llama2-7b-text-to-sql

This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4179
• Rouge Scores: {'rouge1': 0.9526993709609907, 'rouge2': 0.8978075478140412, 'rougeL': 0.9174568046902766, 'rougeLsum': 0.952706382197062}
• Bleu Scores: [0.9662302825731477, 0.9573342773221528, 0.94662296656899, 0.9353992025804378]
• Gen Len: 137.1996

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
0.4199	1.0	4800	0.4083	{'rouge1': 0.9515485575412006, 'rouge2': 0.8969346526448001, 'rougeL': 0.9158914697649283, 'rougeLsum': 0.9515858775802964}	[0.9648385943306861, 0.9555007745625858, 0.9446156319150308, 0.9332866028488176]	137.1996
0.3292	2.0	9600	0.3933	{'rouge1': 0.9529916925938159, 'rouge2': 0.8991327462278231, 'rougeL': 0.9182485534934295, 'rougeLsum': 0.9530038043530137}	[0.9663304534733925, 0.9575607481530943, 0.9470553639271937, 0.936060216085945]	137.1996
0.2569	3.0	14400	0.4179	{'rouge1': 0.9526993709609907, 'rouge2': 0.8978075478140412, 'rougeL': 0.9174568046902766, 'rougeLsum': 0.952706382197062}	[0.9662302825731477, 0.9573342773221528, 0.94662296656899, 0.9353992025804378]	137.1996

Framework versions

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