You can deploy this model and start earning money today!

contemmcm/
59299fac8be745500bb0e1370c63d482

transformers

safetensors

text2text-generation

generated_from_trainer

google-t5/t5-large

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

59299fac8be745500bb0e1370c63d482

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

Loss: 2.1249
Data Size: 1.0
Epoch Runtime: 36.5154
Bleu: 2.5440

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	3.5780	0	3.2564	0.2084
No log	1	75	3.4465	0.0078	3.6419	0.2123
No log	2	150	3.3627	0.0156	4.8223	0.2416
No log	3	225	3.1703	0.0312	6.1301	0.2420
No log	4	300	2.9731	0.0625	7.5254	0.6056
No log	5	375	2.8527	0.125	11.1656	0.8052
No log	6	450	2.7320	0.25	15.1600	0.8919
No log	7	525	2.6007	0.5	21.2658	0.8264
2.6448	8.0	600	2.4550	1.0	44.9395	1.2162
2.5118	9.0	675	2.3749	1.0	39.2771	1.3544
2.3843	10.0	750	2.3101	1.0	38.0081	1.4960
2.2925	11.0	825	2.2629	1.0	37.0218	1.6055
2.1876	12.0	900	2.2230	1.0	36.7004	1.7546
2.1028	13.0	975	2.1942	1.0	35.3264	1.8785
2.0358	14.0	1050	2.1734	1.0	36.8626	1.9230
1.9538	15.0	1125	2.1494	1.0	36.4137	2.0193
1.8905	16.0	1200	2.1377	1.0	36.0013	2.1055
1.8319	17.0	1275	2.1293	1.0	35.8351	2.2524
1.7805	18.0	1350	2.1345	1.0	36.6366	2.3354
1.7177	19.0	1425	2.1111	1.0	39.7540	2.1955
1.6827	20.0	1500	2.1027	1.0	35.8797	2.2600
1.6115	21.0	1575	2.1018	1.0	36.6603	2.3568
1.588	22.0	1650	2.1000	1.0	38.1182	2.3186
1.5261	23.0	1725	2.1135	1.0	35.4529	2.3866
1.4847	24.0	1800	2.1122	1.0	35.8072	2.4640
1.4493	25.0	1875	2.1025	1.0	37.3637	2.5634
1.4104	26.0	1950	2.1249	1.0	36.5154	2.5440

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/59299fac8be745500bb0e1370c63d482

59299fac8be745500bb0e1370c63d482

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
59299fac8be745500bb0e1370c63d482