metadata
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Hyponatremia_L3_450steps_1e7rate_SFT
results: []
Hyponatremia_L3_450steps_1e7rate_SFT
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1366
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: 450
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2632 | 0.2667 | 50 | 2.2327 |
| 2.0363 | 0.5333 | 100 | 1.9784 |
| 1.6535 | 0.8 | 150 | 1.6239 |
| 1.3863 | 1.0667 | 200 | 1.3719 |
| 1.2412 | 1.3333 | 250 | 1.2305 |
| 1.175 | 1.6 | 300 | 1.1618 |
| 1.1468 | 1.8667 | 350 | 1.1401 |
| 1.1374 | 2.1333 | 400 | 1.1373 |
| 1.136 | 2.4 | 450 | 1.1366 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.0.0+cu117
- Datasets 2.20.0
- Tokenizers 0.19.1