You can deploy this model and start earning money today!

contemmcm/
46dffc31173e5994fa242c01a9e45052

transformers

safetensors

text2text-generation

generated_from_trainer

google-t5/t5-small

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

46dffc31173e5994fa242c01a9e45052

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

Loss: 1.7368
Data Size: 1.0
Epoch Runtime: 28.4388
Bleu: 5.0438

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	3.0611	0	2.9703	0.0301
No log	1	204	3.0078	0.0078	3.2411	0.0308
No log	2	408	2.8698	0.0156	3.4128	0.0369
No log	3	612	2.7684	0.0312	4.0831	0.0556
No log	4	816	2.6426	0.0625	4.8108	0.0600
No log	5	1020	2.5587	0.125	6.1610	0.0974
0.2203	6	1224	2.4814	0.25	8.9637	0.1015
2.596	7	1428	2.4157	0.5	15.0651	0.1407
2.5152	8.0	1632	2.3308	1.0	27.9192	0.4834
2.4478	9.0	1836	2.2708	1.0	26.2995	0.5179
2.3984	10.0	2040	2.2261	1.0	28.4935	0.7986
2.3551	11.0	2244	2.1877	1.0	26.8308	0.8706
2.3113	12.0	2448	2.1580	1.0	26.3943	1.1699
2.2844	13.0	2652	2.1308	1.0	27.8054	1.3517
2.2547	14.0	2856	2.1061	1.0	29.1870	1.6041
2.2359	15.0	3060	2.0846	1.0	26.6773	1.7011
2.2051	16.0	3264	2.0633	1.0	26.8046	1.6638
2.1918	17.0	3468	2.0440	1.0	26.5214	1.7798
2.1918	18.0	3672	2.0276	1.0	28.3037	1.9480
2.151	19.0	3876	2.0119	1.0	26.3240	2.1426
2.1282	20.0	4080	1.9951	1.0	26.7860	2.3551
2.1099	21.0	4284	1.9810	1.0	26.3245	2.4976
2.093	22.0	4488	1.9680	1.0	28.4963	2.6265
2.0978	23.0	4692	1.9584	1.0	26.6619	2.7727
2.0676	24.0	4896	1.9423	1.0	27.5896	2.7580
2.0633	25.0	5100	1.9297	1.0	29.7501	2.8652
2.0421	26.0	5304	1.9176	1.0	27.9848	3.0715
2.0165	27.0	5508	1.9068	1.0	26.9319	3.0933
2.0127	28.0	5712	1.8978	1.0	26.6742	3.1966
1.9978	29.0	5916	1.8880	1.0	26.8195	3.4785
1.9888	30.0	6120	1.8774	1.0	26.4744	3.7091
1.9848	31.0	6324	1.8677	1.0	26.7999	3.5623
1.9605	32.0	6528	1.8598	1.0	27.4531	3.7042
1.9561	33.0	6732	1.8507	1.0	26.6322	3.8010
1.9324	34.0	6936	1.8402	1.0	26.8765	3.7413
1.9211	35.0	7140	1.8343	1.0	25.6445	3.7603
1.917	36.0	7344	1.8258	1.0	26.9218	3.9299
1.895	37.0	7548	1.8186	1.0	25.2260	4.0010
1.915	38.0	7752	1.8080	1.0	26.0806	4.0400
1.8929	39.0	7956	1.8051	1.0	26.0911	4.2939
1.8876	40.0	8160	1.7957	1.0	25.9688	4.2530
1.8845	41.0	8364	1.7911	1.0	26.9524	4.4114
1.8741	42.0	8568	1.7842	1.0	26.6725	4.4745
1.8469	43.0	8772	1.7759	1.0	25.8436	4.5768
1.8441	44.0	8976	1.7725	1.0	26.2066	4.6314
1.8338	45.0	9180	1.7661	1.0	26.3576	4.6823
1.8404	46.0	9384	1.7582	1.0	25.9867	4.8253
1.8262	47.0	9588	1.7538	1.0	25.8472	4.8482
1.8214	48.0	9792	1.7486	1.0	27.5726	4.8628
1.8106	49.0	9996	1.7429	1.0	26.2687	4.9152
1.7939	50.0	10200	1.7368	1.0	28.4388	5.0438

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/46dffc31173e5994fa242c01a9e45052

46dffc31173e5994fa242c01a9e45052

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
46dffc31173e5994fa242c01a9e45052