366904384273252e-05,
|
| 1395 |
+
"loss": 2.3258,
|
| 1396 |
+
"step": 190
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.5916666666666668,
|
| 1400 |
+
"grad_norm": 0.08574116477782197,
|
| 1401 |
+
"learning_rate": 2.6321897303823665e-05,
|
| 1402 |
+
"loss": 2.3321,
|
| 1403 |
+
"step": 191
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.6,
|
| 1407 |
+
"grad_norm": 0.08485565209453155,
|
| 1408 |
+
"learning_rate": 2.6276652080795157e-05,
|
| 1409 |
+
"loss": 2.342,
|
| 1410 |
+
"step": 192
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.6083333333333334,
|
| 1414 |
+
"grad_norm": 0.07725287902528816,
|
| 1415 |
+
"learning_rate": 2.6231169666866928e-05,
|
| 1416 |
+
"loss": 2.3362,
|
| 1417 |
+
"step": 193
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.6166666666666667,
|
| 1421 |
+
"grad_norm": 0.08818900103678802,
|
| 1422 |
+
"learning_rate": 2.6185451018707188e-05,
|
| 1423 |
+
"loss": 2.3198,
|
| 1424 |
+
"step": 194
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.625,
|
| 1428 |
+
"grad_norm": 0.08485155874971982,
|
| 1429 |
+
"learning_rate": 2.613949709795307e-05,
|
| 1430 |
+
"loss": 2.3147,
|
| 1431 |
+
"step": 195
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.6333333333333333,
|
| 1435 |
+
"grad_norm": 0.08366087834553593,
|
| 1436 |
+
"learning_rate": 2.6093308871190376e-05,
|
| 1437 |
+
"loss": 2.3575,
|
| 1438 |
+
"step": 196
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.6416666666666666,
|
| 1442 |
+
"grad_norm": 0.0879781017638792,
|
| 1443 |
+
"learning_rate": 2.6046887309933252e-05,
|
| 1444 |
+
"loss": 2.3153,
|
| 1445 |
+
"step": 197
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.65,
|
| 1449 |
+
"grad_norm": 0.0770476452180406,
|
| 1450 |
+
"learning_rate": 2.6000233390603764e-05,
|
| 1451 |
+
"loss": 2.2348,
|
| 1452 |
+
"step": 198
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.6583333333333332,
|
| 1456 |
+
"grad_norm": 0.08097094735261377,
|
| 1457 |
+
"learning_rate": 2.595334809451135e-05,
|
| 1458 |
+
"loss": 2.314,
|
| 1459 |
+
"step": 199
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.6666666666666665,
|
| 1463 |
+
"grad_norm": 0.0843743968162187,
|
| 1464 |
+
"learning_rate": 2.590623240783217e-05,
|
| 1465 |
+
"loss": 2.3729,
|
| 1466 |
+
"step": 200
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.675,
|
| 1470 |
+
"grad_norm": 0.08031606646613978,
|
| 1471 |
+
"learning_rate": 2.5858887321588403e-05,
|
| 1472 |
+
"loss": 2.2832,
|
| 1473 |
+
"step": 201
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.6833333333333333,
|
| 1477 |
+
"grad_norm": 0.07861724615060135,
|
| 1478 |
+
"learning_rate": 2.5811313831627343e-05,
|
| 1479 |
+
"loss": 2.3499,
|
| 1480 |
+
"step": 202
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.6916666666666667,
|
| 1484 |
+
"grad_norm": 0.08096750755479619,
|
| 1485 |
+
"learning_rate": 2.5763512938600496e-05,
|
| 1486 |
+
"loss": 2.3395,
|
| 1487 |
+
"step": 203
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.7,
|
| 1491 |
+
"grad_norm": 0.08269576014108336,
|
| 1492 |
+
"learning_rate": 2.5715485647942526e-05,
|
| 1493 |
+
"loss": 2.3492,
|
| 1494 |
+
"step": 204
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.7083333333333335,
|
| 1498 |
+
"grad_norm": 0.0817344955360849,
|
| 1499 |
+
"learning_rate": 2.566723296985009e-05,
|
| 1500 |
+
"loss": 2.3109,
|
| 1501 |
+
"step": 205
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.7166666666666668,
|
| 1505 |
+
"grad_norm": 0.08754980954018836,
|
| 1506 |
+
"learning_rate": 2.561875591926061e-05,
|
| 1507 |
+
"loss": 2.3365,
|
| 1508 |
+
"step": 206
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.725,
|
| 1512 |
+
"grad_norm": 0.08561587081140326,
|
| 1513 |
+
"learning_rate": 2.55700555158309e-05,
|
| 1514 |
+
"loss": 2.3286,
|
| 1515 |
+
"step": 207
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.7333333333333334,
|
| 1519 |
+
"grad_norm": 0.08669735781585357,
|
| 1520 |
+
"learning_rate": 2.552113278391575e-05,
|
| 1521 |
+
"loss": 2.3257,
|
| 1522 |
+
"step": 208
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.7416666666666667,
|
| 1526 |
+
"grad_norm": 0.08363145499451642,
|
| 1527 |
+
"learning_rate": 2.5471988752546358e-05,
|
| 1528 |
+
"loss": 2.3544,
|
| 1529 |
+
"step": 209
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.75,
|
| 1533 |
+
"grad_norm": 0.08027509930016731,
|
| 1534 |
+
"learning_rate": 2.542262445540869e-05,
|
| 1535 |
+
"loss": 2.3331,
|
| 1536 |
+
"step": 210
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.75,
|
| 1540 |
+
"eval_loss": 2.391552209854126,
|
| 1541 |
+
"eval_runtime": 83.4548,
|
| 1542 |
+
"eval_samples_per_second": 4.913,
|
| 1543 |
+
"eval_steps_per_second": 0.312,
|
| 1544 |
+
"step": 210
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.7583333333333333,
|
| 1548 |
+
"grad_norm": 0.08202472239637462,
|
| 1549 |
+
"learning_rate": 2.5373040930821747e-05,
|
| 1550 |
+
"loss": 2.324,
|
| 1551 |
+
"step": 211
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 1.7666666666666666,
|
| 1555 |
+
"grad_norm": 0.08048755873369126,
|
| 1556 |
+
"learning_rate": 2.5323239221715704e-05,
|
| 1557 |
+
"loss": 2.3371,
|
| 1558 |
+
"step": 212
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 1.775,
|
| 1562 |
+
"grad_norm": 0.0825702244254376,
|
| 1563 |
+
"learning_rate": 2.5273220375609993e-05,
|
| 1564 |
+
"loss": 2.3154,
|
| 1565 |
+
"step": 213
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 1.7833333333333332,
|
| 1569 |
+
"grad_norm": 0.08665151588048187,
|
| 1570 |
+
"learning_rate": 2.5222985444591268e-05,
|
| 1571 |
+
"loss": 2.3245,
|
| 1572 |
+
"step": 214
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 1.7916666666666665,
|
| 1576 |
+
"grad_norm": 0.08708672459127094,
|
| 1577 |
+
"learning_rate": 2.5172535485291263e-05,
|
| 1578 |
+
"loss": 2.2274,
|
| 1579 |
+
"step": 215
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.8,
|
| 1583 |
+
"grad_norm": 0.07828555600912761,
|
| 1584 |
+
"learning_rate": 2.5121871558864588e-05,
|
| 1585 |
+
"loss": 2.3531,
|
| 1586 |
+
"step": 216
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.8083333333333333,
|
| 1590 |
+
"grad_norm": 0.08203104952103267,
|
| 1591 |
+
"learning_rate": 2.5070994730966375e-05,
|
| 1592 |
+
"loss": 2.3679,
|
| 1593 |
+
"step": 217
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 1.8166666666666667,
|
| 1597 |
+
"grad_norm": 0.07994057166419617,
|
| 1598 |
+
"learning_rate": 2.5019906071729905e-05,
|
| 1599 |
+
"loss": 2.356,
|
| 1600 |
+
"step": 218
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 1.825,
|
| 1604 |
+
"grad_norm": 0.0772999399406611,
|
| 1605 |
+
"learning_rate": 2.496860665574406e-05,
|
| 1606 |
+
"loss": 2.3588,
|
| 1607 |
+
"step": 219
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 1.8333333333333335,
|
| 1611 |
+
"grad_norm": 0.07789663921645798,
|
| 1612 |
+
"learning_rate": 2.4917097562030756e-05,
|
| 1613 |
+
"loss": 2.3736,
|
| 1614 |
+
"step": 220
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 1.8416666666666668,
|
| 1618 |
+
"grad_norm": 0.08499804967078164,
|
| 1619 |
+
"learning_rate": 2.4865379874022212e-05,
|
| 1620 |
+
"loss": 2.3694,
|
| 1621 |
+
"step": 221
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 1.85,
|
| 1625 |
+
"grad_norm": 0.08093947726076711,
|
| 1626 |
+
"learning_rate": 2.4813454679538192e-05,
|
| 1627 |
+
"loss": 2.3803,
|
| 1628 |
+
"step": 222
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.8583333333333334,
|
| 1632 |
+
"grad_norm": 0.08181400525359299,
|
| 1633 |
+
"learning_rate": 2.4761323070763103e-05,
|
| 1634 |
+
"loss": 2.3288,
|
| 1635 |
+
"step": 223
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 1.8666666666666667,
|
| 1639 |
+
"grad_norm": 0.08289317209784214,
|
| 1640 |
+
"learning_rate": 2.4708986144223038e-05,
|
| 1641 |
+
"loss": 2.2828,
|
| 1642 |
+
"step": 224
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.875,
|
| 1646 |
+
"grad_norm": 0.09327166185188862,
|
| 1647 |
+
"learning_rate": 2.4656445000762695e-05,
|
| 1648 |
+
"loss": 2.3583,
|
| 1649 |
+
"step": 225
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 1.8833333333333333,
|
| 1653 |
+
"grad_norm": 0.08168227681435707,
|
| 1654 |
+
"learning_rate": 2.4603700745522238e-05,
|
| 1655 |
+
"loss": 2.2695,
|
| 1656 |
+
"step": 226
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 1.8916666666666666,
|
| 1660 |
+
"grad_norm": 0.08545164055562673,
|
| 1661 |
+
"learning_rate": 2.455075448791403e-05,
|
| 1662 |
+
"loss": 2.2865,
|
| 1663 |
+
"step": 227
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 1.9,
|
| 1667 |
+
"grad_norm": 0.08202820719250954,
|
| 1668 |
+
"learning_rate": 2.4497607341599338e-05,
|
| 1669 |
+
"loss": 2.3393,
|
| 1670 |
+
"step": 228
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.9083333333333332,
|
| 1674 |
+
"grad_norm": 0.08242341586624266,
|
| 1675 |
+
"learning_rate": 2.444426042446486e-05,
|
| 1676 |
+
"loss": 2.3055,
|
| 1677 |
+
"step": 229
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 1.9166666666666665,
|
| 1681 |
+
"grad_norm": 0.08265819878861275,
|
| 1682 |
+
"learning_rate": 2.439071485859924e-05,
|
| 1683 |
+
"loss": 2.3281,
|
| 1684 |
+
"step": 230
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 1.925,
|
| 1688 |
+
"grad_norm": 0.07905640613602864,
|
| 1689 |
+
"learning_rate": 2.433697177026947e-05,
|
| 1690 |
+
"loss": 2.3433,
|
| 1691 |
+
"step": 231
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 1.9333333333333333,
|
| 1695 |
+
"grad_norm": 0.07589804976666019,
|
| 1696 |
+
"learning_rate": 2.4283032289897184e-05,
|
| 1697 |
+
"loss": 2.3877,
|
| 1698 |
+
"step": 232
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.9416666666666667,
|
| 1702 |
+
"grad_norm": 0.08607617064906946,
|
| 1703 |
+
"learning_rate": 2.4228897552034885e-05,
|
| 1704 |
+
"loss": 2.3055,
|
| 1705 |
+
"step": 233
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 1.95,
|
| 1709 |
+
"grad_norm": 0.08247034169495676,
|
| 1710 |
+
"learning_rate": 2.417456869534209e-05,
|
| 1711 |
+
"loss": 2.3617,
|
| 1712 |
+
"step": 234
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.9583333333333335,
|
| 1716 |
+
"grad_norm": 0.08205818777619443,
|
| 1717 |
+
"learning_rate": 2.4120046862561367e-05,
|
| 1718 |
+
"loss": 2.3521,
|
| 1719 |
+
"step": 235
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 1.9666666666666668,
|
| 1723 |
+
"grad_norm": 0.08960035910392279,
|
| 1724 |
+
"learning_rate": 2.406533320049431e-05,
|
| 1725 |
+
"loss": 2.3191,
|
| 1726 |
+
"step": 236
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 1.975,
|
| 1730 |
+
"grad_norm": 0.08414207451637007,
|
| 1731 |
+
"learning_rate": 2.4010428859977416e-05,
|
| 1732 |
+
"loss": 2.33,
|
| 1733 |
+
"step": 237
