bedus-creation/eng-limbu-model-002

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

• Train Loss: 6.3256
• Validation Loss: 6.8791
• Epoch: 149

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
9.1271	8.7408	0
8.7900	8.5152	1
8.5937	8.2894	2
8.3940	8.1041	3
8.2510	7.9661	4
8.1174	7.8669	5
8.0494	7.7932	6
7.9458	7.7451	7
7.9505	7.7095	8
7.8572	7.6815	9
7.8339	7.6505	10
7.7734	7.6216	11
7.7619	7.5968	12
7.6829	7.5746	13
7.6692	7.5552	14
7.6492	7.5385	15
7.6289	7.5218	16
7.6122	7.5045	17
7.5815	7.4880	18
7.5513	7.4715	19
7.5763	7.4553	20
7.5594	7.4393	21
7.5081	7.4242	22
7.5002	7.4095	23
7.4710	7.3945	24
7.4328	7.3806	25
7.4605	7.3668	26
7.4181	7.3531	27
7.4068	7.3394	28
7.3782	7.3256	29
7.3866	7.3126	30
7.3759	7.2999	31
7.3582	7.2871	32
7.3298	7.2749	33
7.3253	7.2629	34
7.3116	7.2507	35
7.2920	7.2392	36
7.2491	7.2281	37
7.2856	7.2164	38
7.2565	7.2051	39
7.2665	7.1948	40
7.2424	7.1845	41
7.2314	7.1761	42
7.2365	7.1665	43
7.2141	7.1573	44
7.1938	7.1478	45
7.1938	7.1406	46
7.1646	7.1310	47
7.1463	7.1211	48
7.1652	7.1138	49
7.1247	7.1046	50
7.1294	7.0959	51
7.1428	7.0880	52
7.1101	7.0802	53
7.1195	7.0716	54
7.1366	7.0651	55
7.0781	7.0582	56
7.0638	7.0514	57
7.0636	7.0451	58
7.0585	7.0417	59
7.0634	7.0361	60
7.0355	7.0308	61
7.0535	7.0254	62
7.0424	7.0164	63
7.0075	7.0088	64
6.9984	7.0014	65
7.0072	6.9999	66
6.9888	6.9955	67
6.9763	6.9886	68
6.9629	6.9813	69
6.9639	6.9783	70
6.9769	6.9769	71
6.9634	6.9742	72
6.9616	6.9649	73
6.9513	6.9576	74
6.9337	6.9532	75
6.9313	6.9530	76
6.9044	6.9489	77
6.9203	6.9422	78
6.8990	6.9383	79
6.8745	6.9327	80
6.8947	6.9276	81
6.8696	6.9231	82
6.8699	6.9164	83
6.8697	6.9124	84
6.8504	6.9148	85
6.8526	6.9150	86
6.8367	6.9149	87
6.8351	6.9062	88
6.8641	6.8909	89
6.8182	6.8856	90
6.8246	6.8864	91
6.8376	6.8883	92
6.8005	6.8863	93
6.7832	6.8796	94
6.7806	6.8772	95
6.7876	6.8747	96
6.7757	6.8751	97
6.7548	6.8719	98
6.7685	6.8615	99
6.7535	6.8581	100
6.7244	6.8610	101
6.7281	6.8611	102
6.7342	6.8570	103
6.7141	6.8576	104
6.6942	6.8612	105
6.6985	6.8586	106
6.6644	6.8645	107
6.6835	6.8587	108
6.6289	6.8558	109
6.6531	6.8526	110
6.6052	6.8572	111
6.6341	6.8709	112
6.6392	6.8692	113
6.6320	6.8524	114
6.6142	6.8514	115
6.6246	6.8451	116
6.6171	6.8430	117
6.5912	6.8589	118
6.5726	6.8688	119
6.5736	6.8585	120
6.5748	6.8444	121
6.5666	6.8534	122
6.5968	6.8574	123
6.5416	6.8524	124
6.5257	6.8571	125
6.5724	6.8563	126
6.5125	6.8564	127
6.5113	6.8526	128
6.4686	6.8539	129
6.5103	6.8597	130
6.4730	6.8658	131
6.4959	6.8621	132
6.4437	6.8786	133
6.4526	6.8719	134
6.4328	6.8596	135
6.4678	6.8595	136
6.4271	6.8595	137
6.4482	6.8579	138
6.3347	6.8731	139
6.4074	6.8643	140
6.4132	6.8596	141
6.3897	6.8648	142
6.3232	6.8800	143
6.3461	6.8751	144
6.3384	6.8623	145
6.3414	6.8728	146
6.3258	6.9066	147
6.3153	6.8956	148
6.3256	6.8791	149

Framework versions

• Transformers 4.32.1
• TensorFlow 2.12.0
• Datasets 2.14.4
• Tokenizers 0.13.3