metadata
license: bigscience-bloom-rail-1.0
tags:
- generated_from_trainer
metrics:
- f1
- recall
- precision
model-index:
- name: sentiment-bloom-e6-b16
results: []
sentiment-bloom-e6-b16
This model is a fine-tuned version of LYTinn/bloom-finetuning-sentiment-model-3000-samples on the None dataset. It achieves the following results on the evaluation set:
- Loss: 6.2903
- F1: 0.6792
- Recall: 0.6792
- Precision: 0.6792
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Recall | Precision |
|---|---|---|---|---|---|---|
| No log | 1.0 | 375 | 1.6115 | 0.3208 | 0.3208 | 0.3208 |
| 1.0514 | 2.0 | 750 | 1.4880 | 0.6685 | 0.6685 | 0.6685 |
| 0.3197 | 3.0 | 1125 | 2.6035 | 0.5876 | 0.5876 | 0.5876 |
| 0.1369 | 4.0 | 1500 | 4.2285 | 0.6550 | 0.6550 | 0.6550 |
| 0.1369 | 5.0 | 1875 | 7.1198 | 0.6927 | 0.6927 | 0.6927 |
| 0.0228 | 6.0 | 2250 | 6.2903 | 0.6792 | 0.6792 | 0.6792 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3