lab2_efficient / README.md
rdj-034's picture
Upload README.md with huggingface_hub
0a0d586 verified
metadata
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