metadata
tags:
- generated_from_trainer
model-index:
- name: mistral-7b-peptide-v2
results: []
mistral-7b-peptide-v2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3878
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: 5e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- total_eval_batch_size: 12
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 1100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8125 | 0.0909 | 100 | 1.8548 |
| 0.3637 | 0.1818 | 200 | 2.3370 |
| 0.2775 | 0.2727 | 300 | 2.4800 |
| 0.2097 | 0.3636 | 400 | 2.8027 |
| 0.1534 | 0.4545 | 500 | 2.8239 |
| 0.0907 | 0.5455 | 600 | 3.3357 |
| 0.0706 | 0.6364 | 700 | 3.1721 |
| 0.0569 | 0.7273 | 800 | 3.4330 |
| 0.0473 | 0.8182 | 900 | 3.3746 |
| 0.0455 | 0.9091 | 1000 | 3.4352 |
| 0.0424 | 1.0 | 1100 | 3.3878 |
Framework versions
- Transformers 4.44.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1