You can deploy this model and start earning money today!

contemmcm/
f3e121a25346713ccd2c4fff4d815f46

Name: f3e121a25346713ccd2c4fff4d815f46
Rating: 2.5 (6 reviews)

transformers

safetensors

text2text-generation

generated_from_trainer

google-t5/t5-3b

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

f3e121a25346713ccd2c4fff4d815f46

This model is a fine-tuned version of google-t5/t5-3b on the Helsinki-NLP/opus_books [fi-pl] dataset. It achieves the following results on the evaluation set:

Loss: 1.9362
Data Size: 1.0
Epoch Runtime: 51.8285
Bleu: 0.8314

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	3.2804	0	3.4377	0.1342
No log	1	70	3.0823	0.0078	3.4839	0.1395
No log	2	140	2.8435	0.0156	7.4672	0.1909
No log	3	210	2.6754	0.0312	12.3128	0.2007
No log	4	280	2.3872	0.0625	16.4535	0.2422
No log	5	350	2.2346	0.125	24.2306	0.4289
No log	6	420	2.1195	0.25	28.3492	0.3486
0.3624	7	490	2.0221	0.5	34.1667	0.5347
2.074	8.0	560	1.9428	1.0	53.8043	0.7631
1.9362	9.0	630	1.8958	1.0	52.4890	0.8292
1.7995	10.0	700	1.8802	1.0	44.3414	0.8688
1.6905	11.0	770	1.8770	1.0	46.4804	0.8356
1.6449	12.0	840	1.8817	1.0	43.7407	0.8392
1.5173	13.0	910	1.8903	1.0	45.6560	0.8937
1.4571	14.0	980	1.9116	1.0	49.7741	0.9163
1.3842	15.0	1050	1.9362	1.0	51.8285	0.8314

Framework versions

Transformers 4.57.0
Pytorch 2.8.0+cu128
Datasets 4.2.0
Tokenizers 0.22.1

contemmcm/f3e121a25346713ccd2c4fff4d815f46

f3e121a25346713ccd2c4fff4d815f46

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

contemmcm/
f3e121a25346713ccd2c4fff4d815f46