You can deploy this model and start earning money today!

contemmcm/
5fd64cb122fd971fad5270f97d6f18e8

Name: 5fd64cb122fd971fad5270f97d6f18e8
Rating: 2.5 (5 reviews)

generated_from_trainer

Views

No views yet

5fd64cb122fd971fad5270f97d6f18e8

This model is a fine-tuned version of google/mt5-large on the Helsinki-NLP/opus_books [en-no] dataset. It achieves the following results on the evaluation set:

Loss: 1.8305
Data Size: 1.0
Epoch Runtime: 41.2813
Bleu: 9.7535

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	20.7594	0	3.5468	0.0115
No log	1	87	22.1591	0.0078	3.8572	0.0106
No log	2	174	26.3035	0.0156	6.9651	0.0078
No log	3	261	27.4225	0.0312	9.9823	0.0049
No log	4	348	25.8909	0.0625	13.2737	0.0047
1.0485	5	435	17.5642	0.125	14.9592	0.0026
5.5294	6	522	14.1240	0.25	17.8137	0.0025
6.2793	7	609	8.8713	0.5	26.3739	0.0079
7.6166	8.0	696	7.5873	1.0	43.4025	0.0437
9.052	9.0	783	5.7937	1.0	41.6865	0.0370
3.8981	10.0	870	2.1593	1.0	40.9467	6.2807
2.5113	11.0	957	1.9532	1.0	42.0217	7.3394
2.2808	12.0	1044	1.8856	1.0	41.7985	8.2089
2.0589	13.0	1131	1.8453	1.0	41.7597	8.4916
1.9028	14.0	1218	1.8229	1.0	41.5749	8.9249
1.7645	15.0	1305	1.8045	1.0	41.5527	9.1139
1.6761	16.0	1392	1.7931	1.0	40.3087	9.4682
1.6149	17.0	1479	1.7973	1.0	40.9974	9.6486
1.5258	18.0	1566	1.8213	1.0	40.3061	9.6694
1.472	19.0	1653	1.8052	1.0	40.2931	9.6543
1.3782	20.0	1740	1.8305	1.0	41.2813	9.7535

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/5fd64cb122fd971fad5270f97d6f18e8

5fd64cb122fd971fad5270f97d6f18e8

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
5fd64cb122fd971fad5270f97d6f18e8