--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B tags: - axolotl - generated_from_trainer model-index: - name: 029f10e5-2608-4fa0-b8bb-cbdc2ba54829 results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: Qwen/Qwen2.5-1.5B bf16: auto dataset_prepared_path: null datasets: - data_files: - b45999760ef35661_train_data.json ds_type: json format: custom path: /root/G.O.D-test/core/data/b45999760ef35661_train_data.json type: field_input: system_prompt field_instruction: problem field_output: solution format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 50 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: souging/029f10e5-2608-4fa0-b8bb-cbdc2ba54829 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 500 micro_batch_size: 3 mlflow_experiment_name: /tmp/b45999760ef35661_train_data.json model_type: AutoModelForCausalLM num_epochs: 3 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 50 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 2fcab945-37d4-4262-b912-3bc4bdc46e98 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 2fcab945-37d4-4262-b912-3bc4bdc46e98 warmup_steps: 100 weight_decay: 0.01 xformers_attention: null ```

# 029f10e5-2608-4fa0-b8bb-cbdc2ba54829 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. It achieves the following results on the evaluation set: - Loss: 0.5337 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 3 - eval_batch_size: 3 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 96 - total_eval_batch_size: 24 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 500 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 0.8119 | 0.0020 | 1 | 0.8480 | | 0.8458 | 0.0081 | 4 | 0.8464 | | 0.9139 | 0.0162 | 8 | 0.8185 | | 0.7918 | 0.0243 | 12 | 0.7595 | | 0.7346 | 0.0324 | 16 | 0.6953 | | 0.7496 | 0.0405 | 20 | 0.6672 | | 0.6417 | 0.0486 | 24 | 0.6474 | | 0.6411 | 0.0567 | 28 | 0.6337 | | 0.5976 | 0.0648 | 32 | 0.6236 | | 0.6149 | 0.0729 | 36 | 0.6156 | | 0.6517 | 0.0810 | 40 | 0.6091 | | 0.578 | 0.0891 | 44 | 0.6025 | | 0.5751 | 0.0972 | 48 | 0.5978 | | 0.5774 | 0.1053 | 52 | 0.5933 | | 0.5904 | 0.1134 | 56 | 0.5896 | | 0.6291 | 0.1215 | 60 | 0.5862 | | 0.6046 | 0.1296 | 64 | 0.5829 | | 0.5971 | 0.1377 | 68 | 0.5801 | | 0.5339 | 0.1457 | 72 | 0.5778 | | 0.5838 | 0.1538 | 76 | 0.5762 | | 0.5879 | 0.1619 | 80 | 0.5744 | | 0.6243 | 0.1700 | 84 | 0.5727 | | 0.5588 | 0.1781 | 88 | 0.5710 | | 0.5582 | 0.1862 | 92 | 0.5703 | | 0.4996 | 0.1943 | 96 | 0.5688 | | 0.5783 | 0.2024 | 100 | 0.5679 | | 0.5992 | 0.2105 | 104 | 0.5669 | | 0.576 | 0.2186 | 108 | 0.5658 | | 0.5396 | 0.2267 | 112 | 0.5652 | | 0.5277 | 0.2348 | 116 | 0.5636 | | 0.5383 | 0.2429 | 120 | 0.5633 | | 0.5742 | 0.2510 | 124 | 0.5617 | | 0.5488 | 0.2591 | 128 | 0.5610 | | 0.5117 | 0.2672 | 132 | 0.5596 | | 0.597 | 0.2753 | 136 | 0.5598 | | 0.5429 | 0.2834 | 140 | 0.5586 | | 0.5275 | 0.2915 | 144 | 0.5580 | | 0.6284 | 0.2996 | 148 | 0.5569 | | 0.5636 | 0.3077 | 152 | 0.5565 | | 0.5918 | 0.3158 | 156 | 0.5560 | | 0.5125 | 0.3239 | 160 | 0.5551 | | 