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 1.9833333333333334,
|
| 1737 |
+
"grad_norm": 0.0869050320933055,
|
| 1738 |
+
"learning_rate": 2.3955334995857866e-05,
|
| 1739 |
+
"loss": 2.3498,
|
| 1740 |
+
"step": 238
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 1.9916666666666667,
|
| 1744 |
+
"grad_norm": 0.08578810106178472,
|
| 1745 |
+
"learning_rate": 2.3900052766969252e-05,
|
| 1746 |
+
"loss": 2.2954,
|
| 1747 |
+
"step": 239
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 2.0,
|
| 1751 |
+
"grad_norm": 0.0793300092493953,
|
| 1752 |
+
"learning_rate": 2.3844583336107192e-05,
|
| 1753 |
+
"loss": 2.2758,
|
| 1754 |
+
"step": 240
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 2.0,
|
| 1758 |
+
"eval_loss": 2.3888721466064453,
|
| 1759 |
+
"eval_runtime": 82.3344,
|
| 1760 |
+
"eval_samples_per_second": 4.98,
|
| 1761 |
+
"eval_steps_per_second": 0.316,
|
| 1762 |
+
"step": 240
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.0083333333333333,
|
| 1766 |
+
"grad_norm": 0.08723295859544726,
|
| 1767 |
+
"learning_rate": 2.378892787000487e-05,
|
| 1768 |
+
"loss": 2.3322,
|
| 1769 |
+
"step": 241
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.0166666666666666,
|
| 1773 |
+
"grad_norm": 0.08469708661157217,
|
| 1774 |
+
"learning_rate": 2.37330875393085e-05,
|
| 1775 |
+
"loss": 2.2966,
|
| 1776 |
+
"step": 242
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 2.025,
|
| 1780 |
+
"grad_norm": 0.08282651743293705,
|
| 1781 |
+
"learning_rate": 2.3677063518552706e-05,
|
| 1782 |
+
"loss": 2.2983,
|
| 1783 |
+
"step": 243
|
| 1784 |
+
},
|
| 1785 |
+
{
|
| 1786 |
+
"epoch": 2.033333333333333,
|
| 1787 |
+
"grad_norm": 0.082576862949257,
|
| 1788 |
+
"learning_rate": 2.3620856986135807e-05,
|
| 1789 |
+
"loss": 2.3013,
|
| 1790 |
+
"step": 244
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 2.0416666666666665,
|
| 1794 |
+
"grad_norm": 0.0785765784725401,
|
| 1795 |
+
"learning_rate": 2.356446912429504e-05,
|
| 1796 |
+
"loss": 2.3645,
|
| 1797 |
+
"step": 245
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 2.05,
|
| 1801 |
+
"grad_norm": 0.0857637475909411,
|
| 1802 |
+
"learning_rate": 2.3507901119081694e-05,
|
| 1803 |
+
"loss": 2.2651,
|
| 1804 |
+
"step": 246
|
| 1805 |
+
},
|
| 1806 |
+
{
|
| 1807 |
+
"epoch": 2.058333333333333,
|
| 1808 |
+
"grad_norm": 0.08434021871800561,
|
| 1809 |
+
"learning_rate": 2.3451154160336145e-05,
|
| 1810 |
+
"loss": 2.2378,
|
| 1811 |
+
"step": 247
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 2.066666666666667,
|
| 1815 |
+
"grad_norm": 0.08314862536900369,
|
| 1816 |
+
"learning_rate": 2.3394229441662863e-05,
|
| 1817 |
+
"loss": 2.3237,
|
| 1818 |
+
"step": 248
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 2.075,
|
| 1822 |
+
"grad_norm": 0.08880923154869763,
|
| 1823 |
+
"learning_rate": 2.3337128160405262e-05,
|
| 1824 |
+
"loss": 2.3238,
|
| 1825 |
+
"step": 249
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"epoch": 2.0833333333333335,
|
| 1829 |
+
"grad_norm": 0.0850538530180267,
|
| 1830 |
+
"learning_rate": 2.3279851517620567e-05,
|
| 1831 |
+
"loss": 2.3204,
|
| 1832 |
+
"step": 250
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 2.091666666666667,
|
| 1836 |
+
"grad_norm": 0.07967139338292833,
|
| 1837 |
+
"learning_rate": 2.322240071805449e-05,
|
| 1838 |
+
"loss": 2.3132,
|
| 1839 |
+
"step": 251
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 2.1,
|
| 1843 |
+
"grad_norm": 0.08917392480325348,
|
| 1844 |
+
"learning_rate": 2.3164776970115952e-05,
|
| 1845 |
+
"loss": 2.2813,
|
| 1846 |
+
"step": 252
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 2.1083333333333334,
|
| 1850 |
+
"grad_norm": 0.08039683717145692,
|
| 1851 |
+
"learning_rate": 2.310698148585162e-05,
|
| 1852 |
+
"loss": 2.3244,
|
| 1853 |
+
"step": 253
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 2.1166666666666667,
|
| 1857 |
+
"grad_norm": 0.09041667420915349,
|
| 1858 |
+
"learning_rate": 2.3049015480920432e-05,
|
| 1859 |
+
"loss": 2.3195,
|
| 1860 |
+
"step": 254
|
| 1861 |
+
},
|
| 1862 |
+
{
|
| 1863 |
+
"epoch": 2.125,
|
| 1864 |
+
"grad_norm": 0.08459980536727492,
|
| 1865 |
+
"learning_rate": 2.299088017456803e-05,
|
| 1866 |
+
"loss": 2.3171,
|
| 1867 |
+
"step": 255
|
| 1868 |
+
},
|
| 1869 |
+
{
|
| 1870 |
+
"epoch": 2.1333333333333333,
|
| 1871 |
+
"grad_norm": 0.08343675306303033,
|
| 1872 |
+
"learning_rate": 2.29325767896011e-05,
|
| 1873 |
+
"loss": 2.3048,
|
| 1874 |
+
"step": 256
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 2.1416666666666666,
|
| 1878 |
+
"grad_norm": 0.08099287382142892,
|
| 1879 |
+
"learning_rate": 2.2874106552361672e-05,
|
| 1880 |
+
"loss": 2.3059,
|
| 1881 |
+
"step": 257
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 2.15,
|
| 1885 |
+
"grad_norm": 0.07937262238410536,
|
| 1886 |
+
"learning_rate": 2.2815470692701305e-05,
|
| 1887 |
+
"loss": 2.2877,
|
| 1888 |
+
"step": 258
|
| 1889 |
+
},
|
| 1890 |
+
{
|
| 1891 |
+
"epoch": 2.158333333333333,
|
| 1892 |
+
"grad_norm": 0.08341821425997771,
|
| 1893 |
+
"learning_rate": 2.2756670443955236e-05,
|
| 1894 |
+
"loss": 2.3399,
|
| 1895 |
+
"step": 259
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 2.1666666666666665,
|
| 1899 |
+
"grad_norm": 0.08535715101291032,
|
| 1900 |
+
"learning_rate": 2.2697707042916415e-05,
|
| 1901 |
+
"loss": 2.2755,
|
| 1902 |
+
"step": 260
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 2.175,
|
| 1906 |
+
"grad_norm": 0.08254168705233206,
|
| 1907 |
+
"learning_rate": 2.2638581729809522e-05,
|
| 1908 |
+
"loss": 2.275,
|
| 1909 |
+
"step": 261
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 2.183333333333333,
|
| 1913 |
+
"grad_norm": 0.0880860293354637,
|
| 1914 |
+
"learning_rate": 2.2579295748264856e-05,
|
| 1915 |
+
"loss": 2.3068,
|
| 1916 |
+
"step": 262
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 2.191666666666667,
|
| 1920 |
+
"grad_norm": 0.07778768378258252,
|
| 1921 |
+
"learning_rate": 2.2519850345292192e-05,
|
| 1922 |
+
"loss": 2.3463,
|
| 1923 |
+
"step": 263
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 2.2,
|
| 1927 |
+
"grad_norm": 0.08755949401201166,
|
| 1928 |
+
"learning_rate": 2.2460246771254525e-05,
|
| 1929 |
+
"loss": 2.2709,
|
| 1930 |
+
"step": 264
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.2083333333333335,
|
| 1934 |
+
"grad_norm": 0.08155138728608782,
|
| 1935 |
+
"learning_rate": 2.2400486279841812e-05,
|
| 1936 |
+
"loss": 2.3108,
|
| 1937 |
+
"step": 265
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 2.216666666666667,
|
| 1941 |
+
"grad_norm": 0.09198061908009642,
|
| 1942 |
+
"learning_rate": 2.2340570128044567e-05,
|
| 1943 |
+
"loss": 2.3252,
|
| 1944 |
+
"step": 266
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 2.225,
|
| 1948 |
+
"grad_norm": 0.0848127278556225,
|
| 1949 |
+
"learning_rate": 2.228049957612744e-05,
|
| 1950 |
+
"loss": 2.3125,
|
| 1951 |
+
"step": 267
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 2.2333333333333334,
|
| 1955 |
+
"grad_norm": 0.07962674081939877,
|
| 1956 |
+
"learning_rate": 2.2220275887602688e-05,
|
| 1957 |
+
"loss": 2.3439,
|
| 1958 |
+
"step": 268
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 2.2416666666666667,
|
| 1962 |
+
"grad_norm": 0.0789252857536788,
|
| 1963 |
+
"learning_rate": 2.2159900329203642e-05,
|
| 1964 |
+
"loss": 2.376,
|
| 1965 |
+
"step": 269
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 2.25,
|
| 1969 |
+
"grad_norm": 0.08588790644489314,
|
| 1970 |
+
"learning_rate": 2.2099374170858004e-05,
|
| 1971 |
+
"loss": 2.3227,
|
| 1972 |
+
"step": 270
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 2.25,
|
| 1976 |
+
"eval_loss": 2.3868563175201416,
|
| 1977 |
+
"eval_runtime": 82.3964,
|
| 1978 |
+
"eval_samples_per_second": 4.976,
|
| 1979 |
+
"eval_steps_per_second": 0.316,
|
| 1980 |
+
"step": 270
|
| 1981 |
+
},
|
| 1982 |
+
{
|
| 1983 |
+
"epoch": 2.2583333333333333,
|
| 1984 |
+
"grad_norm": 0.08143518675876504,
|
| 1985 |
+
"learning_rate": 2.2038698685661188e-05,
|
| 1986 |
+
"loss": 2.2619,
|
| 1987 |
+
"step": 271
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 2.2666666666666666,
|
| 1991 |
+
"grad_norm": 0.08181265893366352,
|
| 1992 |
+
"learning_rate": 2.197787514984951e-05,
|
| 1993 |
+
"loss": 2.2799,
|
| 1994 |
+
"step": 272
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.275,
|
| 1998 |
+
"grad_norm": 0.08692318411631018,
|
| 1999 |
+
"learning_rate": 2.1916904842773355e-05,
|
| 2000 |
+
"loss": 2.2678,
|
| 2001 |
+
"step": 273
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 2.283333333333333,
|
| 2005 |
+
"grad_norm": 0.0796260812866669,
|
| 2006 |
+
"learning_rate": 2.1855789046870265e-05,
|
| 2007 |
+
"loss": 2.3143,
|
| 2008 |
+
"step": 274
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 2.2916666666666665,
|
| 2012 |
+
"grad_norm": 0.07995224439929323,
|
| 2013 |
+
"learning_rate": 2.1794529047637962e-05,
|
| 2014 |
+
"loss": 2.3035,
|
| 2015 |
+
"step": 275
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 2.3,
|
| 2019 |
+
"grad_norm": 0.0834468598389171,
|
| 2020 |
+
"learning_rate": 2.1733126133607333e-05,
|
| 2021 |
+
"loss": 2.3495,
|
| 2022 |
+
"step": 276
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 2.3083333333333336,
|
| 2026 |
+
"grad_norm": 0.0804462393611705,
|
| 2027 |
+
"learning_rate": 2.1671581596315277e-05,
|
| 2028 |
+
"loss": 2.3439,
|
| 2029 |
+
"step": 277
|
| 2030 |
+
},
|
| 2031 |
+
{
|
| 2032 |
+
"epoch": 2.3166666666666664,
|
| 2033 |
+
"grad_norm": 0.08559248897449384,
|
| 2034 |
+
"learning_rate": 2.160989673027759e-05,
|
| 2035 |
+
"loss": 2.2537,
|
| 2036 |
+
"step": 278
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.325,
|
| 2040 |
+
"grad_norm": 0.08498696734874535,
|
| 2041 |
+
"learning_rate": 2.154807283296171e-05,
|
| 2042 |
+
"loss": 2.3353,
|
| 2043 |
+
"step": 279
|
| 2044 |
+
},
|
| 2045 |
+
{
|
| 2046 |
+
"epoch": 2.3333333333333335,
|
| 2047 |
+
"grad_norm": 0.08667886039237936,
|
| 2048 |
+
"learning_rate": 2.1486111204759425e-05,
|
| 2049 |
+
"loss": 2.2978,
|
| 2050 |
+
"step": 280
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 2.341666666666667,
|
| 2054 |
+
"grad_norm": 0.08344231665167223,
|
| 2055 |
+
"learning_rate": 2.1424013148959535e-05,
|
| 2056 |
+
"loss": 2.3378,
|
| 2057 |
+
"step": 281
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 2.35,
|
| 2061 |
+
"grad_norm": 0.08505870663781086,
|
| 2062 |
+
"learning_rate": 2.1361779971720438e-05,
|
| 2063 |
+
"loss": 2.3203,
|
| 2064 |
+
"step": 282
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 2.3583333333333334,
|
| 2068 |
+
"grad_norm": 0.08909063571659855,
|
| 2069 |
+
"learning_rate": 2.129941298204263e-05,
|
| 2070 |
+
"loss": 2.2983,
|
| 2071 |
