amazon-reviews-input-output-13b

This model is a fine-tuned version of facebook/opt-13b on the AlekseyKorshuk/amazon-reviews-input-output dataset. It achieves the following results on the evaluation set:

• Loss: 2.7168
• Accuracy: 0.0404
• Samples: 100
• Perplexity: 15.1318
• Table: <wandb.data_types.Table object at 0x7f8c9a3fb6d0>

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: 5e-05
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
3.2134	0.96	15	2.7168	0.0404

Framework versions

• Transformers 4.25.0.dev0
• Pytorch 1.12.1+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1