3-allnli-p-a-p-a-p-a-64-128-3e-5-2600

This model is a fine-tuned version of 3-parallel-9-p-a-p-a-p-64-128-3e-5-26000/checkpoint-26000 on the ALLNLI dataset.

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: 3e-05
• train_batch_size: 128
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• training_steps: 2600

Training results

Framework versions

• Transformers 4.17.0
• Pytorch 1.11.0
• Datasets 2.14.7.dev0
• Tokenizers 0.14.1