0.5762 | 0.3320 | 164 | 0.5548 | | 0.5175 | 0.3401 | 168 | 0.5546 | | 0.5223 | 0.3482 | 172 | 0.5540 | | 0.6249 | 0.3563 | 176 | 0.5535 | | 0.6143 | 0.3644 | 180 | 0.5531 | | 0.5562 | 0.3725 | 184 | 0.5523 | | 0.5256 | 0.3806 | 188 | 0.5519 | | 0.5949 | 0.3887 | 192 | 0.5517 | | 0.5851 | 0.3968 | 196 | 0.5515 | | 0.5621 | 0.4049 | 200 | 0.5506 | | 0.6014 | 0.4130 | 204 | 0.5499 | | 0.6253 | 0.4211 | 208 | 0.5492 | | 0.5418 | 0.4291 | 212 | 0.5492 | | 0.5466 | 0.4372 | 216 | 0.5486 | | 0.5654 | 0.4453 | 220 | 0.5484 | | 0.519 | 0.4534 | 224 | 0.5480 | | 0.5804 | 0.4615 | 228 | 0.5475 | | 0.5876 | 0.4696 | 232 | 0.5470 | | 0.5056 | 0.4777 | 236 | 0.5465 | | 0.6075 | 0.4858 | 240 | 0.5466 | | 0.5904 | 0.4939 | 244 | 0.5459 | | 0.5132 | 0.5020 | 248 | 0.5459 | | 0.5408 | 0.5101 | 252 | 0.5451 | | 0.5664 | 0.5182 | 256 | 0.5449 | | 0.5504 | 0.5263 | 260 | 0.5445 | | 0.586 | 0.5344 | 264 | 0.5444 | | 0.5636 | 0.5425 | 268 | 0.5437 | | 0.5426 | 0.5506 | 272 | 0.5438 | | 0.5506 | 0.5587 | 276 | 0.5432 | | 0.5304 | 0.5668 | 280 | 0.5427 | | 0.5274 | 0.5749 | 284 | 0.5425 | | 0.5152 | 0.5830 | 288 | 0.5429 | | 0.5268 | 0.5911 | 292 | 0.5418 | | 0.5583 | 0.5992 | 296 | 0.5412 | | 0.5721 | 0.6073 | 300 | 0.5413 | | 0.5267 | 0.6154 | 304 | 0.5408 | | 0.4977 | 0.6235 | 308 | 0.5404 | | 0.5398 | 0.6316 | 312 | 0.5404 | | 0.4885 | 0.6397 | 316 | 0.5399 | | 0.4874 | 0.6478 | 320 | 0.5395 | | 0.543 | 0.6559 | 324 | 0.5392 | | 0.5303 | 0.6640 | 328 | 0.5388 | | 0.4639 | 0.6721 | 332 | 0.5386 | | 0.5597 | 0.6802 | 336 | 0.5383 | | 0.5399 | 0.6883 | 340 | 0.5380 | | 0.595 | 0.6964 | 344 | 0.5377 | | 0.5646 | 0.7045 | 348 | 0.5375 | | 0.5836 | 0.7126 | 352 | 0.5372 | | 0.5705 | 0.7206 | 356 | 0.5372 | | 0.5366 | 0.7287 | 360 | 0.5371 | | 0.5268 | 0.7368 | 364 | 0.5370 | | 0.5043 | 0.7449 | 368 | 0.5366 | | 0.5235 | 0.7530 | 372 | 0.5365 | | 0.5688 | 0.7611 | 376 | 0.5364 | | 0.594 | 0.7692 | 380 | 0.5361 | | 0.4947 | 0.7773 | 384 | 0.5360 | | 0.5625 | 0.7854 | 388 | 0.5357 | | 0.5373 | 0.7935 | 392 | 0.5357 | | 0.5124 | 0.8016 | 396 | 0.5355 | | 0.526 | 0.8097 | 400 | 0.5352 | | 0.4984 | 0.8178 | 404 | 0.5351 | | 0.5642 | 0.8259 | 408 | 0.5348 | | 0.5353 | 0.8340 | 412 | 0.5347 | | 0.4514 | 0.8421 | 416 | 0.5347 | | 0.5735 | 0.8502 | 420 | 0.5345 | | 0.5252 | 0.8583 | 424 | 0.5344 | | 0.5355 | 0.8664 | 428 | 0.5343 | | 0.4927 | 0.8745 | 432 | 0.5342 | | 0.5029 | 0.8826 | 436 | 0.5341 | | 0.547 | 0.8907 | 440 | 0.5340 | | 0.5855 | 0.8988 | 444 | 0.5339 | | 0.564 | 0.9069 | 448 | 0.5339 | | 0.5686 | 0.9150 | 452 | 0.5339 | | 0.5222 | 0.9231 | 456 | 0.5338 | | 0.5158 | 0.9312 | 460 | 0.5337 | | 0.523 | 0.9393 | 464 | 0.5337 | | 0.564 | 0.9474 | 468 | 0.5337 | | 0.4984 | 0.9555 | 472 | 0.5337 | | 0.54 | 0.9636 | 476 | 0.5337 | | 0.5355 | 0.9717 | 480 | 0.5337 | | 0.5528 | 0.9798 | 484 | 0.5337 | | 0.5192 | 0.9879 | 488 | 0.5336 | | 0.4789 | 0.9960 | 492 | 0.5337 | | 0.5134 | 1.0040 | 496 | 0.5336 | | 0.5032 | 1.0121 | 500 | 0.5337 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.3