48497d406c8f183e20a72ec45eca170c

This model is a fine-tuned version of google-t5/t5-large on the Helsinki-NLP/opus_books [en-fr] dataset. It achieves the following results on the evaluation set:

• Loss: 1.0011
• Data Size: 1.0
• Epoch Runtime: 1462.0737
• Bleu: 15.8135

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Bleu
No log	0	0	1.5070	0	102.8408	10.7331
No log	1	3177	1.4026	0.0078	103.3393	11.7279
0.0238	2	6354	1.3423	0.0156	118.2286	12.1033
1.4615	3	9531	1.3027	0.0312	139.4393	11.7773
1.4075	4	12708	1.2608	0.0625	183.9380	12.1768
1.3268	5	15885	1.2149	0.125	259.7587	12.7879
1.2789	6	19062	1.1564	0.25	435.4287	13.4067
1.1959	7	22239	1.0987	0.5	750.7934	14.1309
1.1114	8.0	25416	1.0446	1.0	1375.9954	14.7082
1.0286	9.0	28593	1.0150	1.0	1357.4729	14.9622
0.9963	10.0	31770	0.9944	1.0	1358.7141	15.2056
0.9257	11.0	34947	0.9879	1.0	1319.4817	15.4423
0.8692	12.0	38124	0.9862	1.0	1382.0694	15.5747
0.8193	13.0	41301	0.9807	1.0	1413.7907	15.8882
0.7837	14.0	44478	0.9851	1.0	1438.6347	15.7333
0.7581	15.0	47655	0.9893	1.0	1461.2569	15.9266
0.6975	16.0	50832	0.9931	1.0	1454.9646	15.8778
0.6911	17.0	54009	1.0011	1.0	1462.0737	15.8135

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1