+
"step": 283
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 2.3666666666666667,
|
| 2075 |
+
"grad_norm": 0.08448679637942494,
|
| 2076 |
+
"learning_rate": 2.1236913491741212e-05,
|
| 2077 |
+
"loss": 2.2759,
|
| 2078 |
+
"step": 284
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 2.375,
|
| 2082 |
+
"grad_norm": 0.08082991104323622,
|
| 2083 |
+
"learning_rate": 2.117428281541827e-05,
|
| 2084 |
+
"loss": 2.3324,
|
| 2085 |
+
"step": 285
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 2.3833333333333333,
|
| 2089 |
+
"grad_norm": 0.08409024458862085,
|
| 2090 |
+
"learning_rate": 2.1111522270435227e-05,
|
| 2091 |
+
"loss": 2.347,
|
| 2092 |
+
"step": 286
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 2.3916666666666666,
|
| 2096 |
+
"grad_norm": 0.08282724090583614,
|
| 2097 |
+
"learning_rate": 2.104863317688514e-05,
|
| 2098 |
+
"loss": 2.2209,
|
| 2099 |
+
"step": 287
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 2.4,
|
| 2103 |
+
"grad_norm": 0.08767424846482282,
|
| 2104 |
+
"learning_rate": 2.0985616857564933e-05,
|
| 2105 |
+
"loss": 2.2919,
|
| 2106 |
+
"step": 288
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 2.408333333333333,
|
| 2110 |
+
"grad_norm": 0.08366642126892197,
|
| 2111 |
+
"learning_rate": 2.0922474637947578e-05,
|
| 2112 |
+
"loss": 2.3481,
|
| 2113 |
+
"step": 289
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 2.4166666666666665,
|
| 2117 |
+
"grad_norm": 0.0822725163008369,
|
| 2118 |
+
"learning_rate": 2.085920784615419e-05,
|
| 2119 |
+
"loss": 2.3221,
|
| 2120 |
+
"step": 290
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.425,
|
| 2124 |
+
"grad_norm": 0.08688016294370648,
|
| 2125 |
+
"learning_rate": 2.0795817812926137e-05,
|
| 2126 |
+
"loss": 2.3348,
|
| 2127 |
+
"step": 291
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 2.4333333333333336,
|
| 2131 |
+
"grad_norm": 0.09216707920134971,
|
| 2132 |
+
"learning_rate": 2.0732305871597003e-05,
|
| 2133 |
+
"loss": 2.3289,
|
| 2134 |
+
"step": 292
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 2.4416666666666664,
|
| 2138 |
+
"grad_norm": 0.0838994543125676,
|
| 2139 |
+
"learning_rate": 2.066867335806457e-05,
|
| 2140 |
+
"loss": 2.2806,
|
| 2141 |
+
"step": 293
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 2.45,
|
| 2145 |
+
"grad_norm": 0.08436072457637282,
|
| 2146 |
+
"learning_rate": 2.060492161076272e-05,
|
| 2147 |
+
"loss": 2.3303,
|
| 2148 |
+
"step": 294
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 2.4583333333333335,
|
| 2152 |
+
"grad_norm": 0.08048632148072529,
|
| 2153 |
+
"learning_rate": 2.054105197063326e-05,
|
| 2154 |
+
"loss": 2.3483,
|
| 2155 |
+
"step": 295
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 2.466666666666667,
|
| 2159 |
+
"grad_norm": 0.08549094443746076,
|
| 2160 |
+
"learning_rate": 2.047706578109774e-05,
|
| 2161 |
+
"loss": 2.3502,
|
| 2162 |
+
"step": 296
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 2.475,
|
| 2166 |
+
"grad_norm": 0.08322146340842644,
|
| 2167 |
+
"learning_rate": 2.041296438802919e-05,
|
| 2168 |
+
"loss": 2.3332,
|
| 2169 |
+
"step": 297
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 2.4833333333333334,
|
| 2173 |
+
"grad_norm": 0.09131216275452314,
|
| 2174 |
+
"learning_rate": 2.0348749139723798e-05,
|
| 2175 |
+
"loss": 2.267,
|
| 2176 |
+
"step": 298
|
| 2177 |
+
},
|
| 2178 |
+
{
|
| 2179 |
+
"epoch": 2.4916666666666667,
|
| 2180 |
+
"grad_norm": 0.08130060637850993,
|
| 2181 |
+
"learning_rate": 2.028442138687258e-05,
|
| 2182 |
+
"loss": 2.3228,
|
| 2183 |
+
"step": 299
|
| 2184 |
+
},
|
| 2185 |
+
{
|
| 2186 |
+
"epoch": 2.5,
|
| 2187 |
+
"grad_norm": 0.08900969776223101,
|
| 2188 |
+
"learning_rate": 2.021998248253293e-05,
|
| 2189 |
+
"loss": 2.335,
|
| 2190 |
+
"step": 300
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 2.5,
|
| 2194 |
+
"eval_loss": 2.3850934505462646,
|
| 2195 |
+
"eval_runtime": 82.0381,
|
| 2196 |
+
"eval_samples_per_second": 4.998,
|
| 2197 |
+
"eval_steps_per_second": 0.317,
|
| 2198 |
+
"step": 300
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 2.5083333333333333,
|
| 2202 |
+
"grad_norm": 0.08469699805792456,
|
| 2203 |
+
"learning_rate": 2.0155433782100188e-05,
|
| 2204 |
+
"loss": 2.3305,
|
| 2205 |
+
"step": 301
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 2.5166666666666666,
|
| 2209 |
+
"grad_norm": 0.08968992065074562,
|
| 2210 |
+
"learning_rate": 2.0090776643279133e-05,
|
| 2211 |
+
"loss": 2.2445,
|
| 2212 |
+
"step": 302
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 2.525,
|
| 2216 |
+
"grad_norm": 0.07869825759077335,
|
| 2217 |
+
"learning_rate": 2.00260124260554e-05,
|
| 2218 |
+
"loss": 2.3113,
|
| 2219 |
+
"step": 303
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 2.533333333333333,
|
| 2223 |
+
"grad_norm": 0.09288868342092681,
|
| 2224 |
+
"learning_rate": 1.9961142492666908e-05,
|
| 2225 |
+
"loss": 2.2976,
|
| 2226 |
+
"step": 304
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 2.5416666666666665,
|
| 2230 |
+
"grad_norm": 0.08605372320941188,
|
| 2231 |
+
"learning_rate": 1.9896168207575165e-05,
|
| 2232 |
+
"loss": 2.3365,
|
| 2233 |
+
"step": 305
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 2.55,
|
| 2237 |
+
"grad_norm": 0.0856078545837982,
|
| 2238 |
+
"learning_rate": 1.983109093743662e-05,
|
| 2239 |
+
"loss": 2.3393,
|
| 2240 |
+
"step": 306
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 2.5583333333333336,
|
| 2244 |
+
"grad_norm": 0.08486108660505347,
|
| 2245 |
+
"learning_rate": 1.976591205107387e-05,
|
| 2246 |
+
"loss": 2.2787,
|
| 2247 |
+
"step": 307
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 2.5666666666666664,
|
| 2251 |
+
"grad_norm": 0.08573888004578346,
|
| 2252 |
+
"learning_rate": 1.9700632919446895e-05,
|
| 2253 |
+
"loss": 2.3428,
|
| 2254 |
+
"step": 308
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 2.575,
|
| 2258 |
+
"grad_norm": 0.08546817819303061,
|
| 2259 |
+
"learning_rate": 1.963525491562421e-05,
|
| 2260 |
+
"loss": 2.3692,
|
| 2261 |
+
"step": 309
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 2.5833333333333335,
|
| 2265 |
+
"grad_norm": 0.08252021910013779,
|
| 2266 |
+
"learning_rate": 1.9569779414754002e-05,
|
| 2267 |
+
"loss": 2.3706,
|
| 2268 |
+
"step": 310
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 2.591666666666667,
|
| 2272 |
+
"grad_norm": 0.08069933890588736,
|
| 2273 |
+
"learning_rate": 1.9504207794035168e-05,
|
| 2274 |
+
"loss": 2.3134,
|
| 2275 |
+
"step": 311
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 2.6,
|
| 2279 |
+
"grad_norm": 0.08200521883766425,
|
| 2280 |
+
"learning_rate": 1.94385414326884e-05,
|
| 2281 |
+
"loss": 2.3475,
|
| 2282 |
+
"step": 312
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 2.6083333333333334,
|
| 2286 |
+
"grad_norm": 0.0863273905427055,
|
| 2287 |
+
"learning_rate": 1.937278171192711e-05,
|
| 2288 |
+
"loss": 2.2677,
|
| 2289 |
+
"step": 313
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 2.6166666666666667,
|
| 2293 |
+
"grad_norm": 0.08604771462579626,
|
| 2294 |
+
"learning_rate": 1.9306930014928456e-05,
|
| 2295 |
+
"loss": 2.3535,
|
| 2296 |
+
"step": 314
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 2.625,
|
| 2300 |
+
"grad_norm": 0.08753164335493215,
|
| 2301 |
+
"learning_rate": 1.9240987726804175e-05,
|
| 2302 |
+
"loss": 2.3003,
|
| 2303 |
+
"step": 315
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 2.6333333333333333,
|
| 2307 |
+
"grad_norm": 0.08803520147994297,
|
| 2308 |
+
"learning_rate": 1.9174956234571482e-05,
|
| 2309 |
+
"loss": 2.3411,
|
| 2310 |
+
"step": 316
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 2.6416666666666666,
|
| 2314 |
+
"grad_norm": 0.08741804975803627,
|
| 2315 |
+
"learning_rate": 1.9108836927123918e-05,
|
| 2316 |
+
"loss": 2.3316,
|
| 2317 |
+
"step": 317
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 2.65,
|
| 2321 |
+
"grad_norm": 0.09017716551481306,
|
| 2322 |
+
"learning_rate": 1.904263119520208e-05,
|
| 2323 |
+
"loss": 2.2814,
|
| 2324 |
+
"step": 318
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.658333333333333,
|
| 2328 |
+
"grad_norm": 0.08667720334507435,
|
| 2329 |
+
"learning_rate": 1.897634043136443e-05,
|
| 2330 |
+
"loss": 2.2985,
|
| 2331 |
+
"step": 319
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 2.6666666666666665,
|
| 2335 |
+
"grad_norm": 0.08212177574347239,
|
| 2336 |
+
"learning_rate": 1.890996602995795e-05,
|
| 2337 |
+
"loss": 2.2692,
|
| 2338 |
+
"step": 320
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 2.675,
|
| 2342 |
+
"grad_norm": 0.08751048246095193,
|
| 2343 |
+
"learning_rate": 1.8843509387088858e-05,
|
| 2344 |
+
"loss": 2.3059,
|
| 2345 |
+
"step": 321
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 2.6833333333333336,
|
| 2349 |
+
"grad_norm": 0.08633792438794154,
|
| 2350 |
+
"learning_rate": 1.87769719005932e-05,
|
| 2351 |
+
"loss": 2.32,
|
| 2352 |
+
"step": 322
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 2.6916666666666664,
|
| 2356 |
+
"grad_norm": 0.0834066012634354,
|
| 2357 |
+
"learning_rate": 1.87103549700075e-05,
|
| 2358 |
+
"loss": 2.3581,
|
| 2359 |
+
"step": 323
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 2.7,
|
| 2363 |
+
"grad_norm": 0.08921524727960709,
|
| 2364 |
+
"learning_rate": 1.8643659996539274e-05,
|
| 2365 |
+
"loss": 2.2967,
|
| 2366 |
+
"step": 324
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 2.7083333333333335,
|
| 2370 |
+
"grad_norm": 0.08385364888138755,
|
| 2371 |
+
"learning_rate": 1.8576888383037578e-05,
|
| 2372 |
+
"loss": 2.3566,
|
| 2373 |
+
"step": 325
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 2.716666666666667,
|
| 2377 |
+
"grad_norm": 0.09143255435882665,
|
| 2378 |
+
"learning_rate": 1.8510041533963498e-05,
|
| 2379 |
+
"loss": 2.2564,
|
| 2380 |
+
"step": 326
|
| 2381 |
+
},
|
| 2382 |
+
{
|
| 2383 |
+
"epoch": 2.725,
|
| 2384 |
+
"grad_norm": 0.0847400859783059,
|
| 2385 |
+
"learning_rate": 1.8443120855360634e-05,
|
| 2386 |
+
"loss": 2.3054,
|
| 2387 |
+
"step": 327
|
| 2388 |
+
},
|
| 2389 |
+
{
|
| 2390 |
+
"epoch": 2.7333333333333334,
|
| 2391 |
+
"grad_norm": 0.09376421936955583,
|
| 2392 |
+
"learning_rate": 1.8376127754825468e-05,
|
| 2393 |
+
"loss": 2.3514,
|
| 2394 |
+
"step": 328
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 2.7416666666666667,
|
| 2398 |
+
"grad_norm": 0.08696878566458673,
|
| 2399 |
+
"learning_rate": 1.8309063641477807e-05,
|
| 2400 |
+
"loss": 2.2729,
|
| 2401 |
+
"step": 329
|
| 2402 |
+
},
|
| 2403 |
+
{
|
| 2404 |
+
"epoch": 2.75,
|
| 2405 |
+
"grad_norm": 0.0916352106233524,
|
| 2406 |
+
"learning_rate": 1.824192992593113e-05,
|
| 2407 |
+
"loss": 2.349,
|
| 2408 |
+
"step": 330
