metadata
library_name: transformers
license: apache-2.0
base_model: google/t5-small-lm-adapt
tags:
- generated_from_trainer
model-index:
- name: test1
results: []
test1
This model is a fine-tuned version of google/t5-small-lm-adapt on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5772
- Exact Match Acc: 0.0118
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: 0.005
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3.0
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match Acc |
|---|---|---|---|---|
| 1.6493 | 0.4348 | 50 | 1.6531 | 0.0011 |
| 1.6842 | 0.8696 | 100 | 1.6311 | 0.0022 |
| 1.6140 | 1.3043 | 150 | 1.6110 | 0.0054 |
| 1.6240 | 1.7391 | 200 | 1.5943 | 0.0097 |
| 1.5772 | 2.1739 | 250 | 1.5823 | 0.0108 |
| 1.5760 | 2.6087 | 300 | 1.5772 | 0.0118 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.10.0+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2