CapitainData/dyu-fr-t5-base_v3

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: 0.6666
• Validation Loss: 3.0327
• Epoch: 88

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
3.3233	2.8819	0
3.0679	2.7736	1
2.9557	2.7031	2
2.8537	2.6517	3
2.7672	2.6141	4
2.6959	2.5790	5
2.6234	2.5559	6
2.5663	2.5288	7
2.5025	2.5099	8
2.4535	2.4976	9
2.3996	2.4791	10
2.3570	2.4646	11
2.3096	2.4504	12
2.2604	2.4454	13
2.2212	2.4427	14
2.1817	2.4356	15
2.1437	2.4339	16
2.1022	2.4223	17
2.0667	2.4204	18
2.0382	2.4182	19
1.9938	2.4242	20
1.9631	2.4265	21
1.9289	2.4125	22
1.8995	2.4177	23
1.8716	2.4195	24
1.8402	2.4214	25
1.8068	2.4280	26
1.7809	2.4226	27
1.7446	2.4455	28
1.7253	2.4453	29
1.6978	2.4497	30
1.6735	2.4501	31
1.6427	2.4633	32
1.6168	2.4633	33
1.5921	2.4670	34
1.5688	2.4659	35
1.5417	2.4874	36
1.5189	2.4790	37
1.4963	2.4961	38
1.4715	2.4951	39
1.4486	2.5063	40
1.4263	2.5078	41
1.4068	2.5306	42
1.3814	2.5477	43
1.3645	2.5501	44
1.3394	2.5548	45
1.3223	2.5493	46
1.3060	2.5572	47
1.2850	2.6033	48
1.2566	2.5900	49
1.2426	2.6090	50
1.2266	2.6152	51
1.2067	2.6252	52
1.1842	2.6435	53
1.1680	2.6481	54
1.1476	2.6438	55
1.1295	2.6559	56
1.1128	2.6910	57
1.1000	2.6722	58
1.0787	2.6840	59
1.0636	2.7139	60
1.0425	2.7218	61
1.0298	2.7196	62
1.0150	2.7374	63
0.9989	2.7367	64
0.9811	2.7660	65
0.9674	2.7741	66
0.9490	2.7701	67
0.9322	2.7856	68
0.9197	2.7829	69
0.9010	2.8053	70
0.8894	2.8119	71
0.8732	2.8408	72
0.8597	2.8401	73
0.8404	2.8706	74
0.8317	2.8872	75
0.8204	2.8772	76
0.8083	2.8962	77
0.7905	2.9103	78
0.7825	2.9111	79
0.7659	2.9394	80
0.7486	2.9496	81
0.7359	2.9663	82
0.7250	2.9775	83
0.7133	2.9877	84
0.7035	2.9884	85
0.6912	2.9902	86
0.6762	3.0133	87
0.6666	3.0327	88

Framework versions

• Transformers 4.38.2
• TensorFlow 2.16.1
• Datasets 2.18.0
• Tokenizers 0.15.2