README.md

metadata

license: apache-2.0
base_model: bedus-creation/mBart-small-dataset-ii-eng-lim-003
tags:
  - generated_from_keras_callback
model-index:
  - name: bedus-creation/mBart-small-dataset-ii-eng-lim-003
    results: []

bedus-creation/mBart-small-dataset-ii-eng-lim-003

This model is a fine-tuned version of bedus-creation/mBart-small-dataset-ii-eng-lim-003 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.1635
• Validation Loss: 0.2524
• Epoch: 41

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': 1e-04, '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
0.2093	0.2072	0
0.2068	0.2056	1
0.2062	0.2023	2
0.2045	0.2054	3
0.2027	0.2188	4
0.2019	0.2067	5
0.1997	0.2056	6
0.1991	0.2074	7
0.1978	0.2024	8
0.1962	0.2067	9
0.1955	0.2074	10
0.1945	0.2089	11
0.1928	0.2168	12
0.1907	0.2201	13
0.1900	0.2102	14
0.1888	0.2130	15
0.1882	0.2211	16
0.1870	0.2117	17
0.1857	0.2134	18
0.1838	0.2147	19
0.1824	0.2187	20
0.1812	0.2224	21
0.1813	0.2249	22
0.1798	0.2200	23
0.1787	0.2273	24
0.1772	0.2263	25
0.1780	0.2273	26
0.1764	0.2270	27
0.1754	0.2245	28
0.1738	0.2260	29
0.1730	0.2327	30
0.1720	0.2300	31
0.1702	0.2347	32
0.1698	0.2396	33
0.1689	0.2340	34
0.1693	0.2345	35
0.1661	0.2424	36
0.1663	0.2388	37
0.1658	0.2436	38
0.1654	0.2506	39
0.1639	0.2406	40
0.1635	0.2524	41

Framework versions

• Transformers 4.33.3
• TensorFlow 2.13.0
• Datasets 2.14.5
• Tokenizers 0.13.3