metadata
tags:
- generated_from_trainer
model-index:
- name: m2m_pt
results: []
m2m_pt
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4682
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: 0.0005
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7388 | 0.09 | 2000 | 0.6464 |
| 0.6096 | 0.18 | 4000 | 0.5477 |
| 0.612 | 0.27 | 6000 | 0.5144 |
| 0.53 | 0.36 | 8000 | 0.4965 |
| 0.5744 | 0.45 | 10000 | 0.4856 |
| 0.5435 | 0.54 | 12000 | 0.4776 |
| 0.5428 | 0.63 | 14000 | 0.4726 |
| 0.5065 | 0.72 | 16000 | 0.4696 |
| 0.5287 | 0.81 | 18000 | 0.4685 |
| 0.5032 | 0.9 | 20000 | 0.4682 |
| 0.5451 | 0.99 | 22000 | 0.4682 |
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.20.0
- Tokenizers 0.15.2