Training in progress, epoch 0
Browse files- README.md +276 -0
- adapter_config.json +34 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- config.json +29 -0
- merges.txt +0 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +63 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen2.5-1.5B
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: 029f10e5-2608-4fa0-b8bb-cbdc2ba54829
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
[<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)
|
| 17 |
+
<details><summary>See axolotl config</summary>
|
| 18 |
+
|
| 19 |
+
axolotl version: `0.4.1`
|
| 20 |
+
```yaml
|
| 21 |
+
adapter: lora
|
| 22 |
+
base_model: Qwen/Qwen2.5-1.5B
|
| 23 |
+
bf16: auto
|
| 24 |
+
dataset_prepared_path: null
|
| 25 |
+
datasets:
|
| 26 |
+
- data_files:
|
| 27 |
+
- b45999760ef35661_train_data.json
|
| 28 |
+
ds_type: json
|
| 29 |
+
format: custom
|
| 30 |
+
path: /root/G.O.D-test/core/data/b45999760ef35661_train_data.json
|
| 31 |
+
type:
|
| 32 |
+
field_input: system_prompt
|
| 33 |
+
field_instruction: problem
|
| 34 |
+
field_output: solution
|
| 35 |
+
format: '{instruction} {input}'
|
| 36 |
+
no_input_format: '{instruction}'
|
| 37 |
+
system_format: '{system}'
|
| 38 |
+
system_prompt: ''
|
| 39 |
+
debug: null
|
| 40 |
+
deepspeed: null
|
| 41 |
+
early_stopping_patience: null
|
| 42 |
+
eval_max_new_tokens: 128
|
| 43 |
+
eval_table_size: null
|
| 44 |
+
evals_per_epoch: 50
|
| 45 |
+
flash_attention: false
|
| 46 |
+
fp16: null
|
| 47 |
+
fsdp: null
|
| 48 |
+
fsdp_config: null
|
| 49 |
+
gradient_accumulation_steps: 4
|
| 50 |
+
gradient_checkpointing: false
|
| 51 |
+
group_by_length: false
|
| 52 |
+
hub_model_id: souging/029f10e5-2608-4fa0-b8bb-cbdc2ba54829
|
| 53 |
+
hub_repo: null
|
| 54 |
+
hub_strategy: checkpoint
|
| 55 |
+
hub_token: null
|
| 56 |
+
learning_rate: 0.0002
|
| 57 |
+
load_in_4bit: false
|
| 58 |
+
load_in_8bit: false
|
| 59 |
+
local_rank: null
|
| 60 |
+
logging_steps: 1
|
| 61 |
+
lora_alpha: 64
|
| 62 |
+
lora_dropout: 0.05
|
| 63 |
+
lora_fan_in_fan_out: null
|
| 64 |
+
lora_model_dir: null
|
| 65 |
+
lora_r: 32
|
| 66 |
+
lora_target_linear: true
|
| 67 |
+
lr_scheduler: cosine
|
| 68 |
+
max_steps: 500
|
| 69 |
+
micro_batch_size: 3
|
| 70 |
+
mlflow_experiment_name: /tmp/b45999760ef35661_train_data.json
|
| 71 |
+
model_type: AutoModelForCausalLM
|
| 72 |
+
num_epochs: 3
|
| 73 |
+
optimizer: adamw_bnb_8bit
|
| 74 |
+
output_dir: miner_id_24
|
| 75 |
+
pad_to_sequence_len: true
|
| 76 |
+
resume_from_checkpoint: null
|
| 77 |
+
s2_attention: null
|
| 78 |
+
sample_packing: false
|
| 79 |
+
saves_per_epoch: 50
|
| 80 |
+
sequence_len: 1024
|
| 81 |
+
strict: false
|
| 82 |
+
tf32: false
|
| 83 |
+
tokenizer_type: AutoTokenizer
|
| 84 |
+
train_on_inputs: false
|
| 85 |
+
trust_remote_code: true
|
| 86 |
+
val_set_size: 0.05
|
| 87 |
+
wandb_entity: null
|
| 88 |
+
wandb_mode: online
|
| 89 |
+
wandb_name: 2fcab945-37d4-4262-b912-3bc4bdc46e98
|
| 90 |
+
wandb_project: Gradients-On-Demand
|
| 91 |
+
wandb_run: your_name
|
| 92 |
+
wandb_runid: 2fcab945-37d4-4262-b912-3bc4bdc46e98
|
| 93 |
+
warmup_steps: 100
|
| 94 |
+
weight_decay: 0.01
|
| 95 |
+
xformers_attention: null
|
| 96 |
+
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
</details><br>
|
| 100 |
+
|
| 101 |
+
# 029f10e5-2608-4fa0-b8bb-cbdc2ba54829
|
| 102 |
+
|
| 103 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the None dataset.
