Grogros-dmWM-Llama-3.1-8B-Instruct-LucieFr-Al4-OWT-TV-OpenMathInstruct

<!-- 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. -->

Grogros-dmWM-Llama-3.1-8B-Instruct-LucieFr-Al4-OWT-TV-OpenMathInstruct

This model is a fine-tuned version of Grogros/dmWM-meta-llama-Llama-3.1-8B-Instruct-ft-LucieFr-AlpacaGPT4-OpenWebText-TV on an unknown 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
• train_batch_size: 4
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use adafactor and the args are: No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 2500

Training results

Framework versions

• Transformers 4.53.3
• Pytorch 2.2.0a0+81ea7a4
• Datasets 3.6.0
• Tokenizers 0.21.2