Chatbot_Model_Trial – AI Model by StaticOwl | AlphaNeural AI

You can deploy this model and start earning money today!

StaticOwl/
Chatbot_Model_Trial

like

0

text2text-generation

generated_from_trainer

google/flan-t5-base

text-generation-inference

endpoints_compatible

Views

No views yet

Chatbot_Model_Trial

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4141
Rouge1: 20.2835
Rouge2: 9.4794
Rougel: 20.2587
Rougelsum: 20.2835
Gen Len: 14.125

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:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	10	1.9123	18.7955	5.5978	17.9735	17.9848	14.75
No log	2.0	20	1.6554	22.5345	7.961	21.3846	21.8442	15.0
No log	3.0	30	1.5016	25.764	8.9312	24.6364	25.0268	13.75
No log	4.0	40	1.4346	20.2835	9.4794	20.2587	20.2835	14.125
No log	5.0	50	1.4141	20.2835	9.4794	20.2587	20.2835	14.125

Framework versions

Transformers 4.35.0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1