metadata
license: llama2
base_model: epfl-llm/meditron-7b
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: 300STEPS_5e7rate_Meditron_7B_SFT
results: []
300STEPS_5e7rate_Meditron_7B_SFT
This model is a fine-tuned version of epfl-llm/meditron-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3127
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-07
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2096 | 0.1 | 50 | 1.1770 |
| 0.7177 | 0.2 | 100 | 0.6260 |
| 0.3357 | 0.29 | 150 | 0.3221 |
| 0.3191 | 0.39 | 200 | 0.3142 |
| 0.3195 | 0.49 | 250 | 0.3128 |
| 0.3195 | 0.59 | 300 | 0.3127 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.0+cu117
- Datasets 2.17.0
- Tokenizers 0.15.1