alpaca-test

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

• Loss: 0.4690

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	13	10.1816
No log	2.0	26	6.3483
No log	3.0	39	3.6923
No log	4.0	52	1.9466
No log	5.0	65	1.0837
No log	6.0	78	0.8578
No log	7.0	91	0.8170
No log	8.0	104	0.7665
No log	9.0	117	0.7464
No log	10.0	130	0.7227
No log	11.0	143	0.7066
No log	12.0	156	0.6916
No log	13.0	169	0.6775
No log	14.0	182	0.6691
No log	15.0	195	0.6563
No log	16.0	208	0.6450
No log	17.0	221	0.6352
No log	18.0	234	0.6260
No log	19.0	247	0.6178
No log	20.0	260	0.6083
No log	21.0	273	0.6015
No log	22.0	286	0.5942
No log	23.0	299	0.5873
No log	24.0	312	0.5821
No log	25.0	325	0.5774
No log	26.0	338	0.5718
No log	27.0	351	0.5663
No log	28.0	364	0.5618
No log	29.0	377	0.5573
No log	30.0	390	0.5529
No log	31.0	403	0.5492
No log	32.0	416	0.5455
No log	33.0	429	0.5427
No log	34.0	442	0.5394
No log	35.0	455	0.5366
No log	36.0	468	0.5336
No log	37.0	481	0.5310
No log	38.0	494	0.5288
No log	39.0	507	0.5265
No log	40.0	520	0.5237
No log	41.0	533	0.5211
No log	42.0	546	0.5190
No log	43.0	559	0.5165
No log	44.0	572	0.5143
No log	45.0	585	0.5130
No log	46.0	598	0.5115
No log	47.0	611	0.5101
No log	48.0	624	0.5085
No log	49.0	637	0.5067
No log	50.0	650	0.5051
No log	51.0	663	0.5035
No log	52.0	676	0.5021
No log	53.0	689	0.5008
No log	54.0	702	0.4992
No log	55.0	715	0.4979
No log	56.0	728	0.4963
No log	57.0	741	0.4950
No log	58.0	754	0.4937
No log	59.0	767	0.4924
No log	60.0	780	0.4911
No log	61.0	793	0.4899
No log	62.0	806	0.4886
No log	63.0	819	0.4874
No log	64.0	832	0.4869
No log	65.0	845	0.4861
No log	66.0	858	0.4850
No log	67.0	871	0.4838
No log	68.0	884	0.4828
No log	69.0	897	0.4817
No log	70.0	910	0.4808
No log	71.0	923	0.4799
No log	72.0	936	0.4790
No log	73.0	949	0.4781
No log	74.0	962	0.4776
No log	75.0	975	0.4769
No log	76.0	988	0.4763
1.1637	77.0	1001	0.4756
1.1637	78.0	1014	0.4751
1.1637	79.0	1027	0.4744
1.1637	80.0	1040	0.4739
1.1637	81.0	1053	0.4734
1.1637	82.0	1066	0.4729
1.1637	83.0	1079	0.4725
1.1637	84.0	1092	0.4722
1.1637	85.0	1105	0.4719
1.1637	86.0	1118	0.4716
1.1637	87.0	1131	0.4713
1.1637	88.0	1144	0.4710
1.1637	89.0	1157	0.4707
1.1637	90.0	1170	0.4703
1.1637	91.0	1183	0.4701
1.1637	92.0	1196	0.4699
1.1637	93.0	1209	0.4697
1.1637	94.0	1222	0.4695
1.1637	95.0	1235	0.4694
1.1637	96.0	1248	0.4692
1.1637	97.0	1261	0.4691
1.1637	98.0	1274	0.4691
1.1637	99.0	1287	0.4691
1.1637	100.0	1300	0.4690

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1