metadata
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: llama-7b-sst-5
results: []
llama-7b-sst-5
This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3537
- Accuracy: 0.4387
- Precision: 0.4393
- Recall: 0.4264
- F1: 0.4300
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch 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: 100
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.4944 | 100 | 1.7838 | 0.3397 | 0.3352 | 0.3371 | 0.3321 |
| No log | 2.9888 | 200 | 1.5155 | 0.3960 | 0.3916 | 0.3767 | 0.3782 |
| No log | 4.4794 | 300 | 1.4366 | 0.4169 | 0.4313 | 0.4031 | 0.4106 |
| No log | 5.9738 | 400 | 1.3832 | 0.4287 | 0.4224 | 0.4207 | 0.4198 |
| 5.8948 | 7.4644 | 500 | 1.3675 | 0.4369 | 0.4489 | 0.4266 | 0.4345 |
| 5.8948 | 8.9588 | 600 | 1.3537 | 0.4387 | 0.4393 | 0.4264 | 0.4300 |
Framework versions
- PEFT 0.14.0
- Transformers 4.47.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0