llama_2_7b_MetaMathQA_40K
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5058
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.02
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.8364 | 0.0211 | 13 | 0.6835 |
0.642 | 0.0421 | 26 | 0.6490 |
0.6184 | 0.0632 | 39 | 0.6282 |
0.5964 | 0.0842 | 52 | 0.6165 |
0.5847 | 0.1053 | 65 | 0.6063 |
0.5688 | 0.1264 | 78 | 0.6001 |
0.5782 | 0.1474 | 91 | 0.5918 |
0.5552 | 0.1685 | 104 | 0.5858 |
0.5831 | 0.1896 | 117 | 0.5824 |
0.5693 | 0.2106 | 130 | 0.5779 |
0.5469 | 0.2317 | 143 | 0.5726 |
0.5318 | 0.2527 | 156 | 0.5695 |
0.5368 | 0.2738 | 169 | 0.5664 |
0.5359 | 0.2949 | 182 | 0.5610 |
0.5226 | 0.3159 | 195 | 0.5574 |
0.5341 | 0.3370 | 208 | 0.5532 |
0.5356 | 0.3580 | 221 | 0.5514 |
0.5275 | 0.3791 | 234 | 0.5479 |
0.5145 | 0.4002 | 247 | 0.5444 |
0.5177 | 0.4212 | 260 | 0.5419 |
0.5334 | 0.4423 | 273 | 0.5402 |
0.5155 | 0.4633 | 286 | 0.5369 |
0.5213 | 0.4844 | 299 | 0.5346 |
0.5211 | 0.5055 | 312 | 0.5310 |
0.5048 | 0.5265 | 325 | 0.5300 |
0.5131 | 0.5476 | 338 | 0.5277 |
0.4965 | 0.5687 | 351 | 0.5265 |
0.5053 | 0.5897 | 364 | 0.5227 |
0.4989 | 0.6108 | 377 | 0.5210 |
0.5005 | 0.6318 | 390 | 0.5190 |
0.5037 | 0.6529 | 403 | 0.5181 |
0.507 | 0.6740 | 416 | 0.5167 |
0.5002 | 0.6950 | 429 | 0.5154 |
0.498 | 0.7161 | 442 | 0.5141 |
0.491 | 0.7371 | 455 | 0.5121 |
0.4834 | 0.7582 | 468 | 0.5106 |
0.4971 | 0.7793 | 481 | 0.5094 |
0.4864 | 0.8003 | 494 | 0.5085 |
0.4778 | 0.8214 | 507 | 0.5076 |
0.4991 | 0.8424 | 520 | 0.5073 |
0.4951 | 0.8635 | 533 | 0.5068 |
0.489 | 0.8846 | 546 | 0.5064 |
0.4916 | 0.9056 | 559 | 0.5061 |
0.4841 | 0.9267 | 572 | 0.5058 |
0.4919 | 0.9478 | 585 | 0.5058 |
0.486 | 0.9688 | 598 | 0.5059 |
0.489 | 0.9899 | 611 | 0.5058 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 1
Unable to determine this model’s pipeline type. Check the
docs
.