README.md

metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: JuliusFx/dyu-fr-t5-small_v8
    results: []

JuliusFx/dyu-fr-t5-small_v8

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: 2.4243
• Validation Loss: 2.8930
• Epoch: 31

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
3.1481	3.2663	0
3.0205	3.2024	1
2.9712	3.1559	2
2.9209	3.1465	3
2.8848	3.1125	4
2.8512	3.1014	5
2.8239	3.0771	6
2.7965	3.0641	7
2.7743	3.0431	8
2.7505	3.0327	9
2.7325	3.0072	10
2.7153	3.0060	11
2.6904	2.9950	12
2.6750	2.9895	13
2.6554	2.9700	14
2.6400	2.9632	15
2.6220	2.9534	16
2.6059	2.9505	17
2.5913	2.9536	18
2.5779	2.9485	19
2.5624	2.9349	20
2.5469	2.9307	21
2.5341	2.9224	22
2.5223	2.9114	23
2.5093	2.8996	24
2.4995	2.9065	25
2.4855	2.8974	26
2.4706	2.8926	27
2.4589	2.9075	28
2.4521	2.8921	29
2.4380	2.9055	30
2.4243	2.8930	31

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2