biomistral-7b-wo-kqa_golden-iter-sft-step2
This model is a fine-tuned version of Minbyul/biomistral-7b-wo-kqa_golden-iter-sft-dpo-step1 on the HuggingFaceH4/deita-10k-v0-sft dataset. It achieves the following results on the evaluation set:
- Loss: 1.7672
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4982 | 0.95 | 13 | 1.4957 |
| 0.2254 | 1.96 | 27 | 1.6817 |
| 0.1095 | 2.84 | 39 | 1.7672 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.15.2