metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: flan-t5-base-customer-sentiment
results: []
flan-t5-base-customer-sentiment
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5726
- Accuracy: 86.8217
- Gen Len: 1.0
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 113 | 1.2439 | 87.3385 | 1.0 |
| No log | 2.0 | 226 | 0.5994 | 86.5633 | 1.0 |
| No log | 3.0 | 339 | 0.5726 | 86.8217 | 1.0 |
| No log | 4.0 | 452 | 0.6687 | 87.8553 | 1.0 |
| 0.3089 | 5.0 | 565 | 0.7585 | 87.8553 | 1.0 |
Framework versions
- Transformers 4.28.1
- Pytorch 1.12.0+cu116
- Datasets 2.11.0
- Tokenizers 0.13.3