|
| 104 |
+
It achieves the following results on the evaluation set:
|
| 105 |
+
- Loss: 0.5337
|
| 106 |
+
|
| 107 |
+
## Model description
|
| 108 |
+
|
| 109 |
+
More information needed
|
| 110 |
+
|
| 111 |
+
## Intended uses & limitations
|
| 112 |
+
|
| 113 |
+
More information needed
|
| 114 |
+
|
| 115 |
+
## Training and evaluation data
|
| 116 |
+
|
| 117 |
+
More information needed
|
| 118 |
+
|
| 119 |
+
## Training procedure
|
| 120 |
+
|
| 121 |
+
### Training hyperparameters
|
| 122 |
+
|
| 123 |
+
The following hyperparameters were used during training:
|
| 124 |
+
- learning_rate: 0.0002
|
| 125 |
+
- train_batch_size: 3
|
| 126 |
+
- eval_batch_size: 3
|
| 127 |
+
- seed: 42
|
| 128 |
+
- distributed_type: multi-GPU
|
| 129 |
+
- num_devices: 8
|
| 130 |
+
- gradient_accumulation_steps: 4
|
| 131 |
+
- total_train_batch_size: 96
|
| 132 |
+
- total_eval_batch_size: 24
|
| 133 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 134 |
+
- lr_scheduler_type: cosine
|
| 135 |
+
- lr_scheduler_warmup_steps: 100
|
| 136 |
+
- training_steps: 500
|
| 137 |
+
|
| 138 |
+
### Training results
|
| 139 |
+
|
| 140 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 141 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 142 |
+
| 0.8119 | 0.0020 | 1 | 0.8480 |
|
| 143 |
+
| 0.8458 | 0.0081 | 4 | 0.8464 |
|
| 144 |
+
| 0.9139 | 0.0162 | 8 | 0.8185 |
|
| 145 |
+
| 0.7918 | 0.0243 | 12 | 0.7595 |
|
| 146 |
+
| 0.7346 | 0.0324 | 16 | 0.6953 |
|
| 147 |
+
| 0.7496 | 0.0405 | 20 | 0.6672 |
|
| 148 |
+
| 0.6417 | 0.0486 | 24 | 0.6474 |
|
| 149 |
+
| 0.6411 | 0.0567 | 28 | 0.6337 |
|
| 150 |
+
| 0.5976 | 0.0648 | 32 | 0.6236 |
|
| 151 |
+
| 0.6149 | 0.0729 | 36 | 0.6156 |
|
| 152 |
+
| 0.6517 | 0.0810 | 40 | 0.6091 |
|
| 153 |
+
| 0.578 | 0.0891 | 44 | 0.6025 |
|
| 154 |
+
| 0.5751 | 0.0972 | 48 | 0.5978 |
|
| 155 |
+
| 0.5774 | 0.1053 | 52 | 0.5933 |
|
| 156 |
+
| 0.5904 | 0.1134 | 56 | 0.5896 |
|
| 157 |
+
| 0.6291 | 0.1215 | 60 | 0.5862 |
|
| 158 |
+
| 0.6046 | 0.1296 | 64 | 0.5829 |
|
| 159 |
+
| 0.5971 | 0.1377 | 68 | 0.5801 |
|
| 160 |
+
| 0.5339 | 0.1457 | 72 | 0.5778 |
|
| 161 |
+
| 0.5838 | 0.1538 | 76 | 0.5762 |
|
| 162 |
+
| 0.5879 | 0.1619 | 80 | 0.5744 |
|
| 163 |
+
| 0.6243 | 0.1700 | 84 | 0.5727 |
|
| 164 |
+
| 0.5588 | 0.1781 | 88 | 0.5710 |
|
| 165 |
+
| 0.5582 | 0.1862 | 92 | 0.5703 |
|
| 166 |
+
| 0.4996 | 0.1943 | 96 | 0.5688 |
|
| 167 |
+
| 0.5783 | 0.2024 | 100 | 0.5679 |
|
