cewinharhar/iceCream

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

• Train Loss: 1.1909
• Validation Loss: 3.0925
• Epoch: 92

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:

• optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
4.9926	4.0419	0
3.9831	3.8247	1
3.8396	3.7337	2
3.7352	3.6509	3
3.6382	3.5948	4
3.5595	3.5458	5
3.4845	3.4667	6
3.4140	3.4460	7
3.3546	3.4035	8
3.2939	3.3571	9
3.2420	3.3465	10
3.1867	3.2970	11
3.1418	3.2716	12
3.0865	3.2609	13
3.0419	3.2318	14
2.9962	3.2279	15
2.9551	3.1991	16
2.9178	3.1656	17
2.8701	3.1654	18
2.8348	3.1372	19
2.7988	3.1281	20
2.7597	3.0978	21
2.7216	3.1019	22
2.6844	3.0388	23
2.6489	3.0791	24
2.6192	3.0885	25
2.5677	3.0388	26
2.5478	3.0530	27
2.5136	3.0403	28
2.4756	3.0521	29
2.4454	3.0173	30
2.4203	3.0079	31
2.3882	3.0325	32
2.3596	3.0066	33
2.3279	2.9919	34
2.2947	2.9871	35
2.2712	2.9834	36
2.2311	2.9917	37
2.2022	2.9796	38
2.1703	2.9641	39
2.1394	2.9571	40
2.1237	2.9662	41
2.0949	2.9358	42
2.0673	2.9653	43
2.0417	2.9416	44
2.0194	2.9531	45
2.0009	2.9417	46
1.9716	2.9325	47
1.9488	2.9476	48
1.9265	2.9559	49
1.8975	2.9477	50
1.8815	2.9429	51
1.8552	2.9119	52
1.8358	2.9377	53
1.8226	2.9605	54
1.7976	2.9446	55
1.7677	2.9162	56
1.7538	2.9292	57
1.7376	2.9968	58
1.7156	2.9525	59
1.7001	2.9275	60
1.6806	2.9714	61
1.6582	2.9903	62
1.6436	2.9363	63
1.6254	2.9714	64
1.6093	2.9804	65
1.5900	2.9740	66
1.5686	2.9835	67
1.5492	3.0018	68
1.5371	3.0088	69
1.5245	2.9780	70
1.5021	3.0176	71
1.4839	2.9917	72
1.4726	3.0602	73
1.4568	3.0055	74
1.4435	3.0186	75
1.4225	2.9948	76
1.4088	3.0270	77
1.3947	3.0676	78
1.3780	3.0615	79
1.3627	3.0780	80
1.3445	3.0491	81
1.3293	3.0534	82
1.3130	3.0460	83
1.2980	3.0846	84
1.2895	3.0709	85
1.2737	3.0903	86
1.2557	3.0854	87
1.2499	3.1101	88
1.2353	3.1181	89
1.2104	3.1111	90
1.2101	3.1153	91
1.1909	3.0925	92

Framework versions

• Transformers 4.19.2
• TensorFlow 2.9.1
• Datasets 2.1.0
• Tokenizers 0.12.1