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 2.75,
|
| 2412 |
+
"eval_loss": 2.3834824562072754,
|
| 2413 |
+
"eval_runtime": 82.1096,
|
| 2414 |
+
"eval_samples_per_second": 4.993,
|
| 2415 |
+
"eval_steps_per_second": 0.317,
|
| 2416 |
+
"step": 330
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 2.7583333333333333,
|
| 2420 |
+
"grad_norm": 0.08604205760808722,
|
| 2421 |
+
"learning_rate": 1.817472802026291e-05,
|
| 2422 |
+
"loss": 2.2681,
|
| 2423 |
+
"step": 331
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 2.7666666666666666,
|
| 2427 |
+
"grad_norm": 0.08560511719929889,
|
| 2428 |
+
"learning_rate": 1.810745933798492e-05,
|
| 2429 |
+
"loss": 2.3556,
|
| 2430 |
+
"step": 332
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 2.775,
|
| 2434 |
+
"grad_norm": 0.0939257216904316,
|
| 2435 |
+
"learning_rate": 1.8040125294013497e-05,
|
| 2436 |
+
"loss": 2.2541,
|
| 2437 |
+
"step": 333
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 2.783333333333333,
|
| 2441 |
+
"grad_norm": 0.08963858580215443,
|
| 2442 |
+
"learning_rate": 1.797272730463979e-05,
|
| 2443 |
+
"loss": 2.3377,
|
| 2444 |
+
"step": 334
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 2.7916666666666665,
|
| 2448 |
+
"grad_norm": 0.09156839514682046,
|
| 2449 |
+
"learning_rate": 1.7905266787499948e-05,
|
| 2450 |
+
"loss": 2.2546,
|
| 2451 |
+
"step": 335
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 2.8,
|
| 2455 |
+
"grad_norm": 0.09499647533091797,
|
| 2456 |
+
"learning_rate": 1.7837745161545334e-05,
|
| 2457 |
+
"loss": 2.3506,
|
| 2458 |
+
"step": 336
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 2.8083333333333336,
|
| 2462 |
+
"grad_norm": 0.08356355604247087,
|
| 2463 |
+
"learning_rate": 1.7770163847012656e-05,
|
| 2464 |
+
"loss": 2.3416,
|
| 2465 |
+
"step": 337
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 2.8166666666666664,
|
| 2469 |
+
"grad_norm": 0.08300166502092887,
|
| 2470 |
+
"learning_rate": 1.7702524265394092e-05,
|
| 2471 |
+
"loss": 2.3607,
|
| 2472 |
+
"step": 338
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 2.825,
|
| 2476 |
+
"grad_norm": 0.0950271789770435,
|
| 2477 |
+
"learning_rate": 1.7634827839407408e-05,
|
| 2478 |
+
"loss": 2.355,
|
| 2479 |
+
"step": 339
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 2.8333333333333335,
|
| 2483 |
+
"grad_norm": 0.0905124093090388,
|
| 2484 |
+
"learning_rate": 1.756707599296602e-05,
|
| 2485 |
+
"loss": 2.295,
|
| 2486 |
+
"step": 340
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 2.841666666666667,
|
| 2490 |
+
"grad_norm": 0.08805201196096357,
|
| 2491 |
+
"learning_rate": 1.7499270151149053e-05,
|
| 2492 |
+
"loss": 2.3484,
|
| 2493 |
+
"step": 341
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 2.85,
|
| 2497 |
+
"grad_norm": 0.08635499091237363,
|
| 2498 |
+
"learning_rate": 1.7431411740171342e-05,
|
| 2499 |
+
"loss": 2.3929,
|
| 2500 |
+
"step": 342
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 2.8583333333333334,
|
| 2504 |
+
"grad_norm": 0.08872393093509763,
|
| 2505 |
+
"learning_rate": 1.7363502187353476e-05,
|
| 2506 |
+
"loss": 2.2978,
|
| 2507 |
+
"step": 343
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 2.8666666666666667,
|
| 2511 |
+
"grad_norm": 0.08468287952722828,
|
| 2512 |
+
"learning_rate": 1.7295542921091727e-05,
|
| 2513 |
+
"loss": 2.2634,
|
| 2514 |
+
"step": 344
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 2.875,
|
| 2518 |
+
"grad_norm": 0.0969193307878292,
|
| 2519 |
+
"learning_rate": 1.722753537082806e-05,
|
| 2520 |
+
"loss": 2.3222,
|
| 2521 |
+
"step": 345
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 2.8833333333333333,
|
| 2525 |
+
"grad_norm": 0.09457237068788904,
|
| 2526 |
+
"learning_rate": 1.7159480967020002e-05,
|
| 2527 |
+
"loss": 2.2363,
|
| 2528 |
+
"step": 346
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 2.8916666666666666,
|
| 2532 |
+
"grad_norm": 0.08477579034500593,
|
| 2533 |
+
"learning_rate": 1.709138114111061e-05,
|
| 2534 |
+
"loss": 2.315,
|
| 2535 |
+
"step": 347
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 2.9,
|
| 2539 |
+
"grad_norm": 0.08876318923664918,
|
| 2540 |
+
"learning_rate": 1.7023237325498337e-05,
|
| 2541 |
+
"loss": 2.2983,
|
| 2542 |
+
"step": 348
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 2.908333333333333,
|
| 2546 |
+
"grad_norm": 0.09341493028908791,
|
| 2547 |
+
"learning_rate": 1.6955050953506906e-05,
|
| 2548 |
+
"loss": 2.3366,
|
| 2549 |
+
"step": 349
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 2.9166666666666665,
|
| 2553 |
+
"grad_norm": 0.08768258037568251,
|
| 2554 |
+
"learning_rate": 1.688682345935516e-05,
|
| 2555 |
+
"loss": 2.2517,
|
| 2556 |
+
"step": 350
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 2.925,
|
| 2560 |
+
"grad_norm": 0.10205004678612419,
|
| 2561 |
+
"learning_rate": 1.6818556278126905e-05,
|
| 2562 |
+
"loss": 2.2547,
|
| 2563 |
+
"step": 351
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 2.9333333333333336,
|
| 2567 |
+
"grad_norm": 0.09783741945218803,
|
| 2568 |
+
"learning_rate": 1.6750250845740698e-05,
|
| 2569 |
+
"loss": 2.3396,
|
| 2570 |
+
"step": 352
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 2.9416666666666664,
|
| 2574 |
+
"grad_norm": 0.0910772527936302,
|
| 2575 |
+
"learning_rate": 1.668190859891969e-05,
|
| 2576 |
+
"loss": 2.291,
|
| 2577 |
+
"step": 353
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 2.95,
|
| 2581 |
+
"grad_norm": 0.10360592839753946,
|
| 2582 |
+
"learning_rate": 1.661353097516137e-05,
|
| 2583 |
+
"loss": 2.3048,
|
| 2584 |
+
"step": 354
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 2.9583333333333335,
|
| 2588 |
+
"grad_norm": 0.09106472201247891,
|
| 2589 |
+
"learning_rate": 1.6545119412707317e-05,
|
| 2590 |
+
"loss": 2.2524,
|
| 2591 |
+
"step": 355
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 2.966666666666667,
|
| 2595 |
+
"grad_norm": 0.08402400401887918,
|
| 2596 |
+
"learning_rate": 1.6476675350513e-05,
|
| 2597 |
+
"loss": 2.3614,
|
| 2598 |
+
"step": 356
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 2.975,
|
| 2602 |
+
"grad_norm": 0.10747977774987429,
|
| 2603 |
+
"learning_rate": 1.6408200228217476e-05,
|
| 2604 |
+
"loss": 2.3517,
|
| 2605 |
+
"step": 357
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 2.9833333333333334,
|
| 2609 |
+
"grad_norm": 0.08973239330181115,
|
| 2610 |
+
"learning_rate": 1.6339695486113095e-05,
|
| 2611 |
+
"loss": 2.2962,
|
| 2612 |
+
"step": 358
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 2.9916666666666667,
|
| 2616 |
+
"grad_norm": 0.09076171639200155,
|
| 2617 |
+
"learning_rate": 1.627116256511524e-05,
|
| 2618 |
+
"loss": 2.3083,
|
| 2619 |
+
"step": 359
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 3.0,
|
| 2623 |
+
"grad_norm": 0.1007797989418104,
|
| 2624 |
+
"learning_rate": 1.6202602906732004e-05,
|
| 2625 |
+
"loss": 2.2828,
|
| 2626 |
+
"step": 360
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 3.0,
|
| 2630 |
+
"eval_loss": 2.3818039894104004,
|
| 2631 |
+
"eval_runtime": 82.8777,
|
| 2632 |
+
"eval_samples_per_second": 4.947,
|
| 2633 |
+
"eval_steps_per_second": 0.314,
|
| 2634 |
+
"step": 360
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 3.0083333333333333,
|
| 2638 |
+
"grad_norm": 0.10338433397745281,
|
| 2639 |
+
"learning_rate": 1.613401795303386e-05,
|
| 2640 |
+
"loss": 2.2868,
|
| 2641 |
+
"step": 361
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 3.0166666666666666,
|
| 2645 |
+
"grad_norm": 0.08983199306580612,
|
| 2646 |
+
"learning_rate": 1.6065409146623346e-05,
|
| 2647 |
+
"loss": 2.2921,
|
| 2648 |
+
"step": 362
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 3.025,
|
| 2652 |
+
"grad_norm": 0.0975817627852949,
|
| 2653 |
+
"learning_rate": 1.5996777930604714e-05,
|
| 2654 |
+
"loss": 2.3402,
|
| 2655 |
+
"step": 363
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 3.033333333333333,
|
| 2659 |
+
"grad_norm": 0.10245360882679408,
|
| 2660 |
+
"learning_rate": 1.5928125748553565e-05,
|
| 2661 |
+
"loss": 2.3311,
|
| 2662 |
+
"step": 364
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 3.0416666666666665,
|
| 2666 |
+
"grad_norm": 0.08483098034937916,
|
| 2667 |
+
"learning_rate": 1.58594540444865e-05,
|
| 2668 |
+
"loss": 2.3152,
|
| 2669 |
+
"step": 365
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 3.05,
|
| 2673 |
+
"grad_norm": 0.10458160072608975,
|
| 2674 |
+
"learning_rate": 1.579076426283075e-05,
|
| 2675 |
+
"loss": 2.3368,
|
| 2676 |
+
"step": 366
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 3.058333333333333,
|
| 2680 |
+
"grad_norm": 0.09254078167858161,
|
| 2681 |
+
"learning_rate": 1.572205784839378e-05,
|
| 2682 |
+
"loss": 2.2594,
|
| 2683 |
+
"step": 367
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 3.066666666666667,
|
| 2687 |
+
"grad_norm": 0.08791904183245927,
|
| 2688 |
+
"learning_rate": 1.56533362463329e-05,
|
| 2689 |
+
"loss": 2.3546,
|
| 2690 |
+
"step": 368
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 3.075,
|
| 2694 |
+
"grad_norm": 0.09886727526220379,
|
| 2695 |
+
"learning_rate": 1.5584600902124885e-05,
|
| 2696 |
+
"loss": 2.3214,
|
| 2697 |
+
"step": 369
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 3.0833333333333335,
|
| 2701 |
+
"grad_norm": 0.08687430287675091,
|
| 2702 |
+
"learning_rate": 1.5515853261535557e-05,
|
| 2703 |
+
"loss": 2.3574,
|
| 2704 |
+
"step": 370
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 3.091666666666667,
|
| 2708 |
+
"grad_norm": 0.09267445893943518,
|
| 2709 |
+
"learning_rate": 1.5447094770589372e-05,
|
| 2710 |
+
"loss": 2.2959,
|
| 2711 |
+
"step": 371
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 3.1,
|
| 2715 |
+
"grad_norm": 0.08896205591637517,
|
| 2716 |
+
"learning_rate": 1.5378326875539014e-05,
|
| 2717 |
+
"loss": 2.2761,
|
| 2718 |
+
"step": 372
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 3.1083333333333334,
|
| 2722 |
+
"grad_norm": 0.08868993314014653,
|
| 2723 |
+
"learning_rate": 1.530955102283497e-05,
|
| 2724 |
+
"loss": 2.2502,
|
| 2725 |
+
"step": 373
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 3.1166666666666667,
|
| 2729 |
+
"grad_norm": 0.09073948321845955,
|
| 2730 |
+
"learning_rate": 1.52407686590951e-05,
|
| 2731 |
+
"loss": 2.3475,
|
| 2732 |
+
"step": 374
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 3.125,
|
| 2736 |
+
"grad_norm": 0.08776718745927117,
|
| 2737 |
+
"learning_rate": 1.5171981231074235e-05,
|
| 2738 |
+
"loss": 2.3101,
|
| 2739 |
+
"step": 375
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 3.1333333333333333,
|
| 2743 |
+
"grad_norm": 0.09103814064392408,
|
| 2744 |
+
"learning_rate": 1.510319018563371e-05,
|
| 2745 |
+
"loss": 2.2863,
|
| 2746 |
+
"step": 376