| 168 |
+
| 0.5992 | 0.2105 | 104 | 0.5669 |
|
| 169 |
+
| 0.576 | 0.2186 | 108 | 0.5658 |
|
| 170 |
+
| 0.5396 | 0.2267 | 112 | 0.5652 |
|
| 171 |
+
| 0.5277 | 0.2348 | 116 | 0.5636 |
|
| 172 |
+
| 0.5383 | 0.2429 | 120 | 0.5633 |
|
| 173 |
+
| 0.5742 | 0.2510 | 124 | 0.5617 |
|
| 174 |
+
| 0.5488 | 0.2591 | 128 | 0.5610 |
|
| 175 |
+
| 0.5117 | 0.2672 | 132 | 0.5596 |
|
| 176 |
+
| 0.597 | 0.2753 | 136 | 0.5598 |
|
| 177 |
+
| 0.5429 | 0.2834 | 140 | 0.5586 |
|
| 178 |
+
| 0.5275 | 0.2915 | 144 | 0.5580 |
|
| 179 |
+
| 0.6284 | 0.2996 | 148 | 0.5569 |
|
| 180 |
+
| 0.5636 | 0.3077 | 152 | 0.5565 |
|
| 181 |
+
| 0.5918 | 0.3158 | 156 | 0.5560 |
|
| 182 |
+
| 0.5125 | 0.3239 | 160 | 0.5551 |
|
| 183 |
+
| 0.5762 | 0.3320 | 164 | 0.5548 |
|
| 184 |
+
| 0.5175 | 0.3401 | 168 | 0.5546 |
|
| 185 |
+
| 0.5223 | 0.3482 | 172 | 0.5540 |
|
| 186 |
+
| 0.6249 | 0.3563 | 176 | 0.5535 |
|
| 187 |
+
| 0.6143 | 0.3644 | 180 | 0.5531 |
|
| 188 |
+
| 0.5562 | 0.3725 | 184 | 0.5523 |
|
| 189 |
+
| 0.5256 | 0.3806 | 188 | 0.5519 |
|
| 190 |
+
| 0.5949 | 0.3887 | 192 | 0.5517 |
|
| 191 |
+
| 0.5851 | 0.3968 | 196 | 0.5515 |
|
| 192 |
+
| 0.5621 | 0.4049 | 200 | 0.5506 |
|
| 193 |
+
| 0.6014 | 0.4130 | 204 | 0.5499 |
|
| 194 |
+
| 0.6253 | 0.4211 | 208 | 0.5492 |
|
| 195 |
+
| 0.5418 | 0.4291 | 212 | 0.5492 |
|
| 196 |
+
| 0.5466 | 0.4372 | 216 | 0.5486 |
|
| 197 |
+
| 0.5654 | 0.4453 | 220 | 0.5484 |
|
| 198 |
+
| 0.519 | 0.4534 | 224 | 0.5480 |
|
| 199 |
+
| 0.5804 | 0.4615 | 228 | 0.5475 |
|
| 200 |
+
| 0.5876 | 0.4696 | 232 | 0.5470 |
|
| 201 |
+
| 0.5056 | 0.4777 | 236 | 0.5465 |
|
| 202 |
+
| 0.6075 | 0.4858 | 240 | 0.5466 |
|
| 203 |
+
| 0.5904 | 0.4939 | 244 | 0.5459 |
|
| 204 |
+
| 0.5132 | 0.5020 | 248 | 0.5459 |
|
| 205 |
+
| 0.5408 | 0.5101 | 252 | 0.5451 |
|
| 206 |
+
| 0.5664 | 0.5182 | 256 | 0.5449 |
|
| 207 |
+
| 0.5504 | 0.5263 | 260 | 0.5445 |
|
| 208 |
+
| 0.586 | 0.5344 | 264 | 0.5444 |
|
| 209 |
+
| 0.5636 | 0.5425 | 268 | 0.5437 |
|
| 210 |
+
| 0.5426 | 0.5506 | 272 | 0.5438 |
|
| 211 |
+
| 0.5506 | 0.5587 | 276 | 0.5432 |
|
| 212 |
+
| 0.5304 | 0.5668 | 280 | 0.5427 |
|
| 213 |
+
| 0.5274 | 0.5749 | 284 | 0.5425 |
|
| 214 |
+
| 0.5152 | 0.5830 | 288 | 0.5429 |
|
| 215 |
+
| 0.5268 | 0.5911 | 292 | 0.5418 |
|
| 216 |
+
| 0.5583 | 0.5992 | 296 | 0.5412 |
|
| 217 |
+
| 0.5721 | 0.6073 | 300 | 0.5413 |
|
| 218 |
+
| 0.5267 | 0.6154 | 304 | 0.5408 |
|
| 219 |
+
| 0.4977 | 0.6235 | 308 | 0.5404 |
|
| 220 |
+
