README.md

metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_keras_callback
model-index:
  - name: ecolibrium
    results: []

ecolibrium

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: 0.3202
• Validation Loss: 0.0689
• Epoch: 49

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': 0.0002, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
1.6155	1.3909	0
1.4232	1.2592	1
1.3301	1.1768	2
1.2562	1.0908	3
1.1925	1.0136	4
1.1417	0.9589	5
1.0953	0.9173	6
1.0502	0.8531	7
1.0103	0.8009	8
0.9761	0.7488	9
0.9404	0.7100	10
0.9095	0.6793	11
0.8743	0.6319	12
0.8480	0.6139	13
0.8233	0.5741	14
0.7942	0.5479	15
0.7697	0.5176	16
0.7456	0.4847	17
0.7250	0.4650	18
0.6996	0.4370	19
0.6790	0.4141	20
0.6607	0.3959	21
0.6428	0.3666	22
0.6249	0.3511	23
0.6060	0.3344	24
0.5944	0.3178	25
0.5750	0.2942	26
0.5607	0.2787	27
0.5453	0.2608	28
0.5317	0.2472	29
0.5146	0.2365	30
0.5017	0.2146	31
0.4909	0.2078	32
0.4764	0.1945	33
0.4664	0.1831	34
0.4517	0.1703	35
0.4397	0.1643	36
0.4316	0.1588	37
0.4196	0.1428	38
0.4073	0.1311	39
0.3949	0.1232	40
0.3871	0.1175	41
0.3776	0.1105	42
0.3705	0.1025	43
0.3623	0.0959	44
0.3514	0.0928	45
0.3427	0.0828	46
0.3346	0.0799	47
0.3268	0.0736	48
0.3202	0.0689	49

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1