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: 0.1194
- Precision: 0.2718
- Recall: 0.2789
- F1: 0.2753
- Accuracy: 0.9676
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: 0.0001
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 39 | 0.1625 | 0.0 | 0.0 | 0.0 | 0.9671 |
| No log | 2.0 | 78 | 0.1430 | 0.0 | 0.0 | 0.0 | 0.9673 |
| No log | 3.0 | 117 | 0.1297 | 0.3235 | 0.0579 | 0.0982 | 0.9674 |
| No log | 4.0 | 156 | 0.1158 | 0.3015 | 0.2158 | 0.2515 | 0.9676 |
| No log | 5.0 | 195 | 0.1197 | 0.45 | 0.0947 | 0.1565 | 0.9690 |
| No log | 6.0 | 234 | 0.1105 | 0.2526 | 0.2579 | 0.2552 | 0.9664 |
| No log | 7.0 | 273 | 0.1071 | 0.2632 | 0.2632 | 0.2632 | 0.9674 |
| No log | 8.0 | 312 | 0.1170 | 0.3030 | 0.2632 | 0.2817 | 0.9687 |
| No log | 9.0 | 351 | 0.1165 | 0.2512 | 0.2737 | 0.2620 | 0.9665 |
| No log | 10.0 | 390 | 0.1194 | 0.2718 | 0.2789 | 0.2753 | 0.9676 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.2+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1