batch_size_8_50_epochs_V3

This model is a fine-tuned version of JordanWHLewis/batch_size_8_50_epochs_V2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9178

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
17.9139	6.67	200	2.8998
0.5858	13.33	400	2.5126
0.2578	20.0	600	2.9842
0.155	26.67	800	3.1740
0.1156	33.33	1000	2.9952
0.0971	40.0	1200	2.8684
0.075	46.67	1400	2.9178

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1
• Datasets 2.12.0
• Tokenizers 0.13.2