myodel

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3333
• Bleu: 0.4497
• Gen Len: 18.3556

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: 5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	23	3.5473	0.128	19.9667
No log	2.0	46	3.4701	0.2473	18.95
No log	3.0	69	3.4291	0.2522	19.6611
No log	4.0	92	3.4070	0.1359	19.6611
No log	5.0	115	3.3855	0.334	19.4889
No log	6.0	138	3.3705	0.2762	19.2722
No log	7.0	161	3.3573	0.3152	19.0944
No log	8.0	184	3.3508	0.1745	19.4778
No log	9.0	207	3.3471	0.3251	19.4944
No log	10.0	230	3.3392	0.4026	19.35
No log	11.0	253	3.3377	0.4314	18.8444
No log	12.0	276	3.3360	0.4322	18.9333
No log	13.0	299	3.3344	0.4387	18.8333
No log	14.0	322	3.3329	0.4653	18.6778
No log	15.0	345	3.3333	0.4497	18.3556

Framework versions

• Transformers 5.0.0
• Pytorch 2.11.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2