dyu-fr-t5-small

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: 2.7460
• Validation Loss: 2.7296
• Epoch: 24

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
3.6901	3.2495	0
3.4675	3.1435	1
3.3768	3.0836	2
3.3150	3.0325	3
3.2568	2.9926	4
3.2142	2.9639	5
3.1743	2.9341	6
3.1376	2.9166	7
3.1019	2.8968	8
3.0716	2.8781	9
3.0480	2.8647	10
3.0187	2.8465	11
2.9931	2.8347	12
2.9661	2.8247	13
2.9482	2.8123	14
2.9176	2.7992	15
2.9023	2.7922	16
2.8792	2.7826	17
2.8600	2.7731	18
2.8422	2.7683	19
2.8236	2.7567	20
2.7979	2.7493	21
2.7856	2.7438	22
2.7681	2.7346	23
2.7460	2.7296	24

Framework versions

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