metadata
tags:
- generated_from_trainer
model-index:
- name: llama-2-7b-hf-ft-compact
results: []
llama-2-7b-hf-ft-compact
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8405
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9697 | 0.36 | 25 | 3.0220 |
| 1.1283 | 0.73 | 50 | 0.9941 |
| 0.9218 | 1.09 | 75 | 0.8991 |
| 0.8849 | 1.45 | 100 | 0.8700 |
| 0.8644 | 1.82 | 125 | 0.8561 |
| 0.8388 | 2.18 | 150 | 0.8465 |
| 0.8208 | 2.55 | 175 | 0.8417 |
| 0.8038 | 2.91 | 200 | 0.8405 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0