You can deploy this model and start earning money today!

contemmcm/
e4847f991792ade211af852fa56d56a9

generated_from_trainer

google/long-t5-local-large

finetune

apache-2.0

endpoints_compatible

Views

No views yet

e4847f991792ade211af852fa56d56a9

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

Loss: 1.4160
Data Size: 1.0
Epoch Runtime: 989.3161
Bleu: 10.6080

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	246.8430	0	70.2147	0.0121
No log	1	2336	117.7648	0.0078	79.0063	0.0060
2.1817	2	4672	25.6817	0.0156	88.5264	0.0047
1.001	3	7008	13.6103	0.0312	103.8313	0.0300
17.2046	4	9344	10.5885	0.0625	136.3088	0.1041
12.6662	5	11680	8.2395	0.125	195.8561	0.0220
8.6169	6	14016	6.0275	0.25	321.4557	0.0452
5.7542	7	16352	4.0988	0.5	561.4889	0.1270
4.0237	8.0	18688	3.1397	1.0	1055.3004	0.2512
3.4186	9.0	21024	2.8511	1.0	1049.6856	0.3956
3.1121	10.0	23360	2.6719	1.0	1060.8305	0.5120
2.9602	11.0	25696	2.5553	1.0	1006.4375	0.8038
2.8125	12.0	28032	2.4600	1.0	997.7744	0.9112
2.6707	13.0	30368	2.3870	1.0	1005.8584	1.2012
2.5901	14.0	32704	2.3140	1.0	1015.1406	1.4366
2.4856	15.0	35040	2.2496	1.0	1005.3348	1.7582
2.4326	16.0	37376	2.1611	1.0	1001.0406	2.2608
2.3176	17.0	39712	2.0675	1.0	997.2437	3.3927
2.2014	18.0	42048	1.9610	1.0	1006.1480	4.2419
2.1097	19.0	44384	1.8678	1.0	987.4824	5.5525
1.9952	20.0	46720	1.7919	1.0	992.8617	6.5480
1.9192	21.0	49056	1.7281	1.0	991.5432	7.1512
1.8502	22.0	51392	1.6848	1.0	993.8319	7.8702
1.7994	23.0	53728	1.6455	1.0	995.0187	8.3164
1.6939	24.0	56064	1.6007	1.0	993.9329	8.7631
1.661	25.0	58400	1.5670	1.0	994.8879	9.0783
1.6075	26.0	60736	1.5397	1.0	995.2204	9.7950
1.5721	27.0	63072	1.5166	1.0	997.4119	9.5339
1.5069	28.0	65408	1.4963	1.0	989.6687	9.9624
1.4669	29.0	67744	1.4795	1.0	997.3584	10.7574
1.4432	30.0	70080	1.4665	1.0	989.7209	9.8995
1.4014	31.0	72416	1.4471	1.0	986.6704	10.1398
1.3847	32.0	74752	1.4422	1.0	987.1844	10.1534
1.3324	33.0	77088	1.4250	1.0	994.7598	10.4637
1.3104	34.0	79424	1.4202	1.0	994.9600	10.2487
1.2824	35.0	81760	1.4135	1.0	997.3620	10.2880
1.266	36.0	84096	1.4101	1.0	997.1869	10.4098
1.216	37.0	86432	1.4044	1.0	996.9699	10.2484
1.2069	38.0	88768	1.4147	1.0	992.1381	10.3908
1.1914	39.0	91104	1.4027	1.0	993.1078	10.6603
1.1562	40.0	93440	1.4058	1.0	985.1606	10.4011
1.1252	41.0	95776	1.4023	1.0	989.5193	10.6423
1.0827	42.0	98112	1.4123	1.0	994.8483	10.6877
1.0668	43.0	100448	1.4123	1.0	992.7704	10.4747
1.016	44.0	102784	1.4208	1.0	988.4605	10.4355
1.0309	45.0	105120	1.4160	1.0	989.3161	10.6080

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/e4847f991792ade211af852fa56d56a9

e4847f991792ade211af852fa56d56a9

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
e4847f991792ade211af852fa56d56a9