| library_name: transformers | |
| language: | |
| - en | |
| - fr | |
| tags: | |
| - translation | |
| - seq2seq | |
| metrics: | |
| - bleu | |
| model-index: | |
| - name: lab2_efficient | |
| results: | |
| - task: | |
| type: translation | |
| dataset: | |
| name: kde4 | |
| type: kde4 | |
| metrics: | |
| - type: bleu | |
| value: 44.113 | |
| name: BLEU | |
| - type: loss | |
| value: 1.3546 | |
| name: Loss | |
| # lab2_efficient | |
| ## Hyperparameters | |
| - learning_rate: 2e-5 | |
| - per_device_train_batch_size: 128 | |
| - effective_batch_size: 128 | |
| - gradient_accumulation_steps: 1 | |
| - weight_decay: 0.1 | |
| - optimizer: adamw_torch | |
| - fp16: True | |
| - gradient_checkpointing: True | |
| - lr_scheduler: cosine | |
| - warmup_ratio: 0.1 | |
| - max_steps: 100 | |
| ## Results | |
| | Metric | Value | | |
| |--------|-------| | |
| | BLEU | 44.113 | | |
| | Eval Loss | 1.3546 | | |
| | Train Steps | 100 | | |
| | Epoch | 0.0615 | | |