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 3.1416666666666666,
|
| 2750 |
+
"grad_norm": 0.08677195458777316,
|
| 2751 |
+
"learning_rate": 1.5034396969710957e-05,
|
| 2752 |
+
"loss": 2.3113,
|
| 2753 |
+
"step": 377
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 3.15,
|
| 2757 |
+
"grad_norm": 0.09514335839893395,
|
| 2758 |
+
"learning_rate": 1.4965603030289049e-05,
|
| 2759 |
+
"loss": 2.3037,
|
| 2760 |
+
"step": 378
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 3.158333333333333,
|
| 2764 |
+
"grad_norm": 0.08912871701655573,
|
| 2765 |
+
"learning_rate": 1.489680981436629e-05,
|
| 2766 |
+
"loss": 2.2794,
|
| 2767 |
+
"step": 379
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 3.1666666666666665,
|
| 2771 |
+
"grad_norm": 0.09259798341231154,
|
| 2772 |
+
"learning_rate": 1.4828018768925764e-05,
|
| 2773 |
+
"loss": 2.2658,
|
| 2774 |
+
"step": 380
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 3.175,
|
| 2778 |
+
"grad_norm": 0.08802533686446708,
|
| 2779 |
+
"learning_rate": 1.47592313409049e-05,
|
| 2780 |
+
"loss": 2.3038,
|
| 2781 |
+
"step": 381
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 3.183333333333333,
|
| 2785 |
+
"grad_norm": 0.08899926187377338,
|
| 2786 |
+
"learning_rate": 1.4690448977165033e-05,
|
| 2787 |
+
"loss": 2.2964,
|
| 2788 |
+
"step": 382
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 3.191666666666667,
|
| 2792 |
+
"grad_norm": 0.08779432475308313,
|
| 2793 |
+
"learning_rate": 1.4621673124460992e-05,
|
| 2794 |
+
"loss": 2.2932,
|
| 2795 |
+
"step": 383
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 3.2,
|
| 2799 |
+
"grad_norm": 0.08860776822166405,
|
| 2800 |
+
"learning_rate": 1.4552905229410628e-05,
|
| 2801 |
+
"loss": 2.284,
|
| 2802 |
+
"step": 384
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 3.2083333333333335,
|
| 2806 |
+
"grad_norm": 0.08787596105604804,
|
| 2807 |
+
"learning_rate": 1.448414673846444e-05,
|
| 2808 |
+
"loss": 2.3028,
|
| 2809 |
+
"step": 385
|
| 2810 |
+
},
|
| 2811 |
+
{
|
| 2812 |
+
"epoch": 3.216666666666667,
|
| 2813 |
+
"grad_norm": 0.08640615123140007,
|
| 2814 |
+
"learning_rate": 1.4415399097875116e-05,
|
| 2815 |
+
"loss": 2.3568,
|
| 2816 |
+
"step": 386
|
| 2817 |
+
},
|
| 2818 |
+
{
|
| 2819 |
+
"epoch": 3.225,
|
| 2820 |
+
"grad_norm": 0.08637567560444034,
|
| 2821 |
+
"learning_rate": 1.4346663753667102e-05,
|
| 2822 |
+
"loss": 2.3244,
|
| 2823 |
+
"step": 387
|
| 2824 |
+
},
|
| 2825 |
+
{
|
| 2826 |
+
"epoch": 3.2333333333333334,
|
| 2827 |
+
"grad_norm": 0.08770337703494425,
|
| 2828 |
+
"learning_rate": 1.4277942151606227e-05,
|
| 2829 |
+
"loss": 2.2681,
|
| 2830 |
+
"step": 388
|
| 2831 |
+
},
|
| 2832 |
+
{
|
| 2833 |
+
"epoch": 3.2416666666666667,
|
| 2834 |
+
"grad_norm": 0.09113667038261426,
|
| 2835 |
+
"learning_rate": 1.4209235737169254e-05,
|
| 2836 |
+
"loss": 2.3245,
|
| 2837 |
+
"step": 389
|
| 2838 |
+
},
|
| 2839 |
+
{
|
| 2840 |
+
"epoch": 3.25,
|
| 2841 |
+
"grad_norm": 0.0903079086442714,
|
| 2842 |
+
"learning_rate": 1.4140545955513503e-05,
|
| 2843 |
+
"loss": 2.2632,
|
| 2844 |
+
"step": 390
|
| 2845 |
+
},
|
| 2846 |
+
{
|
| 2847 |
+
"epoch": 3.25,
|
| 2848 |
+
"eval_loss": 2.3810861110687256,
|
| 2849 |
+
"eval_runtime": 82.1753,
|
| 2850 |
+
"eval_samples_per_second": 4.989,
|
| 2851 |
+
"eval_steps_per_second": 0.316,
|
| 2852 |
+
"step": 390
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 3.2583333333333333,
|
| 2856 |
+
"grad_norm": 0.08488360183716726,
|
| 2857 |
+
"learning_rate": 1.407187425144644e-05,
|
| 2858 |
+
"loss": 2.3126,
|
| 2859 |
+
"step": 391
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 3.2666666666666666,
|
| 2863 |
+
"grad_norm": 0.08475436949475408,
|
| 2864 |
+
"learning_rate": 1.400322206939529e-05,
|
| 2865 |
+
"loss": 2.3369,
|
| 2866 |
+
"step": 392
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 3.275,
|
| 2870 |
+
"grad_norm": 0.08399538907200171,
|
| 2871 |
+
"learning_rate": 1.3934590853376653e-05,
|
| 2872 |
+
"loss": 2.2917,
|
| 2873 |
+
"step": 393
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 3.283333333333333,
|
| 2877 |
+
"grad_norm": 0.09117788897736656,
|
| 2878 |
+
"learning_rate": 1.3865982046966142e-05,
|
| 2879 |
+
"loss": 2.3261,
|
| 2880 |
+
"step": 394
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 3.2916666666666665,
|
| 2884 |
+
"grad_norm": 0.0909704861037152,
|
| 2885 |
+
"learning_rate": 1.3797397093267997e-05,
|
| 2886 |
+
"loss": 2.2377,
|
| 2887 |
+
"step": 395
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 3.3,
|
| 2891 |
+
"grad_norm": 0.08450013486785617,
|
| 2892 |
+
"learning_rate": 1.3728837434884766e-05,
|
| 2893 |
+
"loss": 2.3301,
|
| 2894 |
+
"step": 396
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 3.3083333333333336,
|
| 2898 |
+
"grad_norm": 0.09440735192732533,
|
| 2899 |
+
"learning_rate": 1.3660304513886908e-05,
|
| 2900 |
+
"loss": 2.3075,
|
| 2901 |
+
"step": 397
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 3.3166666666666664,
|
| 2905 |
+
"grad_norm": 0.09168608858526697,
|
| 2906 |
+
"learning_rate": 1.3591799771782526e-05,
|
| 2907 |
+
"loss": 2.3034,
|
| 2908 |
+
"step": 398
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 3.325,
|
| 2912 |
+
"grad_norm": 0.08588225922937906,
|
| 2913 |
+
"learning_rate": 1.3523324649487002e-05,
|
| 2914 |
+
"loss": 2.2782,
|
| 2915 |
+
"step": 399
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 3.3333333333333335,
|
| 2919 |
+
"grad_norm": 0.08803985637532977,
|
| 2920 |
+
"learning_rate": 1.3454880587292687e-05,
|
| 2921 |
+
"loss": 2.3068,
|
| 2922 |
+
"step": 400
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 3.341666666666667,
|
| 2926 |
+
"grad_norm": 0.08935196181959137,
|
| 2927 |
+
"learning_rate": 1.338646902483864e-05,
|
| 2928 |
+
"loss": 2.3343,
|
| 2929 |
+
"step": 401
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 3.35,
|
| 2933 |
+
"grad_norm": 0.09040264096598875,
|
| 2934 |
+
"learning_rate": 1.331809140108031e-05,
|
| 2935 |
+
"loss": 2.3112,
|
| 2936 |
+
"step": 402
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 3.3583333333333334,
|
| 2940 |
+
"grad_norm": 0.08687816656180893,
|
| 2941 |
+
"learning_rate": 1.3249749154259303e-05,
|
| 2942 |
+
"loss": 2.3216,
|
| 2943 |
+
"step": 403
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 3.3666666666666667,
|
| 2947 |
+
"grad_norm": 0.08823418670784175,
|
| 2948 |
+
"learning_rate": 1.3181443721873102e-05,
|
| 2949 |
+
"loss": 2.2815,
|
| 2950 |
+
"step": 404
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 3.375,
|
| 2954 |
+
"grad_norm": 0.09178277236847845,
|
| 2955 |
+
"learning_rate": 1.3113176540644841e-05,
|
| 2956 |
+
"loss": 2.2846,
|
| 2957 |
+
"step": 405
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 3.3833333333333333,
|
| 2961 |
+
"grad_norm": 0.09209490775678109,
|
| 2962 |
+
"learning_rate": 1.3044949046493095e-05,
|
| 2963 |
+
"loss": 2.2238,
|
| 2964 |
+
"step": 406
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 3.3916666666666666,
|
| 2968 |
+
"grad_norm": 0.09457552051598997,
|
| 2969 |
+
"learning_rate": 1.2976762674501665e-05,
|
| 2970 |
+
"loss": 2.3047,
|
| 2971 |
+
"step": 407
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 3.4,
|
| 2975 |
+
"grad_norm": 0.0898065874636998,
|
| 2976 |
+
"learning_rate": 1.2908618858889392e-05,
|
| 2977 |
+
"loss": 2.2752,
|
| 2978 |
+
"step": 408
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 3.408333333333333,
|
| 2982 |
+
"grad_norm": 0.08788754061760551,
|
| 2983 |
+
"learning_rate": 1.2840519032980008e-05,
|
| 2984 |
+
"loss": 2.3076,
|
| 2985 |
+
"step": 409
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 3.4166666666666665,
|
| 2989 |
+
"grad_norm": 0.09386988904460127,
|
| 2990 |
+
"learning_rate": 1.2772464629171945e-05,
|
| 2991 |
+
"loss": 2.2765,
|
| 2992 |
+
"step": 410
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 3.425,
|
| 2996 |
+
"grad_norm": 0.08613700732697491,
|
| 2997 |
+
"learning_rate": 1.2704457078908269e-05,
|
| 2998 |
+
"loss": 2.3288,
|
| 2999 |
+
"step": 411
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 3.4333333333333336,
|
| 3003 |
+
"grad_norm": 0.08756602905136124,
|
| 3004 |
+
"learning_rate": 1.263649781264653e-05,
|
| 3005 |
+
"loss": 2.2864,
|
| 3006 |
+
"step": 412
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 3.4416666666666664,
|
| 3010 |
+
"grad_norm": 0.08589869403306019,
|
| 3011 |
+
"learning_rate": 1.256858825982866e-05,
|
| 3012 |
+
"loss": 2.3591,
|
| 3013 |
+
"step": 413
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 3.45,
|
| 3017 |
+
"grad_norm": 0.08730009417783254,
|
| 3018 |
+
"learning_rate": 1.2500729848850954e-05,
|
| 3019 |
+
"loss": 2.3495,
|
| 3020 |
+
"step": 414
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 3.4583333333333335,
|
| 3024 |
+
"grad_norm": 0.08770184046271857,
|
| 3025 |
+
"learning_rate": 1.243292400703398e-05,
|
| 3026 |
+
"loss": 2.2648,
|
| 3027 |
+
"step": 415
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 3.466666666666667,
|
| 3031 |
+
"grad_norm": 0.08781284297694333,
|
| 3032 |
+
"learning_rate": 1.2365172160592593e-05,
|
| 3033 |
+
"loss": 2.3369,
|
| 3034 |
+
"step": 416
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 3.475,
|
| 3038 |
+
"grad_norm": 0.08675269239865462,
|
| 3039 |
+
"learning_rate": 1.229747573460591e-05,
|
| 3040 |
+
"loss": 2.2685,
|
| 3041 |
+
"step": 417
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 3.4833333333333334,
|
| 3045 |
+
"grad_norm": 0.08708072692783757,
|
| 3046 |
+
"learning_rate": 1.2229836152987347e-05,
|
| 3047 |
+
"loss": 2.2452,
|
| 3048 |
+
"step": 418
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 3.4916666666666667,
|
| 3052 |
+
"grad_norm": 0.09077909683373944,
|
| 3053 |
+
"learning_rate": 1.2162254838454665e-05,
|
| 3054 |
+
"loss": 2.2756,
|
| 3055 |
+
"step": 419
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 3.5,
|
| 3059 |
+
"grad_norm": 0.08829475418897426,
|
| 3060 |
+
"learning_rate": 1.2094733212500053e-05,
|
| 3061 |
+
"loss": 2.3254,
|
| 3062 |
+
"step": 420
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 3.5,
|
| 3066 |
+
"eval_loss": 2.380058526992798,
|
| 3067 |
+
"eval_runtime": 81.4718,
|
| 3068 |
+
"eval_samples_per_second": 5.032,
|
| 3069 |
+
"eval_steps_per_second": 0.319,
|
| 3070 |
+
"step": 420
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 3.5083333333333333,
|
| 3074 |
+
"grad_norm": 0.08405158268403932,
|
| 3075 |
+
"learning_rate": 1.2027272695360215e-05,
|
| 3076 |
+
"loss": 2.3041,
|
| 3077 |
+
"step": 421
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 3.5166666666666666,
|
| 3081 |
+
"grad_norm": 0.08853171098198077,
|
| 3082 |
+
"learning_rate": 1.1959874705986508e-05,
|
| 3083 |
+
"loss": 2.2859,
