metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: Llama-3.2-1B-Instruct-classifier
results: []
Llama-3.2-1B-Instruct-classifier
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: 0.2160
- Accuracy: 0.9308
- F1: 0.8621
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0 | 0 | 1.0194 | 0.4524 | 0.3310 |
| No log | 0.2020 | 79 | 0.3185 | 0.8804 | 0.7508 |
| No log | 0.4041 | 158 | 0.2728 | 0.8948 | 0.7989 |
| No log | 0.6061 | 237 | 0.2436 | 0.9006 | 0.8110 |
| No log | 0.8082 | 316 | 0.2251 | 0.8963 | 0.7895 |
| No log | 1.0102 | 395 | 0.2713 | 0.8905 | 0.81 |
| No log | 1.2123 | 474 | 0.3203 | 0.9020 | 0.8162 |
| 0.3016 | 1.4143 | 553 | 0.2289 | 0.9164 | 0.8324 |
| 0.3016 | 1.6164 | 632 | 0.2306 | 0.9280 | 0.8641 |
| 0.3016 | 1.8184 | 711 | 0.2160 | 0.9308 | 0.8621 |
Framework versions
- Transformers 4.53.3
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.2