| 0.5398 | 0.6316 | 312 | 0.5404 |
|
| 221 |
+
| 0.4885 | 0.6397 | 316 | 0.5399 |
|
| 222 |
+
| 0.4874 | 0.6478 | 320 | 0.5395 |
|
| 223 |
+
| 0.543 | 0.6559 | 324 | 0.5392 |
|
| 224 |
+
| 0.5303 | 0.6640 | 328 | 0.5388 |
|
| 225 |
+
| 0.4639 | 0.6721 | 332 | 0.5386 |
|
| 226 |
+
| 0.5597 | 0.6802 | 336 | 0.5383 |
|
| 227 |
+
| 0.5399 | 0.6883 | 340 | 0.5380 |
|
| 228 |
+
| 0.595 | 0.6964 | 344 | 0.5377 |
|
| 229 |
+
| 0.5646 | 0.7045 | 348 | 0.5375 |
|
| 230 |
+
| 0.5836 | 0.7126 | 352 | 0.5372 |
|
| 231 |
+
| 0.5705 | 0.7206 | 356 | 0.5372 |
|
| 232 |
+
| 0.5366 | 0.7287 | 360 | 0.5371 |
|
| 233 |
+
| 0.5268 | 0.7368 | 364 | 0.5370 |
|
| 234 |
+
| 0.5043 | 0.7449 | 368 | 0.5366 |
|
| 235 |
+
| 0.5235 | 0.7530 | 372 | 0.5365 |
|
| 236 |
+
| 0.5688 | 0.7611 | 376 | 0.5364 |
|
| 237 |
+
| 0.594 | 0.7692 | 380 | 0.5361 |
|
| 238 |
+
| 0.4947 | 0.7773 | 384 | 0.5360 |
|
| 239 |
+
| 0.5625 | 0.7854 | 388 | 0.5357 |
|
| 240 |
+
| 0.5373 | 0.7935 | 392 | 0.5357 |
|
| 241 |
+
| 0.5124 | 0.8016 | 396 | 0.5355 |
|
| 242 |
+
| 0.526 | 0.8097 | 400 | 0.5352 |
|
| 243 |
+
| 0.4984 | 0.8178 | 404 | 0.5351 |
|
| 244 |
+
| 0.5642 | 0.8259 | 408 | 0.5348 |
|
| 245 |
+
| 0.5353 | 0.8340 | 412 | 0.5347 |
|
| 246 |
+
| 0.4514 | 0.8421 | 416 | 0.5347 |
|
| 247 |
+
| 0.5735 | 0.8502 | 420 | 0.5345 |
|
| 248 |
+
| 0.5252 | 0.8583 | 424 | 0.5344 |
|
| 249 |
+
| 0.5355 | 0.8664 | 428 | 0.5343 |
|
| 250 |
+
| 0.4927 | 0.8745 | 432 | 0.5342 |
|
| 251 |
+
| 0.5029 | 0.8826 | 436 | 0.5341 |
|
| 252 |
+
| 0.547 | 0.8907 | 440 | 0.5340 |
|
| 253 |
+
| 0.5855 | 0.8988 | 444 | 0.5339 |
|
| 254 |
+
| 0.564 | 0.9069 | 448 | 0.5339 |
|
| 255 |
+
| 0.5686 | 0.9150 | 452 | 0.5339 |
|
| 256 |
+
| 0.5222 | 0.9231 | 456 | 0.5338 |
|
| 257 |
+
| 0.5158 | 0.9312 | 460 | 0.5337 |
|
| 258 |
+
| 0.523 | 0.9393 | 464 | 0.5337 |
|
| 259 |
+
| 0.564 | 0.9474 | 468 | 0.5337 |
|
| 260 |
+
| 0.4984 | 0.9555 | 472 | 0.5337 |
|
| 261 |
+
| 0.54 | 0.9636 | 476 | 0.5337 |
|
| 262 |
+
| 0.5355 | 0.9717 | 480 | 0.5337 |
|
| 263 |
+
| 0.5528 | 0.9798 | 484 | 0.5337 |
|
| 264 |
+
| 0.5192 | 0.9879 | 488 | 0.5336 |
|
| 265 |
+
| 0.4789 | 0.9960 | 492 | 0.5337 |
|
| 266 |
+
| 0.5134 | 1.0040 | 496 | 0.5336 |
|
| 267 |
+
| 0.5032 | 1.0121 | 500 | 0.5337 |
|
| 268 |
+
|
| 269 |
+
|
| 270 |
+
### Framework versions
|
| 271 |
+
|
| 272 |
+
- PEFT 0.13.2
|
| 273 |
+
- Transformers 4.46.0
|
| 274 |
+
- Pytorch 2.5.0+cu124
|
| 275 |
+
- Datasets 3.0.1
|
| 276 |
+
