fine3

This model is a fine-tuned version of clui/fine2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2159
• Bleu: 14.3787
• Gen Len: 46.7062

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.3767	1.0	2133	1.2394	14.0964	46.4002
1.3309	2.0	4266	1.2291	14.1811	46.4653
1.2996	3.0	6399	1.2227	14.3077	46.6912
1.2717	4.0	8532	1.2169	14.3494	46.75
1.2582	5.0	10665	1.2159	14.3787	46.7062

Framework versions

• Transformers 4.48.0
• Pytorch 2.4.0
• Datasets 2.19.1
• Tokenizers 0.21.0