metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-large
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: mt5_large_lr3e-05_bs4_ep3
results: []
mt5_large_lr3e-05_bs4_ep3
This model is a fine-tuned version of google/mt5-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4810
- Precision: 0.6887
- Recall: 0.2946
- F1: 0.4127
- Accuracy: 0.8063
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.926 | 1.0 | 860 | 0.5150 | 0.7078 | 0.1380 | 0.2310 | 0.7877 |
| 0.5082 | 2.0 | 1720 | 0.4233 | 0.6442 | 0.4180 | 0.5070 | 0.8122 |
| 0.4551 | 3.0 | 2580 | 0.4810 | 0.6887 | 0.2946 | 0.4127 | 0.8063 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0
- Datasets 3.4.1
- Tokenizers 0.21.1