ledat1205/mistral-instruct-duress-data

transformers

This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.0959

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: 48
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 90
• training_steps: 906

Training results

Training Loss	Epoch	Step	Validation Loss
0.1489	0.6094	181	0.1426
0.1299	1.2189	362	0.1197
0.1036	1.8283	543	0.1043
0.0999	2.4377	724	0.0975
0.0868	3.0471	905	0.0959

Framework versions

• Transformers 4.41.1
• Pytorch 2.0.1+cu118
• Datasets 2.16.0
• Tokenizers 0.19.1