llama3-1_8b_oh_dcft_v1_wo_camel_math_gpt-4o-mini

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/OH_DCFT_v1_wo_camel_math_gpt-4o-mini dataset. It achieves the following results on the evaluation set:

• Loss: 0.5990

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: 5e-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 32
• total_train_batch_size: 512
• total_eval_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 1738
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6304	1.0	364	0.6319
0.5776	2.0	728	0.6050
0.5347	3.0	1092	0.5990

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1