ff-en

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8258

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
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
8.2472	1.0	20	3.2102
2.8238	2.0	40	1.2139
1.7661	3.0	60	1.1075
1.4094	4.0	80	1.0537
1.2869	5.0	100	1.0106
1.2366	6.0	120	0.9804
1.1731	7.0	140	0.9549
1.1356	8.0	160	0.9422
1.1196	9.0	180	0.9286
1.031	10.0	200	0.9169
1.0438	11.0	220	0.9014
1.0231	12.0	240	0.9007
1.0015	13.0	260	0.8829
0.9908	14.0	280	0.8803
0.995	15.0	300	0.8689
0.951	16.0	320	0.8638
0.948	17.0	340	0.8601
0.9157	18.0	360	0.8551
0.9074	19.0	380	0.8519
0.9021	20.0	400	0.8506
0.8898	21.0	420	0.8472
0.8842	22.0	440	0.8448
0.9024	23.0	460	0.8437
0.858	24.0	480	0.8403
0.8801	25.0	500	0.8381
0.8441	26.0	520	0.8375
0.8379	27.0	540	0.8358
0.8403	28.0	560	0.8344
0.8615	29.0	580	0.8333
0.8697	30.0	600	0.8327
0.8403	31.0	620	0.8314
0.8373	32.0	640	0.8299
0.8094	33.0	660	0.8292
0.8023	34.0	680	0.8291
0.8426	35.0	700	0.8289
0.8275	36.0	720	0.8281
0.8177	37.0	740	0.8278
0.8183	38.0	760	0.8266
0.8058	39.0	780	0.8262
0.7929	40.0	800	0.8263
0.8218	41.0	820	0.8261
0.8198	42.0	840	0.8261
0.7957	43.0	860	0.8259
0.7966	44.0	880	0.8260
0.7941	45.0	900	0.8260
0.7771	46.0	920	0.8261
0.7883	47.0	940	0.8260
0.8113	48.0	960	0.8259
0.8155	49.0	980	0.8258
0.7782	50.0	1000	0.8258

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1