metadata

license: apache-2.0
base_model: ai-forever/FRED-T5-1.7B
tags:
  - generated_from_keras_callback
model-index:
  - name: t5-xl-tpu-jumoreski
    results: []

t5-xl-tpu-jumoreski

This model is a fine-tuned version of ai-forever/FRED-T5-1.7B on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.3608
Epoch: 7

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': 0.01, 'clipnorm': 1, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'CosineDecay', 'config': {'initial_learning_rate': 2e-06, 'decay_steps': 8552, 'alpha': 5e-09, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: mixed_bfloat16

Training results

Train Loss	Epoch
0.3666	0
0.3650	1
0.3643	2
0.3627	3
0.3625	4
0.3613	5
0.3605	6
0.3608	7

Framework versions

Transformers 4.33.3
TensorFlow 2.12.0
Datasets 2.14.5
Tokenizers 0.13.3