metadata
library_name: peft
tags:
- generated_from_trainer
base_model: NousResearch/Llama-2-7b-hf
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: llama-2-ner
results: []
llama-2-ner
This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1413
- Precision: 0.5320
- Recall: 0.5684
- F1: 0.5496
- Accuracy: 0.9784
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: 0.0009
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 39 | 0.1312 | 0.1429 | 0.0053 | 0.0102 | 0.9677 |
| No log | 2.0 | 78 | 0.1077 | 0.3717 | 0.2211 | 0.2772 | 0.9700 |
| No log | 3.0 | 117 | 0.0770 | 0.4156 | 0.3368 | 0.3721 | 0.9752 |
| No log | 4.0 | 156 | 0.0683 | 0.4304 | 0.5368 | 0.4778 | 0.9755 |
| No log | 5.0 | 195 | 0.1069 | 0.4923 | 0.5053 | 0.4987 | 0.9768 |
| No log | 6.0 | 234 | 0.1214 | 0.5506 | 0.5158 | 0.5326 | 0.9776 |
| No log | 7.0 | 273 | 0.1393 | 0.5276 | 0.5526 | 0.5398 | 0.9783 |
| No log | 8.0 | 312 | 0.1413 | 0.5320 | 0.5684 | 0.5496 | 0.9784 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1