|
| 3084 |
+
"step": 422
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 3.525,
|
| 3088 |
+
"grad_norm": 0.08634072520589231,
|
| 3089 |
+
"learning_rate": 1.1892540662015081e-05,
|
| 3090 |
+
"loss": 2.2781,
|
| 3091 |
+
"step": 423
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 3.533333333333333,
|
| 3095 |
+
"grad_norm": 0.08267458808501957,
|
| 3096 |
+
"learning_rate": 1.182527197973709e-05,
|
| 3097 |
+
"loss": 2.2584,
|
| 3098 |
+
"step": 424
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 3.5416666666666665,
|
| 3102 |
+
"grad_norm": 0.08942690245564228,
|
| 3103 |
+
"learning_rate": 1.1758070074068875e-05,
|
| 3104 |
+
"loss": 2.2275,
|
| 3105 |
+
"step": 425
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 3.55,
|
| 3109 |
+
"grad_norm": 0.08911399724539566,
|
| 3110 |
+
"learning_rate": 1.1690936358522198e-05,
|
| 3111 |
+
"loss": 2.2578,
|
| 3112 |
+
"step": 426
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 3.5583333333333336,
|
| 3116 |
+
"grad_norm": 0.09248364969117114,
|
| 3117 |
+
"learning_rate": 1.162387224517454e-05,
|
| 3118 |
+
"loss": 2.3028,
|
| 3119 |
+
"step": 427
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 3.5666666666666664,
|
| 3123 |
+
"grad_norm": 0.09158360398831261,
|
| 3124 |
+
"learning_rate": 1.1556879144639368e-05,
|
| 3125 |
+
"loss": 2.3111,
|
| 3126 |
+
"step": 428
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 3.575,
|
| 3130 |
+
"grad_norm": 0.08472105194382792,
|
| 3131 |
+
"learning_rate": 1.14899584660365e-05,
|
| 3132 |
+
"loss": 2.2976,
|
| 3133 |
+
"step": 429
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 3.5833333333333335,
|
| 3137 |
+
"grad_norm": 0.08687678447285525,
|
| 3138 |
+
"learning_rate": 1.1423111616962427e-05,
|
| 3139 |
+
"loss": 2.3424,
|
| 3140 |
+
"step": 430
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 3.591666666666667,
|
| 3144 |
+
"grad_norm": 0.08478960287987566,
|
| 3145 |
+
"learning_rate": 1.135634000346073e-05,
|
| 3146 |
+
"loss": 2.2614,
|
| 3147 |
+
"step": 431
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 3.6,
|
| 3151 |
+
"grad_norm": 0.09779247115831088,
|
| 3152 |
+
"learning_rate": 1.12896450299925e-05,
|
| 3153 |
+
"loss": 2.2812,
|
| 3154 |
+
"step": 432
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 3.6083333333333334,
|
| 3158 |
+
"grad_norm": 0.09129784739369494,
|
| 3159 |
+
"learning_rate": 1.1223028099406801e-05,
|
| 3160 |
+
"loss": 2.2603,
|
| 3161 |
+
"step": 433
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 3.6166666666666667,
|
| 3165 |
+
"grad_norm": 0.09487945962116957,
|
| 3166 |
+
"learning_rate": 1.1156490612911148e-05,
|
| 3167 |
+
"loss": 2.3165,
|
| 3168 |
+
"step": 434
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 3.625,
|
| 3172 |
+
"grad_norm": 0.0841738581651058,
|
| 3173 |
+
"learning_rate": 1.1090033970042058e-05,
|
| 3174 |
+
"loss": 2.3239,
|
| 3175 |
+
"step": 435
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 3.6333333333333333,
|
| 3179 |
+
"grad_norm": 0.08691830559116377,
|
| 3180 |
+
"learning_rate": 1.1023659568635571e-05,
|
| 3181 |
+
"loss": 2.2775,
|
| 3182 |
+
"step": 436
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 3.6416666666666666,
|
| 3186 |
+
"grad_norm": 0.0928861795996369,
|
| 3187 |
+
"learning_rate": 1.0957368804797916e-05,
|
| 3188 |
+
"loss": 2.3341,
|
| 3189 |
+
"step": 437
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 3.65,
|
| 3193 |
+
"grad_norm": 0.09232537359227677,
|
| 3194 |
+
"learning_rate": 1.0891163072876088e-05,
|
| 3195 |
+
"loss": 2.303,
|
| 3196 |
+
"step": 438
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 3.658333333333333,
|
| 3200 |
+
"grad_norm": 0.09444904243413879,
|
| 3201 |
+
"learning_rate": 1.0825043765428519e-05,
|
| 3202 |
+
"loss": 2.3032,
|
| 3203 |
+
"step": 439
|
| 3204 |
+
},
|
| 3205 |
+
{
|
| 3206 |
+
"epoch": 3.6666666666666665,
|
| 3207 |
+
"grad_norm": 0.08844515360397427,
|
| 3208 |
+
"learning_rate": 1.0759012273195828e-05,
|
| 3209 |
+
"loss": 2.2545,
|
| 3210 |
+
"step": 440
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 3.675,
|
| 3214 |
+
"grad_norm": 0.08811461478019997,
|
| 3215 |
+
"learning_rate": 1.0693069985071548e-05,
|
| 3216 |
+
"loss": 2.2521,
|
| 3217 |
+
"step": 441
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 3.6833333333333336,
|
| 3221 |
+
"grad_norm": 0.0895181195137759,
|
| 3222 |
+
"learning_rate": 1.062721828807289e-05,
|
| 3223 |
+
"loss": 2.3133,
|
| 3224 |
+
"step": 442
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 3.6916666666666664,
|
| 3228 |
+
"grad_norm": 0.08653338479492595,
|
| 3229 |
+
"learning_rate": 1.0561458567311608e-05,
|
| 3230 |
+
"loss": 2.313,
|
| 3231 |
+
"step": 443
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 3.7,
|
| 3235 |
+
"grad_norm": 0.09785941972932603,
|
| 3236 |
+
"learning_rate": 1.0495792205964833e-05,
|
| 3237 |
+
"loss": 2.248,
|
| 3238 |
+
"step": 444
|
| 3239 |
+
},
|
| 3240 |
+
{
|
| 3241 |
+
"epoch": 3.7083333333333335,
|
| 3242 |
+
"grad_norm": 0.08577494376546319,
|
| 3243 |
+
"learning_rate": 1.0430220585246e-05,
|
| 3244 |
+
"loss": 2.3414,
|
| 3245 |
+
"step": 445
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 3.716666666666667,
|
| 3249 |
+
"grad_norm": 0.0846390195009267,
|
| 3250 |
+
"learning_rate": 1.036474508437579e-05,
|
| 3251 |
+
"loss": 2.338,
|
| 3252 |
+
"step": 446
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 3.725,
|
| 3256 |
+
"grad_norm": 0.08598862656976118,
|
| 3257 |
+
"learning_rate": 1.0299367080553106e-05,
|
| 3258 |
+
"loss": 2.2558,
|
| 3259 |
+
"step": 447
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 3.7333333333333334,
|
| 3263 |
+
"grad_norm": 0.08540486447902608,
|
| 3264 |
+
"learning_rate": 1.0234087948926136e-05,
|
| 3265 |
+
"loss": 2.2747,
|
| 3266 |
+
"step": 448
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 3.7416666666666667,
|
| 3270 |
+
"grad_norm": 0.09406240638253516,
|
| 3271 |
+
"learning_rate": 1.0168909062563381e-05,
|
| 3272 |
+
"loss": 2.3391,
|
| 3273 |
+
"step": 449
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 3.75,
|
| 3277 |
+
"grad_norm": 0.08577651142799778,
|
| 3278 |
+
"learning_rate": 1.0103831792424833e-05,
|
| 3279 |
+
"loss": 2.3073,
|
| 3280 |
+
"step": 450
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 3.75,
|
| 3284 |
+
"eval_loss": 2.379122734069824,
|
| 3285 |
+
"eval_runtime": 84.5478,
|
| 3286 |
+
"eval_samples_per_second": 4.849,
|
| 3287 |
+
"eval_steps_per_second": 0.308,
|
| 3288 |
+
"step": 450
|
| 3289 |
+
},
|
| 3290 |
+
{
|
| 3291 |
+
"epoch": 3.7583333333333333,
|
| 3292 |
+
"grad_norm": 0.08767661646493884,
|
| 3293 |
+
"learning_rate": 1.0038857507333098e-05,
|
| 3294 |
+
"loss": 2.3283,
|
| 3295 |
+
"step": 451
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 3.7666666666666666,
|
| 3299 |
+
"grad_norm": 0.08708038249070911,
|
| 3300 |
+
"learning_rate": 9.973987573944601e-06,
|
| 3301 |
+
"loss": 2.3301,
|
| 3302 |
+
"step": 452
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 3.775,
|
| 3306 |
+
"grad_norm": 0.08628502677159525,
|
| 3307 |
+
"learning_rate": 9.909223356720864e-06,
|
| 3308 |
+
"loss": 2.3463,
|
| 3309 |
+
"step": 453
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 3.783333333333333,
|
| 3313 |
+
"grad_norm": 0.08292552370875894,
|
| 3314 |
+
"learning_rate": 9.844566217899814e-06,
|
| 3315 |
+
"loss": 2.3462,
|
| 3316 |
+
"step": 454
|
| 3317 |
+
},
|
| 3318 |
+
{
|
| 3319 |
+
"epoch": 3.7916666666666665,
|
| 3320 |
+
"grad_norm": 0.08426376123943377,
|
| 3321 |
+
"learning_rate": 9.780017517467072e-06,
|
| 3322 |
+
"loss": 2.2919,
|
| 3323 |
+
"step": 455
|
| 3324 |
+
},
|
| 3325 |
+
{
|
| 3326 |
+
"epoch": 3.8,
|
| 3327 |
+
"grad_norm": 0.08063683234801552,
|
| 3328 |
+
"learning_rate": 9.715578613127423e-06,
|
| 3329 |
+
"loss": 2.2564,
|
| 3330 |
+
"step": 456
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"epoch": 3.8083333333333336,
|
| 3334 |
+
"grad_norm": 0.08673549520199171,
|
| 3335 |
+
"learning_rate": 9.651250860276202e-06,
|
| 3336 |
+
"loss": 2.2732,
|
| 3337 |
+
"step": 457
|
| 3338 |
+
},
|
| 3339 |
+
{
|
| 3340 |
+
"epoch": 3.8166666666666664,
|
| 3341 |
+
"grad_norm": 0.08529278540380274,
|
| 3342 |
+
"learning_rate": 9.587035611970812e-06,
|
| 3343 |
+
"loss": 2.2874,
|
| 3344 |
+
"step": 458
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 3.825,
|
| 3348 |
+
"grad_norm": 0.08720780135587118,
|
| 3349 |
+
"learning_rate": 9.522934218902261e-06,
|
| 3350 |
+
"loss": 2.2556,
|
| 3351 |
+
"step": 459
|
| 3352 |
+
},
|
| 3353 |
+
{
|
| 3354 |
+
"epoch": 3.8333333333333335,
|
| 3355 |
+
"grad_norm": 0.09134756583746935,
|
| 3356 |
+
"learning_rate": 9.458948029366742e-06,
|
| 3357 |
+
"loss": 2.227,
|
| 3358 |
+
"step": 460
|
| 3359 |
+
},
|
| 3360 |
+
{
|
| 3361 |
+
"epoch": 3.841666666666667,
|
| 3362 |
+
"grad_norm": 0.08731337955526987,
|
| 3363 |
+
"learning_rate": 9.395078389237286e-06,
|
| 3364 |
+
"loss": 2.3315,
|
| 3365 |
+
"step": 461
|
| 3366 |
+
},
|
| 3367 |
+
{
|
| 3368 |
+
"epoch": 3.85,
|
| 3369 |
+
"grad_norm": 0.08741580629661501,
|
| 3370 |
+
"learning_rate": 9.331326641935428e-06,
|
| 3371 |
+
"loss": 2.3162,
|
| 3372 |
+
"step": 462
|
| 3373 |
+
},
|
| 3374 |
+
{
|
| 3375 |
+
"epoch": 3.8583333333333334,
|
| 3376 |
+
"grad_norm": 0.09434987554609216,
|
| 3377 |
+
"learning_rate": 9.267694128402998e-06,
|
| 3378 |
+
"loss": 2.319,
|
| 3379 |
+
"step": 463
|
| 3380 |
+
},
|
| 3381 |
+
{
|
| 3382 |
+
"epoch": 3.8666666666666667,
|
| 3383 |
+
"grad_norm": 0.086173830839335,
|
| 3384 |
+
"learning_rate": 9.20418218707387e-06,
|
| 3385 |
+
"loss": 2.2612,
|
| 3386 |
+
"step": 464
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 3.875,
|
| 3390 |
+
"grad_norm": 0.09071934821719907,
|
| 3391 |
+
"learning_rate": 9.140792153845812e-06,
|
| 3392 |
+
"loss": 2.3166,
|
| 3393 |
+
"step": 465
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"epoch": 3.8833333333333333,
|
| 3397 |
+
"grad_norm": 0.08458028069912522,
|
| 3398 |
+
"learning_rate": 9.077525362052425e-06,
|
| 3399 |
+
"loss": 2.3305,
|
| 3400 |
+
"step": 466
|
| 3401 |
+
},
|
| 3402 |
+
{
|
| 3403 |
+
"epoch": 3.8916666666666666,
|
| 3404 |
+
"grad_norm": 0.0846135185376732,
|
| 3405 |
+
"learning_rate": 9.014383142435068e-06,
|
| 3406 |
+
"loss": 2.3217,
|
| 3407 |
+
"step": 467
|
| 3408 |
+
},
|
| 3409 |
+
{
|
| 3410 |
+
"epoch": 3.9,
|
| 3411 |
+
"grad_norm": 0.09108081025157018,
|
| 3412 |
+
"learning_rate": 8.951366823114862e-06,
|
| 3413 |
+
"loss": 2.3002,
|
| 3414 |
+
"step": 468
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 3.908333333333333,
|
| 3418 |
+
"grad_norm": 0.08493618483276442,
|
| 3419 |
+
"learning_rate": 8.888477729564778e-06,
|
| 3420 |
+
"loss": 2.2843,
|
| 3421 |
+
"step": 469
|
