bedus-creation/eng-limbu-t5-manual-001

This model is a fine-tuned version of bedus-creation/eng-limbu-t5-all-001 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 2.8893
• Validation Loss: 3.6600
• Epoch: 69

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
4.2750	4.2322	0
4.1667	4.1503	1
4.0966	4.0952	2
4.0536	4.0500	3
3.9914	4.0121	4
3.9422	3.9765	5
3.9123	3.9451	6
3.8867	3.9304	7
3.8378	3.9014	8
3.8279	3.8862	9
3.7932	3.8835	10
3.7725	3.8579	11
3.7653	3.8483	12
3.7401	3.8159	13
3.7069	3.8228	14
3.7007	3.7981	15
3.6797	3.7953	16
3.6476	3.7833	17
3.6299	3.7847	18
3.6046	3.7627	19
3.5917	3.7639	20
3.5799	3.7540	21
3.5757	3.7310	22
3.5402	3.7316	23
3.5430	3.7213	24
3.5086	3.7202	25
3.4939	3.7163	26
3.4725	3.6984	27
3.4554	3.6964	28
3.4278	3.6964	29
3.4357	3.6970	30
3.4297	3.6938	31
3.4024	3.6820	32
3.3928	3.6600	33
3.3757	3.6642	34
3.3640	3.6555	35
3.3264	3.6627	36
3.3270	3.6347	37
3.3104	3.6260	38
3.2856	3.6419	39
3.2632	3.6561	40
3.2600	3.6350	41
3.2450	3.6322	42
3.2248	3.6355	43
3.2071	3.6192	44
3.1965	3.6300	45
3.1809	3.6332	46
3.1697	3.6217	47
3.1591	3.6306	48
3.1451	3.6444	49
3.1168	3.6353	50
3.0928	3.6329	51
3.1097	3.6163	52
3.0847	3.6268	53
3.0832	3.6534	54
3.0712	3.6443	55
3.0607	3.6229	56
3.0110	3.6439	57
3.0208	3.6574	58
3.0153	3.6063	59
2.9872	3.6301	60
2.9894	3.6558	61
2.9745	3.6310	62
2.9629	3.6169	63
2.9564	3.6445	64
2.9207	3.6498	65
2.9216	3.6453	66
2.9199	3.6353	67
2.8910	3.6616	68
2.8893	3.6600	69

Framework versions

• Transformers 4.33.2
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3