metadata
base_model: facebook/opt-350m
library_name: peft
license: other
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: sample_data
results: []
sample_data
This model is a fine-tuned version of facebook/opt-350m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 4.6426
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.9032 | 0.4444 | 1 | 5.1705 |
| 4.8617 | 0.8889 | 2 | 4.8856 |
| 4.6261 | 1.3333 | 3 | 4.7009 |
| 4.4803 | 1.7778 | 4 | 4.6426 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.0
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.20.0