metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: semeval2026_Llama-3.2-3B-Instruct_5ep_v1
results: []
semeval2026_Llama-3.2-3B-Instruct_5ep_v1
This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1535
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0993 | 1.0 | 388 | 0.0891 |
| 0.0649 | 2.0 | 776 | 0.0843 |
| 0.0528 | 3.0 | 1164 | 0.0994 |
| 0.0146 | 4.0 | 1552 | 0.1150 |
| 0.0035 | 5.0 | 1940 | 0.1535 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3