sqlm

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3168

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.03
• training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
0.5858	0.0333	20	0.4605
0.395	0.0667	40	0.3820
0.352	0.1	60	0.3551
0.3695	0.1333	80	0.3410
0.3281	0.1667	100	0.3359
0.3304	0.2	120	0.3325
0.3435	0.2333	140	0.3292
0.3416	0.2667	160	0.3275
0.3331	0.3	180	0.3221
0.328	0.3333	200	0.3168

Framework versions

• PEFT 0.10.0
• Transformers 4.40.0
• Pytorch 2.2.2+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1