You can deploy this model and start earning money today!

yunhuijang/
flpj0vul

Name: flpj0vul
Availability: InStock

transformers

safetensors

text2text-generation

generated_from_trainer

laituan245/molt5-small-caption2smiles

finetune

apache-2.0

text-generation-inference

endpoints_compatible

Views

No views yet

Visualize in Weights & Biases

flpj0vul

This model is a fine-tuned version of laituan245/molt5-small-caption2smiles on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8231
Bleu: 0.098
Exact: 0.02
Levenshtein: 46.34
Maccs fts: 0.595
Rdk fts: 0.464
Morgan fts: 0.437
Fcd metric: 28.939
Validity: 0.2

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: 2e-05
train_batch_size: 1024
eval_batch_size: 1024
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Exact	Levenshtein	Maccs fts	Rdk fts	Morgan fts	Fcd metric	Validity
No log	1.0	1	0.8254	0.098	0.01	46.36	0.574	0.436	0.407	29.33	0.19
No log	2.0	2	0.8245	0.098	0.01	46.37	0.574	0.436	0.407	29.33	0.19
No log	3.0	3	0.8238	0.098	0.02	46.33	0.577	0.448	0.421	29.103	0.21
No log	4.0	4	0.8234	0.098	0.02	46.34	0.595	0.464	0.437	28.939	0.2
No log	5.0	5	0.8231	0.098	0.02	46.34	0.595	0.464	0.437	28.939	0.2

Framework versions

Transformers 4.42.4
Pytorch 1.12.0
Datasets 2.20.0
Tokenizers 0.19.1

yunhuijang/flpj0vul

flpj0vul

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

yunhuijang/
flpj0vul