metadata
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: UTI_L3_300steps_1e7rate_SFT
results: []
UTI_L3_300steps_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: 2.6612
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: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7452 | 0.3333 | 25 | 2.7748 |
| 2.7844 | 0.6667 | 50 | 2.7704 |
| 2.7915 | 1.0 | 75 | 2.7596 |
| 2.7945 | 1.3333 | 100 | 2.7379 |
| 2.6614 | 1.6667 | 125 | 2.7138 |
| 2.555 | 2.0 | 150 | 2.6921 |
| 2.6746 | 2.3333 | 175 | 2.6756 |
| 2.7057 | 2.6667 | 200 | 2.6665 |
| 2.7025 | 3.0 | 225 | 2.6620 |
| 2.6592 | 3.3333 | 250 | 2.6607 |
| 2.5701 | 3.6667 | 275 | 2.6610 |
| 2.6338 | 4.0 | 300 | 2.6612 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1