output
This model is a fine-tuned version of bigscience/mt0-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9606
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3121 | 1.0 | 638 | 1.1311 |
| 1.1313 | 2.0 | 1276 | 1.0387 |
| 1.1919 | 3.0 | 1914 | 1.0036 |
| 1.1422 | 4.0 | 2552 | 0.9848 |
| 1.0812 | 5.0 | 3190 | 0.9746 |
| 1.207 | 6.0 | 3828 | 0.9681 |
| 1.1055 | 7.0 | 4466 | 0.9631 |
| 1.2116 | 8.0 | 5104 | 0.9618 |
| 1.1455 | 9.0 | 5742 | 0.9607 |
| 0.9016 | 10.0 | 6380 | 0.9606 |
Framework versions
- PEFT 0.16.0
- Transformers 4.53.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.2
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Dalfaxy/output
Base model
bigscience/mt0-large