metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: prompt_tuning_sst2_text_origin_0_meta-llama-3.2-1b
results: []
prompt_tuning_11122024064002_sst2_text_origin_0_meta-llama-3.2-1b
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1542
- Exact Match: 1.0
- F1: 1.0
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: 0.3
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
|---|---|---|---|---|---|
| 0.2942 | 1.0 | 4147 | 0.2772 | 0.999 | 0.9991 |
| 0.2297 | 2.0 | 8294 | 0.2496 | 0.995 | 0.9955 |
| 0.2011 | 3.0 | 12441 | 0.1866 | 1.0 | 1.0 |
| 0.1699 | 4.0 | 16588 | 0.1678 | 1.0 | 1.0 |
| 0.1585 | 5.0 | 20735 | 0.1542 | 1.0 | 1.0 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.0.dev0
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3