Grogros/dmWM-mistralai-Ministral-8B-Instruct-2410-LucieFr-Al4-OWT-d4-a0.1-v2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

dmWM-mistralai-Ministral-8B-Instruct-2410-LucieFr-Al4-OWT-d4-a0.1-v2

This model is a fine-tuned version of mistralai/Ministral-8B-Instruct-2410 on the None dataset.

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: 2e-05
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 32
• —optimizer: Use adafactor and the args are: No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —training_steps: 2500

Training results

Framework versions

• —Transformers 4.51.3
• —Pytorch 2.2.0a0+81ea7a4
• —Datasets 3.6.0
• —Tokenizers 0.21.1