codellama-7b-text-to-sql

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4224
• Rouge Scores: {'rouge1': 0.9523274691414706, 'rouge2': 0.8974742261714255, 'rougeL': 0.9171288478946306, 'rougeLsum': 0.9523427810006704}
• Bleu Scores: [0.9655707421980068, 0.9566701190306537, 0.9459215028465041, 0.9346533822146271]
• Gen Len: 138.6233

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: 0.0002
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.03
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge Scores	Bleu Scores	Gen Len
0.4229	1.0	4800	0.4162	{'rouge1': 0.9506510098188024, 'rouge2': 0.8949972495187106, 'rougeL': 0.9142255494550289, 'rougeLsum': 0.9506551339456668}	[0.9637759028147137, 0.9546609970402782, 0.9437656479747901, 0.9323669423057117]	138.6233
0.3314	2.0	9600	0.4004	{'rouge1': 0.9524326989909003, 'rouge2': 0.8987509624898048, 'rougeL': 0.9179414410323365, 'rougeLsum': 0.9524550499725172}	[0.9652102001679345, 0.9563139443363083, 0.9456856232691524, 0.9345677892198804]	138.6233
0.2666	3.0	14400	0.4224	{'rouge1': 0.9523274691414706, 'rouge2': 0.8974742261714255, 'rougeL': 0.9171288478946306, 'rougeLsum': 0.9523427810006704}	[0.9655707421980068, 0.9566701190306537, 0.9459215028465041, 0.9346533822146271]	138.6233

Framework versions

• PEFT 0.7.2.dev0
• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.2