- Tokenizers 0.20.3
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": null,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 64,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"up_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b69ede4697fbedc28670b49fa75ffb7318090d1b887d5a26ac8232e56ef1daf8
|
| 3 |
+
size 147859242
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee8c79b897e7f1924a495c74f6ad15fbb9e24b7ffbdd66fa9030d2ce61b29ac8
|
| 3 |
+
size 335604696
|
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|im_end|>": 32000,
|
| 3 |
+
"<|im_start|>": 32001
|
| 4 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_attn_implementation_autoset": true,
|
| 3 |
+
"_name_or_path": "unsloth/OpenHermes-2.5-Mistral-7B",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MistralForCausalLM"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 32000,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"max_position_embeddings": 32768,
|
| 16 |
+
"model_type": "mistral",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"sliding_window": 4096,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.46.0",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"vocab_size": 32002
|
| 29 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 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": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": true,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<|im_end|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"32001": {
|
| 39 |
+
"content": "<|im_start|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
}
|
| 46 |
+
},
|
| 47 |
+
"additional_special_tokens": [],
|
| 48 |
+
"bos_token": "<s>",
|
| 49 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 50 |
+
"clean_up_tokenization_spaces": false,
|
| 51 |
+
"eos_token": "<|im_end|>",
|
| 52 |
+
"legacy": true,
|
| 53 |
+
"model_max_length": 32768,
|
| 54 |
+
"pad_token": "<unk>",
|
| 55 |
+
"padding_side": "right",
|
| 56 |
+
"sp_model_kwargs": {},
|
| 57 |
+
"spaces_between_special_tokens": false,
|
| 58 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 59 |
+
"trust_remote_code": false,
|
| 60 |
+
"unk_token": "<unk>",
|
| 61 |
+
"use_default_system_prompt": true,
|
| 62 |
+
"use_fast": true
|
| 63 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41aeb69cd9f4330b87bfb989691efe277eaa940f32f9d548da7686deb8a59dbd
|
| 3 |
+
size 6264
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|