README.md

metadata

library_name: transformers
license: mit
base_model: Labira/LabiraPJOK_2_100_Full
tags:
  - generated_from_keras_callback
model-index:
  - name: Labira/LabiraPJOK_3_100_Full
    results: []

Labira/LabiraPJOK_3_100_Full

This model is a fine-tuned version of Labira/LabiraPJOK_2_100_Full on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0091
• Validation Loss: 0.0018
• Epoch: 29

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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
2.7614	1.1522	0
1.5531	0.5524	1
1.0482	0.2232	2
0.5443	0.0847	3
0.5227	0.0529	4
0.2873	0.0412	5
0.2568	0.0330	6
0.1310	0.0190	7
0.1108	0.0067	8
0.1252	0.0117	9
0.0740	0.0071	10
0.0507	0.0059	11
0.0790	0.0058	12
0.0282	0.0036	13
0.0562	0.0070	14
0.0850	0.0047	15
0.0715	0.0176	16
0.0724	0.0077	17
0.0361	0.0024	18
0.0266	0.0029	19
0.0207	0.0026	20
0.0158	0.0023	21
0.0086	0.0016	22
0.0214	0.0093	23
0.0327	0.0063	24
0.0102	0.0016	25
0.0072	0.0012	26
0.0273	0.0024	27
0.0185	0.0034	28
0.0091	0.0018	29

Framework versions

• Transformers 4.46.2
• TensorFlow 2.17.0
• Datasets 3.1.0
• Tokenizers 0.20.3