metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Transaminitis_M2_200rate_1e7_SFT
results: []
Transaminitis_M2_200rate_1e7_SFT
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4066
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: 1e-07
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2942 | 0.2 | 25 | 2.2327 |
| 2.0387 | 0.4 | 50 | 1.9312 |
| 1.6442 | 0.6 | 75 | 1.3586 |
| 0.7444 | 0.8 | 100 | 0.5869 |
| 0.452 | 1.0 | 125 | 0.4245 |
| 0.4076 | 1.2 | 150 | 0.4099 |
| 0.4008 | 1.4 | 175 | 0.4067 |
| 0.4075 | 1.6 | 200 | 0.4066 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1