metadata
license: apache-2.0
base_model: google/flan-t5-small
tags:
- generated_from_trainer
model-index:
- name: T5_mrqa_b32_9ep
results: []
T5_mrqa_b32_9ep
This model is a fine-tuned version of google/flan-t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7267
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 300 | 0.7897 |
| 0.9438 | 2.0 | 600 | 0.7702 |
| 0.9438 | 3.0 | 900 | 0.7400 |
| 0.9153 | 4.0 | 1200 | 0.7380 |
| 0.8721 | 5.0 | 1500 | 0.7316 |
| 0.8721 | 6.0 | 1800 | 0.7277 |
| 0.8536 | 7.0 | 2100 | 0.7277 |
| 0.8536 | 8.0 | 2400 | 0.7275 |
| 0.8291 | 9.0 | 2700 | 0.7267 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1