semeval2026_Llama-3.2-1B-Instruct_5ep_v0
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8758
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: 4
- eval_batch_size: 2
- seed: 3407
- gradient_accumulation_steps: 2
- 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 |
|---|---|---|---|
| 0.3289 | 1.0 | 388 | 0.3477 |
| 0.2508 | 2.0 | 776 | 0.3282 |
| 0.1681 | 3.0 | 1164 | 0.4020 |
| 0.057 | 4.0 | 1552 | 0.7046 |
| 0.0364 | 5.0 | 1940 | 0.8758 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 2.20.0
- Tokenizers 0.20.3
- Downloads last month
- 47
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for juliadollis/semeval2026_Llama-3.2-1B-Instruct_5ep_v0
Base model
meta-llama/Llama-3.2-1B-Instruct