oh-dcft-v1.2_no-curation_no-airoboros_gpt-4o-mini

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh-dcft-v1.2_no-curation_no-airoboros_gpt-4o-mini dataset. It achieves the following results on the evaluation set:

• Loss: 0.6511

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 16
• gradient_accumulation_steps: 4
• total_train_batch_size: 512
• total_eval_batch_size: 128
• 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
0.6662	0.9985	323	0.6590
0.6121	2.0	647	0.6484
0.5679	2.9954	969	0.6511

Framework versions

• Transformers 4.45.2
• Pytorch 2.3.0
• Datasets 2.21.0
• Tokenizers 0.20.3