metadata
license: mit
base_model: microsoft/git-base
tags:
- generated_from_trainer
model-index:
- name: poem
results: []
poem
This model is a fine-tuned version of microsoft/git-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5017
- Wer Score: 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 11.2976 | 2.5 | 25 | 9.5740 | 420.8 |
| 9.1277 | 5.0 | 50 | 6.6363 | 687.975 |
| 6.8333 | 7.5 | 75 | 4.2680 | 1.0 |
| 3.8819 | 10.0 | 100 | 3.5017 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.0
- Datasets 2.15.0
- Tokenizers 0.15.0