mistral_instruct_generation_1

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.1697

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
1.1269	1.05	20	0.9776
0.7172	2.11	40	0.6484
0.3904	3.16	60	0.4038
0.2259	4.21	80	0.2688
0.1255	5.26	100	0.2077
0.0844	6.32	120	0.1844
0.0702	7.37	140	0.1669
0.0596	8.42	160	0.1673
0.0471	9.47	180	0.1629
0.0378	10.53	200	0.1697

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.17.0
• Tokenizers 0.15.1