ceb-tl-model-v2

This model is a fine-tuned version of youdiniplays/ceb-tl-model on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5619
• Bleu: 4.3134
• Gen Len: 18.148

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: 0.001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.741	1.0	6516	0.6333	3.8614	18.103
0.6821	2.0	13032	0.6116	4.1546	18.124
0.6257	3.0	19548	0.5879	4.2546	18.136
0.5806	4.0	26064	0.5673	4.3143	18.138
0.5472	5.0	32580	0.5619	4.3134	18.148

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0