text2sql_t5large_tenjin_online

This model is a fine-tuned version of tscholak/1wnr382e on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: nan
• Bleu: 21.389
• Gen Len: 59.8256

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	21.389	59.8256
No log	2.0	86	nan	21.389	59.8256
No log	3.0	129	nan	21.389	59.8256
No log	4.0	172	nan	21.389	59.8256
No log	5.0	215	nan	21.389	59.8256
No log	6.0	258	nan	21.389	59.8256
No log	7.0	301	nan	21.389	59.8256
No log	8.0	344	nan	21.389	59.8256
No log	9.0	387	nan	21.389	59.8256
No log	10.0	430	nan	21.389	59.8256

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3