| 3422 |
+
},
|
| 3423 |
+
{
|
| 3424 |
+
"epoch": 3.9166666666666665,
|
| 3425 |
+
"grad_norm": 0.08965735588870012,
|
| 3426 |
+
"learning_rate": 8.825717184581731e-06,
|
| 3427 |
+
"loss": 2.2938,
|
| 3428 |
+
"step": 470
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 3.925,
|
| 3432 |
+
"grad_norm": 0.08739339224034733,
|
| 3433 |
+
"learning_rate": 8.763086508258787e-06,
|
| 3434 |
+
"loss": 2.2613,
|
| 3435 |
+
"step": 471
|
| 3436 |
+
},
|
| 3437 |
+
{
|
| 3438 |
+
"epoch": 3.9333333333333336,
|
| 3439 |
+
"grad_norm": 0.0859648586429565,
|
| 3440 |
+
"learning_rate": 8.700587017957372e-06,
|
| 3441 |
+
"loss": 2.3067,
|
| 3442 |
+
"step": 472
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 3.9416666666666664,
|
| 3446 |
+
"grad_norm": 0.0999494650393646,
|
| 3447 |
+
"learning_rate": 8.63822002827957e-06,
|
| 3448 |
+
"loss": 2.2808,
|
| 3449 |
+
"step": 473
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 3.95,
|
| 3453 |
+
"grad_norm": 0.09229071300924392,
|
| 3454 |
+
"learning_rate": 8.57598685104047e-06,
|
| 3455 |
+
"loss": 2.2956,
|
| 3456 |
+
"step": 474
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 3.9583333333333335,
|
| 3460 |
+
"grad_norm": 0.0865252185258513,
|
| 3461 |
+
"learning_rate": 8.513888795240581e-06,
|
| 3462 |
+
"loss": 2.334,
|
| 3463 |
+
"step": 475
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 3.966666666666667,
|
| 3467 |
+
"grad_norm": 0.09221547471519957,
|
| 3468 |
+
"learning_rate": 8.451927167038297e-06,
|
| 3469 |
+
"loss": 2.3004,
|
| 3470 |
+
"step": 476
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 3.975,
|
| 3474 |
+
"grad_norm": 0.0929024717566319,
|
| 3475 |
+
"learning_rate": 8.390103269722415e-06,
|
| 3476 |
+
"loss": 2.2878,
|
| 3477 |
+
"step": 477
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 3.9833333333333334,
|
| 3481 |
+
"grad_norm": 0.08714753080075317,
|
| 3482 |
+
"learning_rate": 8.328418403684724e-06,
|
| 3483 |
+
"loss": 2.2178,
|
| 3484 |
+
"step": 478
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 3.9916666666666667,
|
| 3488 |
+
"grad_norm": 0.08720587931621408,
|
| 3489 |
+
"learning_rate": 8.26687386639267e-06,
|
| 3490 |
+
"loss": 2.3157,
|
| 3491 |
+
"step": 479
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 4.0,
|
| 3495 |
+
"grad_norm": 0.08995570371826912,
|
| 3496 |
+
"learning_rate": 8.205470952362037e-06,
|
| 3497 |
+
"loss": 2.337,
|
| 3498 |
+
"step": 480
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 4.0,
|
| 3502 |
+
"eval_loss": 2.378326177597046,
|
| 3503 |
+
"eval_runtime": 84.721,
|
| 3504 |
+
"eval_samples_per_second": 4.839,
|
| 3505 |
+
"eval_steps_per_second": 0.307,
|
| 3506 |
+
"step": 480
|
| 3507 |
+
},
|
| 3508 |
+
{
|
| 3509 |
+
"epoch": 4.008333333333334,
|
| 3510 |
+
"grad_norm": 0.08919113582730508,
|
| 3511 |
+
"learning_rate": 8.144210953129736e-06,
|
| 3512 |
+
"loss": 2.242,
|
| 3513 |
+
"step": 481
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 4.016666666666667,
|
| 3517 |
+
"grad_norm": 0.08759937125503202,
|
| 3518 |
+
"learning_rate": 8.083095157226652e-06,
|
| 3519 |
+
"loss": 2.2876,
|
| 3520 |
+
"step": 482
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 4.025,
|
| 3524 |
+
"grad_norm": 0.08753567164607333,
|
| 3525 |
+
"learning_rate": 8.022124850150492e-06,
|
| 3526 |
+
"loss": 2.3099,
|
| 3527 |
+
"step": 483
|
| 3528 |
+
},
|
| 3529 |
+
{
|
| 3530 |
+
"epoch": 4.033333333333333,
|
| 3531 |
+
"grad_norm": 0.09003114590609616,
|
| 3532 |
+
"learning_rate": 7.96130131433881e-06,
|
| 3533 |
+
"loss": 2.2634,
|
| 3534 |
+
"step": 484
|
| 3535 |
+
},
|
| 3536 |
+
{
|
| 3537 |
+
"epoch": 4.041666666666667,
|
| 3538 |
+
"grad_norm": 0.08927006210597378,
|
| 3539 |
+
"learning_rate": 7.900625829142002e-06,
|
| 3540 |
+
"loss": 2.286,
|
| 3541 |
+
"step": 485
|
| 3542 |
+
},
|
| 3543 |
+
{
|
| 3544 |
+
"epoch": 4.05,
|
| 3545 |
+
"grad_norm": 0.08991255421045895,
|
| 3546 |
+
"learning_rate": 7.840099670796362e-06,
|
| 3547 |
+
"loss": 2.2781,
|
| 3548 |
+
"step": 486
|
| 3549 |
+
},
|
| 3550 |
+
{
|
| 3551 |
+
"epoch": 4.058333333333334,
|
| 3552 |
+
"grad_norm": 0.09046469993347242,
|
| 3553 |
+
"learning_rate": 7.779724112397315e-06,
|
| 3554 |
+
"loss": 2.246,
|
| 3555 |
+
"step": 487
|
| 3556 |
+
},
|
| 3557 |
+
{
|
| 3558 |
+
"epoch": 4.066666666666666,
|
| 3559 |
+
"grad_norm": 0.08702068124653241,
|
| 3560 |
+
"learning_rate": 7.71950042387257e-06,
|
| 3561 |
+
"loss": 2.3044,
|
| 3562 |
+
"step": 488
|
| 3563 |
+
},
|
| 3564 |
+
{
|
| 3565 |
+
"epoch": 4.075,
|
| 3566 |
+
"grad_norm": 0.08866159081991672,
|
| 3567 |
+
"learning_rate": 7.659429871955434e-06,
|
| 3568 |
+
"loss": 2.3091,
|
| 3569 |
+
"step": 489
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 4.083333333333333,
|
| 3573 |
+
"grad_norm": 0.08637579658199847,
|
| 3574 |
+
"learning_rate": 7.599513720158189e-06,
|
| 3575 |
+
"loss": 2.2714,
|
| 3576 |
+
"step": 490
|
| 3577 |
+
},
|
| 3578 |
+
{
|
| 3579 |
+
"epoch": 4.091666666666667,
|
| 3580 |
+
"grad_norm": 0.08847148200976988,
|
| 3581 |
+
"learning_rate": 7.539753228745478e-06,
|
| 3582 |
+
"loss": 2.276,
|
| 3583 |
+
"step": 491
|
| 3584 |
+
},
|
| 3585 |
+
{
|
| 3586 |
+
"epoch": 4.1,
|
| 3587 |
+
"grad_norm": 0.09129247522362395,
|
| 3588 |
+
"learning_rate": 7.480149654707808e-06,
|
| 3589 |
+
"loss": 2.2878,
|
| 3590 |
+
"step": 492
|
| 3591 |
+
},
|
| 3592 |
+
{
|
| 3593 |
+
"epoch": 4.108333333333333,
|
| 3594 |
+
"grad_norm": 0.08838312475719622,
|
| 3595 |
+
"learning_rate": 7.420704251735141e-06,
|
| 3596 |
+
"loss": 2.3154,
|
| 3597 |
+
"step": 493
|
| 3598 |
+
},
|
| 3599 |
+
{
|
| 3600 |
+
"epoch": 4.116666666666666,
|
| 3601 |
+
"grad_norm": 0.08917895756883464,
|
| 3602 |
+
"learning_rate": 7.361418270190479e-06,
|
| 3603 |
+
"loss": 2.3019,
|
| 3604 |
+
"step": 494
|
| 3605 |
+
},
|
| 3606 |
+
{
|
| 3607 |
+
"epoch": 4.125,
|
| 3608 |
+
"grad_norm": 0.08272092199205452,
|
| 3609 |
+
"learning_rate": 7.302292957083587e-06,
|
| 3610 |
+
"loss": 2.2354,
|
| 3611 |
+
"step": 495
|
| 3612 |
+
},
|
| 3613 |
+
{
|
| 3614 |
+
"epoch": 4.133333333333334,
|
| 3615 |
+
"grad_norm": 0.08982095864229954,
|
| 3616 |
+
"learning_rate": 7.2433295560447655e-06,
|
| 3617 |
+
"loss": 2.3105,
|
| 3618 |
+
"step": 496
|
| 3619 |
+
},
|
| 3620 |
+
{
|
| 3621 |
+
"epoch": 4.141666666666667,
|
| 3622 |
+
"grad_norm": 0.0902386431754279,
|
| 3623 |
+
"learning_rate": 7.184529307298694e-06,
|
| 3624 |
+
"loss": 2.3137,
|
| 3625 |
+
"step": 497
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 4.15,
|
| 3629 |
+
"grad_norm": 0.08603100235627485,
|
| 3630 |
+
"learning_rate": 7.125893447638329e-06,
|
| 3631 |
+
"loss": 2.2916,
|
| 3632 |
+
"step": 498
|
| 3633 |
+
},
|
| 3634 |
+
{
|
| 3635 |
+
"epoch": 4.158333333333333,
|
| 3636 |
+
"grad_norm": 0.08712915794831784,
|
| 3637 |
+
"learning_rate": 7.067423210398903e-06,
|
| 3638 |
+
"loss": 2.2793,
|
| 3639 |
+
"step": 499
|
| 3640 |
+
},
|
| 3641 |
+
{
|
| 3642 |
+
"epoch": 4.166666666666667,
|
| 3643 |
+
"grad_norm": 0.08871665864799087,
|
| 3644 |
+
"learning_rate": 7.009119825431978e-06,
|
| 3645 |
+
"loss": 2.3179,
|
| 3646 |
+
"step": 500
|
| 3647 |
+
},
|
| 3648 |
+
{
|
| 3649 |
+
"epoch": 4.175,
|
| 3650 |
+
"grad_norm": 0.08856431988654334,
|
| 3651 |
+
"learning_rate": 6.95098451907957e-06,
|
| 3652 |
+
"loss": 2.2702,
|
| 3653 |
+
"step": 501
|
| 3654 |
+
},
|
| 3655 |
+
{
|
| 3656 |
+
"epoch": 4.183333333333334,
|
| 3657 |
+
"grad_norm": 0.09133555176554371,
|
| 3658 |
+
"learning_rate": 6.893018514148385e-06,
|
| 3659 |
+
"loss": 2.2762,
|
| 3660 |
+
"step": 502
|
| 3661 |
+
},
|
| 3662 |
+
{
|
| 3663 |
+
"epoch": 4.191666666666666,
|
| 3664 |
+
"grad_norm": 0.08792043831091591,
|
| 3665 |
+
"learning_rate": 6.835223029884053e-06,
|
| 3666 |
+
"loss": 2.2674,
|
| 3667 |
+
"step": 503
|
| 3668 |
+
},
|
| 3669 |
+
{
|
| 3670 |
+
"epoch": 4.2,
|
| 3671 |
+
"grad_norm": 0.08507815543168454,
|
| 3672 |
+
"learning_rate": 6.777599281945508e-06,
|
| 3673 |
+
"loss": 2.3366,
|
| 3674 |
+
"step": 504
|
| 3675 |
+
},
|
| 3676 |
+
{
|
| 3677 |
+
"epoch": 4.208333333333333,
|
| 3678 |
+
"grad_norm": 0.08343401034815186,
|
| 3679 |
+
"learning_rate": 6.720148482379437e-06,
|
| 3680 |
+
"loss": 2.2868,
|
| 3681 |
+
"step": 505
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"epoch": 4.216666666666667,
|
| 3685 |
+
"grad_norm": 0.09013730711797593,
|
| 3686 |
+
"learning_rate": 6.662871839594738e-06,
|
| 3687 |
+
"loss": 2.2756,
|
| 3688 |
+
"step": 506
|
| 3689 |
+
},
|
| 3690 |
+
{
|
| 3691 |
+
"epoch": 4.225,
|
| 3692 |
+
"grad_norm": 0.09372016399430004,
|
| 3693 |
+
"learning_rate": 6.6057705583371365e-06,
|
| 3694 |
+
"loss": 2.2952,
|
| 3695 |
+
"step": 507
|
| 3696 |
+
},
|
| 3697 |
+
{
|
| 3698 |
+
"epoch": 4.233333333333333,
|
| 3699 |
+
"grad_norm": 0.08935904879415948,
|
| 3700 |
+
"learning_rate": 6.5488458396638585e-06,
|
| 3701 |
+
"loss": 2.2661,
|
| 3702 |
+
"step": 508
|
| 3703 |
+
},
|
| 3704 |
+
{
|
| 3705 |
+
"epoch": 4.241666666666666,
|
| 3706 |
+
"grad_norm": 0.08924097873961723,
|
| 3707 |
+
"learning_rate": 6.492098880918309e-06,
|
| 3708 |
+
"loss": 2.2635,
|
| 3709 |
+
"step": 509
|
| 3710 |
+
},
|
| 3711 |
+
{
|
| 3712 |
+
"epoch": 4.25,
|
| 3713 |
+
"grad_norm": 0.09058785972120827,
|
| 3714 |
+
"learning_rate": 6.435530875704958e-06,
|
| 3715 |
+
"loss": 2.2319,
|
| 3716 |
+
"step": 510
|
| 3717 |
+
},
|
| 3718 |
+
{
|
| 3719 |
+
"epoch": 4.25,
|
| 3720 |
+
"eval_loss": 2.3782477378845215,
|
| 3721 |
+
"eval_runtime": 83.2835,
|
| 3722 |
+
"eval_samples_per_second": 4.923,
|
| 3723 |
+
"eval_steps_per_second": 0.312,
|
| 3724 |
+
"step": 510
|
| 3725 |
+
},
|
| 3726 |
+
{
|
| 3727 |
+
"epoch": 4.258333333333334,
|
| 3728 |
+
"grad_norm": 0.08929076585357533,
|
| 3729 |
+
"learning_rate": 6.3791430138641995e-06,
|
| 3730 |
+
"loss": 2.3013,
|
| 3731 |
+
"step": 511
|
| 3732 |
+
},
|
| 3733 |
+
{
|
| 3734 |
+
"epoch": 4.266666666666667,
|
| 3735 |
+
"grad_norm": 0.08879100075201603,
|
| 3736 |
+
"learning_rate": 6.3229364814472975e-06,
|
| 3737 |
+
"loss": 2.3238,
|
| 3738 |
+
"step": 512
|
| 3739 |
+
},
|
| 3740 |
+
{
|
| 3741 |
+
"epoch": 4.275,
|
| 3742 |
+
"grad_norm": 0.08522012607603127,
|
| 3743 |
+
"learning_rate": 6.266912460691504e-06,
|
| 3744 |
+
"loss": 2.297,
|
| 3745 |
+
"step": 513
|
| 3746 |
+
},
|
| 3747 |
+
{
|
| 3748 |
+
"epoch": 4.283333333333333,
|
| 3749 |
+
"grad_norm": 0.09055050762865996,
|
| 3750 |
+
"learning_rate": 6.2110721299951355e-06,
|
| 3751 |
+
"loss": 2.2563,
|
| 3752 |
+
"step": 514
|
| 3753 |
+
},
|
| 3754 |
+
{
|
| 3755 |
+
"epoch": 4.291666666666667,
|
| 3756 |
+
"grad_norm": 0.0863469759988823,
|
| 3757 |
+
"learning_rate": 6.155416663892809e-06,
|
| 3758 |
+
"loss": 2.3414,
|
| 3759 |
+
"step": 515
|
| 3760 |
+
},
|
| 3761 |
+
{
|
| 3762 |
+
"epoch": 4.3,
