metadata
base_model: meta-llama/Llama-2-7b-hf
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: hubbub-topics
results: []
hubbub-topics
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5901
- Accuracy: 0.8152
- Precision: 0.8134
- Recall: 0.8152
- F1: 0.8079
Model description
Hubbub Categories/Topics fine-tuned model
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: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 1.209 | 1.0 | 1406 | 1.0149 | 0.6644 | 0.6512 | 0.6644 | 0.6460 |
| 1.0161 | 2.0 | 2812 | 0.8027 | 0.7444 | 0.7414 | 0.7444 | 0.7327 |
| 0.7695 | 3.0 | 4218 | 0.5901 | 0.8152 | 0.8134 | 0.8152 | 0.8079 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3