tl-ceb-model-v2

This model is a fine-tuned version of youdiniplays/tl-ceb-model-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3606
• Bleu: 3.942
• Gen Len: 18.31

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
0.4837	1.0	6516	0.3805	3.8228	18.313
0.4479	2.0	13032	0.3810	3.7662	18.331
0.4036	3.0	19548	0.3755	3.8306	18.343
0.3572	4.0	26064	0.3673	3.8996	18.321
0.3183	5.0	32580	0.3606	3.942	18.31

Framework versions

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