|
| 3763 |
+
"grad_norm": 0.08467266157554244,
|
| 3764 |
+
"learning_rate": 6.0999472330307485e-06,
|
| 3765 |
+
"loss": 2.2484,
|
| 3766 |
+
"step": 516
|
| 3767 |
+
},
|
| 3768 |
+
{
|
| 3769 |
+
"epoch": 4.308333333333334,
|
| 3770 |
+
"grad_norm": 0.08801603551205223,
|
| 3771 |
+
"learning_rate": 6.044665004142137e-06,
|
| 3772 |
+
"loss": 2.3089,
|
| 3773 |
+
"step": 517
|
| 3774 |
+
},
|
| 3775 |
+
{
|
| 3776 |
+
"epoch": 4.316666666666666,
|
| 3777 |
+
"grad_norm": 0.0844379883728587,
|
| 3778 |
+
"learning_rate": 5.9895711400225846e-06,
|
| 3779 |
+
"loss": 2.3152,
|
| 3780 |
+
"step": 518
|
| 3781 |
+
},
|
| 3782 |
+
{
|
| 3783 |
+
"epoch": 4.325,
|
| 3784 |
+
"grad_norm": 0.09475666975189992,
|
| 3785 |
+
"learning_rate": 5.93466679950569e-06,
|
| 3786 |
+
"loss": 2.2796,
|
| 3787 |
+
"step": 519
|
| 3788 |
+
},
|
| 3789 |
+
{
|
| 3790 |
+
"epoch": 4.333333333333333,
|
| 3791 |
+
"grad_norm": 0.08662508350751986,
|
| 3792 |
+
"learning_rate": 5.879953137438637e-06,
|
| 3793 |
+
"loss": 2.2695,
|
| 3794 |
+
"step": 520
|
| 3795 |
+
},
|
| 3796 |
+
{
|
| 3797 |
+
"epoch": 4.341666666666667,
|
| 3798 |
+
"grad_norm": 0.08739857009531579,
|
| 3799 |
+
"learning_rate": 5.825431304657915e-06,
|
| 3800 |
+
"loss": 2.3006,
|
| 3801 |
+
"step": 521
|
| 3802 |
+
},
|
| 3803 |
+
{
|
| 3804 |
+
"epoch": 4.35,
|
| 3805 |
+
"grad_norm": 0.1023467437625082,
|
| 3806 |
+
"learning_rate": 5.771102447965115e-06,
|
| 3807 |
+
"loss": 2.3026,
|
| 3808 |
+
"step": 522
|
| 3809 |
+
},
|
| 3810 |
+
{
|
| 3811 |
+
"epoch": 4.358333333333333,
|
| 3812 |
+
"grad_norm": 0.0870476312107288,
|
| 3813 |
+
"learning_rate": 5.7169677101028176e-06,
|
| 3814 |
+
"loss": 2.3286,
|
| 3815 |
+
"step": 523
|
| 3816 |
+
},
|
| 3817 |
+
{
|
| 3818 |
+
"epoch": 4.366666666666666,
|
| 3819 |
+
"grad_norm": 0.0883594327551923,
|
| 3820 |
+
"learning_rate": 5.663028229730531e-06,
|
| 3821 |
+
"loss": 2.3161,
|
| 3822 |
+
"step": 524
|
| 3823 |
+
},
|
| 3824 |
+
{
|
| 3825 |
+
"epoch": 4.375,
|
| 3826 |
+
"grad_norm": 0.09292418179947157,
|
| 3827 |
+
"learning_rate": 5.609285141400763e-06,
|
| 3828 |
+
"loss": 2.3068,
|
| 3829 |
+
"step": 525
|
| 3830 |
+
},
|
| 3831 |
+
{
|
| 3832 |
+
"epoch": 4.383333333333334,
|
| 3833 |
+
"grad_norm": 0.09093033900864315,
|
| 3834 |
+
"learning_rate": 5.555739575535148e-06,
|
| 3835 |
+
"loss": 2.2288,
|
| 3836 |
+
"step": 526
|
| 3837 |
+
},
|
| 3838 |
+
{
|
| 3839 |
+
"epoch": 4.391666666666667,
|
| 3840 |
+
"grad_norm": 0.0936908598434722,
|
| 3841 |
+
"learning_rate": 5.502392658400665e-06,
|
| 3842 |
+
"loss": 2.3246,
|
| 3843 |
+
"step": 527
|
| 3844 |
+
},
|
| 3845 |
+
{
|
| 3846 |
+
"epoch": 4.4,
|
| 3847 |
+
"grad_norm": 0.09415001109687457,
|
| 3848 |
+
"learning_rate": 5.449245512085971e-06,
|
| 3849 |
+
"loss": 2.2836,
|
| 3850 |
+
"step": 528
|
| 3851 |
+
},
|
| 3852 |
+
{
|
| 3853 |
+
"epoch": 4.408333333333333,
|
| 3854 |
+
"grad_norm": 0.0874544533868624,
|
| 3855 |
+
"learning_rate": 5.3962992544777685e-06,
|
| 3856 |
+
"loss": 2.304,
|
| 3857 |
+
"step": 529
|
| 3858 |
+
},
|
| 3859 |
+
{
|
| 3860 |
+
"epoch": 4.416666666666667,
|
| 3861 |
+
"grad_norm": 0.09231594022995022,
|
| 3862 |
+
"learning_rate": 5.343554999237304e-06,
|
| 3863 |
+
"loss": 2.3104,
|
| 3864 |
+
"step": 530
|
| 3865 |
+
},
|
| 3866 |
+
{
|
| 3867 |
+
"epoch": 4.425,
|
| 3868 |
+
"grad_norm": 0.08731188673980567,
|
| 3869 |
+
"learning_rate": 5.291013855776963e-06,
|
| 3870 |
+
"loss": 2.2607,
|
| 3871 |
+
"step": 531
|
| 3872 |
+
},
|
| 3873 |
+
{
|
| 3874 |
+
"epoch": 4.433333333333334,
|
| 3875 |
+
"grad_norm": 0.08802032808350461,
|
| 3876 |
+
"learning_rate": 5.238676929236897e-06,
|
| 3877 |
+
"loss": 2.2865,
|
| 3878 |
+
"step": 532
|
| 3879 |
+
},
|
| 3880 |
+
{
|
| 3881 |
+
"epoch": 4.441666666666666,
|
| 3882 |
+
"grad_norm": 0.08652840802895843,
|
| 3883 |
+
"learning_rate": 5.186545320461809e-06,
|
| 3884 |
+
"loss": 2.3104,
|
| 3885 |
+
"step": 533
|
| 3886 |
+
},
|
| 3887 |
+
{
|
| 3888 |
+
"epoch": 4.45,
|
| 3889 |
+
"grad_norm": 0.09441825138651445,
|
| 3890 |
+
"learning_rate": 5.1346201259777945e-06,
|
| 3891 |
+
"loss": 2.2924,
|
| 3892 |
+
"step": 534
|
| 3893 |
+
},
|
| 3894 |
+
{
|
| 3895 |
+
"epoch": 4.458333333333333,
|
| 3896 |
+
"grad_norm": 0.08530615857488104,
|
| 3897 |
+
"learning_rate": 5.082902437969249e-06,
|
| 3898 |
+
"loss": 2.1971,
|
| 3899 |
+
"step": 535
|
| 3900 |
+
},
|
| 3901 |
+
{
|
| 3902 |
+
"epoch": 4.466666666666667,
|
| 3903 |
+
"grad_norm": 0.09159068805971998,
|
| 3904 |
+
"learning_rate": 5.031393344255939e-06,
|
| 3905 |
+
"loss": 2.237,
|
| 3906 |
+
"step": 536
|
| 3907 |
+
},
|
| 3908 |
+
{
|
| 3909 |
+
"epoch": 4.475,
|
| 3910 |
+
"grad_norm": 0.08654553449940829,
|
| 3911 |
+
"learning_rate": 4.980093928270101e-06,
|
| 3912 |
+
"loss": 2.2438,
|
| 3913 |
+
"step": 537
|
| 3914 |
+
},
|
| 3915 |
+
{
|
| 3916 |
+
"epoch": 4.483333333333333,
|
| 3917 |
+
"grad_norm": 0.09484247338609686,
|
| 3918 |
+
"learning_rate": 4.929005269033625e-06,
|
| 3919 |
+
"loss": 2.2471,
|
| 3920 |
+
"step": 538
|
| 3921 |
+
},
|
| 3922 |
+
{
|
| 3923 |
+
"epoch": 4.491666666666666,
|
| 3924 |
+
"grad_norm": 0.08868650217559723,
|
| 3925 |
+
"learning_rate": 4.878128441135415e-06,
|
| 3926 |
+
"loss": 2.2412,
|
| 3927 |
+
"step": 539
|
| 3928 |
+
},
|
| 3929 |
+
{
|
| 3930 |
+
"epoch": 4.5,
|
| 3931 |
+
"grad_norm": 0.0908142386130087,
|
| 3932 |
+
"learning_rate": 4.827464514708738e-06,
|
| 3933 |
+
"loss": 2.3044,
|
| 3934 |
+
"step": 540
|
| 3935 |
+
},
|
| 3936 |
+
{
|
| 3937 |
+
"epoch": 4.5,
|
| 3938 |
+
"eval_loss": 2.377849817276001,
|
| 3939 |
+
"eval_runtime": 84.2146,
|
| 3940 |
+
"eval_samples_per_second": 4.869,
|
| 3941 |
+
"eval_steps_per_second": 0.309,
|
| 3942 |
+
"step": 540
|
| 3943 |
+
}
|
| 3944 |
+
],
|
| 3945 |
+
"logging_steps": 1,
|
| 3946 |
+
"max_steps": 720,
|
| 3947 |
+
"num_input_tokens_seen": 0,
|
| 3948 |
+
"num_train_epochs": 6,
|
| 3949 |
+
"save_steps": 60,
|
| 3950 |
+
"stateful_callbacks": {
|
| 3951 |
+
"TrainerControl": {
|
| 3952 |
+
"args": {
|
| 3953 |
+
"should_epoch_stop": false,
|
| 3954 |
+
"should_evaluate": false,
|
| 3955 |
+
"should_log": false,
|
| 3956 |
+
"should_save": true,
|
| 3957 |
+
"should_training_stop": false
|
| 3958 |
+
},
|
| 3959 |
+
"attributes": {}
|
| 3960 |
+
}
|
| 3961 |
+
},
|
| 3962 |
+
"total_flos": 6.69966982447104e+17,
|
| 3963 |
+
"train_batch_size": 4,
|
| 3964 |
+
"trial_name": null,
|
| 3965 |
+
"trial_params": null
|
| 3966 |
+
}
|
checkpoint-540/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb7b58ef47c3b4ab10c3901b5a9844fd2d6ee742a2bc050a4e5243187413021
|
| 3 |
+
size 8504
|
checkpoint-540/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
checkpoint-600/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: NewEden/Hamanasu-KTO-V2
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.15.0
|
checkpoint-600/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NewEden/Hamanasu-KTO-V2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": null,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 16,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"q_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": true
|
| 39 |
+
}
|
checkpoint-600/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a429e00a4159ae5441fceafb2797c0ba91019820cedf671b3e7bfdb8d62cfd63
|
| 3 |
+
size 486600536
|
checkpoint-600/global_step600/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4074007683b666ac26b2f47adf36124b70a6d979875a8096eaa63254360bcbb
|
| 3 |
+
size 367555424
|
checkpoint-600/global_step600/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fc2fe522c72409a28f210f418f87577ff0ba52265218116c9c9ff5cabb96d38
|
| 3 |
+
size 367555424
|
checkpoint-600/global_step600/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e660f0d70af2499ed197c977ce3c43d9949e7998fc16f082a1abe1c3915ee4ed
|
| 3 |
+
size 367555424
|
checkpoint-600/global_step600/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:feb1f4d04dfb0533c9a46b9c8d525469394a64f343f9eccde6fd7dc182112305
|
| 3 |
+
size 367555424
|
checkpoint-600/global_step600/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4030f40992c5b8ed888dcbe5b1c9b80333baed09999d9efa3a4f0e03a1f11a95
|
| 3 |
+
size 445742
|
checkpoint-600/global_step600/zero_pp_rank_1_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ba7bc54ee782a17cf90ad446b6fa4c9769a368449ec4248911d8ade159feb87
|
| 3 |
+
size 445742
|
checkpoint-600/global_step600/zero_pp_rank_2_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e4ad48eb9060f4ae5f4c7dba62b5c0364471b6fe2517b74d9622d3880c5cda8
|
| 3 |
+
size 445742
|
checkpoint-600/global_step600/zero_pp_rank_3_mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01d01dbefa6dca1b7017012be3927aab0a15afa7f19538542bb9d6915ea3b4b
|
| 3 |
+
size 445742
|
checkpoint-600/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step600
|
checkpoint-600/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9480b60b05f055cd4d695a7fb67c9f0044c2698b122f8e768e76700a5a0e112
|
| 3 |
+
size 15024
|
checkpoint-600/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da187b810cec1abaaa2431af10b1b94e8822262d318925bf12b16cd21e2f9b93
|
| 3 |
+
size 15024
|
checkpoint-600/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31458a8829f8cf89c81f1ddf69e47012ed5d3d6442585bee25ff000990cb083f
|
| 3 |
+
size 15024
|
checkpoint-600/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a75a399aa643df98ad214eff95d6a2d8cd728651d1ad642041ea9358cb06a99
|
| 3 |
+
size 15024
|
checkpoint-600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:931e964d0930e95ef4a1d44c2a5968749599a01251a42143fb9c5e6bdd9e426e
|
| 3 |
+
size 1064
|
checkpoint-600/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_end|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|finetune_right_pad_id|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-600/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:907a7b3b13afcc9d481433f17277a6dd7cf852c6185262597f1a849d2ebeaa45
|
| 3 |
+
size 17209884
|
checkpoint-600/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|im_start|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|im_end|>",
|
| 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": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 2054 |
+
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|im_end|>",
|
| 2056 |
+
"extra_special_tokens": {},
|
| 2057 |
+
"model_input_names": [
|
| 2058 |
+
"input_ids",
|
| 2059 |
+
"attention_mask"
|
| 2060 |
+
],
|
| 2061 |
+
"model_max_length": 131072,
|
| 2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
| 2063 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 2064 |
+
}
|
checkpoint-600/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb7b58ef47c3b4ab10c3901b5a9844fd2d6ee742a2bc050a4e5243187413021
|
| 3 |
+
size 8504
|