metadata
library_name: transformers
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama_3b_step2_batch_v7
results: []
llama_3b_step2_batch_v7
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3371
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 40
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6252 | 0.2725 | 50 | 0.6565 |
| 0.5027 | 0.5450 | 100 | 0.4653 |
| 0.3997 | 0.8174 | 150 | 0.3908 |
| 0.2514 | 1.0899 | 200 | 0.3597 |
| 0.2616 | 1.3624 | 250 | 0.3475 |
| 0.2714 | 1.6349 | 300 | 0.3390 |
| 0.2247 | 1.9074 | 350 | 0.3371 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.1.0+cu118
- Datasets 3.0.2
- Tokenizers 0.20.1