sft-mistral-v1

This model is a fine-tuned version of kam414/pre-train-mistral-v2-full on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 1.2212

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: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_steps: 0.2
• training_steps: 60

Training results

Training Loss	Epoch	Step	Validation Loss
1.9676	0.5	10	1.4137
1.3178	1.0	20	1.2463
1.071	1.5	30	1.2405
1.0554	2.0	40	1.2212

Framework versions

• PEFT 0.8.2
• Transformers 4.37.2
• Pytorch 2.2.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1