tenjinonline_text2sql_withjoins

This model is a fine-tuned version of tscholak/3vnuv1vf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Bleu: 22.2682
• Gen Len: 72.2442

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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	43	nan	22.2682	72.2442
No log	2.0	86	nan	22.2682	72.2442
No log	3.0	129	nan	22.2682	72.2442
No log	4.0	172	nan	22.2682	72.2442
No log	5.0	215	nan	22.2682	72.2442
No log	6.0	258	nan	22.2682	72.2442
No log	7.0	301	nan	22.2682	72.2442
No log	8.0	344	nan	22.2682	72.2442
No log	9.0	387	nan	22.2682	72.2442
No log	10.0	430	nan	22.2682	72.2442

Framework versions

• Transformers 4.30.2
• Pytorch 1.13.1+cu117
• Datasets 2.13.0
• Tokenizers 0.13.3