metadata
library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: IE_L3_1000steps_1e7rate_SFT
results: []
IE_L3_1000steps_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: 1.6772
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: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.2086 | 0.4 | 50 | 2.2064 |
| 2.2198 | 0.8 | 100 | 2.1548 |
| 2.2023 | 1.2 | 150 | 2.0793 |
| 2.0602 | 1.6 | 200 | 2.0114 |
| 2.0378 | 2.0 | 250 | 1.9558 |
| 2.0038 | 2.4 | 300 | 1.8972 |
| 1.9713 | 2.8 | 350 | 1.8398 |
| 1.8103 | 3.2 | 400 | 1.7944 |
| 1.8982 | 3.6 | 450 | 1.7569 |
| 1.7218 | 4.0 | 500 | 1.7267 |
| 1.824 | 4.4 | 550 | 1.7062 |
| 1.7494 | 4.8 | 600 | 1.6925 |
| 1.7574 | 5.2 | 650 | 1.6844 |
| 1.738 | 5.6 | 700 | 1.6798 |
| 1.6533 | 6.0 | 750 | 1.6779 |
| 1.7537 | 6.4 | 800 | 1.6770 |
| 1.7075 | 6.8 | 850 | 1.6770 |
| 1.7128 | 7.2 | 900 | 1.6772 |
| 1.7139 | 7.6 | 950 | 1.6772 |
| 1.7539 | 8.0 | 1000 | 1.6772 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.0.0+cu117
- Datasets 3.0.0
- Tokenizers 0.19.1