metadata
base_model: lnxdx/21_2500_1e-4_hp-mehrdad
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: 23_3000_1e-4_hp-mehrdad
results: []
23_3000_1e-4_hp-mehrdad
This model is a fine-tuned version of lnxdx/21_2500_1e-4_hp-mehrdad on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9137
- Wer: 0.2932
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7626 | 0.62 | 100 | 0.6772 | 0.3216 |
| 0.7702 | 1.25 | 200 | 0.6705 | 0.3178 |
| 0.7605 | 1.88 | 300 | 0.6425 | 0.3175 |
| 0.6617 | 2.5 | 400 | 0.7113 | 0.3029 |
| 0.661 | 3.12 | 500 | 0.7173 | 0.3020 |
| 0.6037 | 3.75 | 600 | 0.6833 | 0.3478 |
| 0.5343 | 4.38 | 700 | 0.8272 | 0.2959 |
| 0.5096 | 5.0 | 800 | 0.8571 | 0.2973 |
| 0.4471 | 5.62 | 900 | 0.9498 | 0.2909 |
| 0.4393 | 6.25 | 1000 | 0.9137 | 0.2932 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0