You can deploy this model and start earning money today!

contemmcm/
85ae953a757afeedfea6b1965caad37d

transformers

safetensors

text2text-generation

generated_from_trainer

google-t5/t5-base

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

85ae953a757afeedfea6b1965caad37d

This model is a fine-tuned version of google-t5/t5-base on the Helsinki-NLP/opus_books [fi-no] dataset. It achieves the following results on the evaluation set:

Loss: 2.2773
Data Size: 1.0
Epoch Runtime: 28.2142
Bleu: 1.0716

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	4.2728	0	3.9311	0.1613
No log	1	85	4.1646	0.0078	3.4406	0.1621
No log	2	170	3.8846	0.0156	3.7661	0.1223
No log	3	255	3.7565	0.0312	3.6119	0.1136
No log	4	340	3.5739	0.0625	5.1716	0.1262
0.2435	5	425	3.3799	0.125	6.9609	0.2811
0.2435	6	510	3.2151	0.25	11.4406	0.2764
1.0705	7	595	3.0480	0.5	16.5465	0.3229
3.1699	8.0	680	2.8789	1.0	30.8015	0.4691
2.9859	9.0	765	2.7744	1.0	26.9812	0.6084
2.8812	10.0	850	2.6981	1.0	25.0984	0.7507
2.8271	11.0	935	2.6411	1.0	30.0702	0.7673
2.7429	12.0	1020	2.5965	1.0	30.6460	0.8492
2.6719	13.0	1105	2.5551	1.0	29.0121	0.8753
2.6307	14.0	1190	2.5250	1.0	25.6483	0.8464
2.5956	15.0	1275	2.4933	1.0	25.7452	0.9030
2.5345	16.0	1360	2.4678	1.0	29.9591	0.9116
2.4959	17.0	1445	2.4435	1.0	30.4582	0.9149
2.4733	18.0	1530	2.4280	1.0	28.6478	0.9690
2.4284	19.0	1615	2.4108	1.0	27.3458	0.9625
2.3791	20.0	1700	2.3882	1.0	27.6031	0.9434
2.3546	21.0	1785	2.3769	1.0	25.7595	0.9964
2.3337	22.0	1870	2.3661	1.0	25.3353	1.0021
2.285	23.0	1955	2.3518	1.0	28.1686	1.0710
2.2752	24.0	2040	2.3420	1.0	28.8875	1.0655
2.2436	25.0	2125	2.3336	1.0	28.5906	1.0102
2.2297	26.0	2210	2.3232	1.0	28.2973	1.0416
2.1907	27.0	2295	2.3118	1.0	26.2241	1.0234
2.1941	28.0	2380	2.3124	1.0	25.7713	1.0197
2.1428	29.0	2465	2.3070	1.0	23.9412	1.0905
2.1107	30.0	2550	2.2989	1.0	23.8112	1.0995
2.1018	31.0	2635	2.2963	1.0	27.4252	1.0863
2.0871	32.0	2720	2.2952	1.0	29.6458	1.1361
2.0478	33.0	2805	2.2823	1.0	27.3086	1.0435
2.041	34.0	2890	2.2830	1.0	25.8805	1.0999
2.0072	35.0	2975	2.2981	1.0	24.7047	1.1148
1.9919	36.0	3060	2.2736	1.0	25.0025	1.1112
1.9891	37.0	3145	2.2763	1.0	28.3820	1.1097
1.9583	38.0	3230	2.2791	1.0	24.7341	1.0930
1.9393	39.0	3315	2.2730	1.0	23.6233	1.1063
1.9302	40.0	3400	2.2759	1.0	22.8854	1.1317
1.91	41.0	3485	2.2740	1.0	22.9390	1.1311
1.8784	42.0	3570	2.2755	1.0	22.6556	1.1323
1.8681	43.0	3655	2.2773	1.0	28.2142	1.0716

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/85ae953a757afeedfea6b1965caad37d

85ae953a757afeedfea6b1965caad37d

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
85ae953a757afeedfea6b1965caad37d