metadata
license: bigscience-bloom-rail-1.0
library_name: peft
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
base_model: bigscience/bloom-560m
model-index:
- name: 4bit-emotion-detection
results: []
4bit-emotion-detection
This model is a fine-tuned version of bigscience/bloom-560m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9589
- Accuracy: 0.372
- F1: 0.3552
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: 1e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 750
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 2.887 | 1.0 | 250 | 2.9863 | 0.2865 | 0.2788 |
| 2.4198 | 2.0 | 500 | 2.1868 | 0.345 | 0.3360 |
| 1.7684 | 3.0 | 750 | 1.9589 | 0.372 | 0.3552 |
Framework versions
- PEFT 0.8.2.dev0
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.1