opt-ahmed

This model is a fine-tuned version of facebook/opt-125m on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.6232

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: 0.0002
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.5683	10.0	50	3.6232

Framework versions

• PEFT 0.9.1.dev0
• Transformers 4.39.0.dev0
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2