oh-dcft-v3.1-claude-3-5-haiku-20241022

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh-dcft-v3.1-claude-3-5-haiku-20241022 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4348

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: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 512
  • total_eval_batch_size: 64
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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
0.4531 0.9979 419 0.4542
0.3953 1.9976 838 0.4369
0.3539 2.9973 1257 0.4348

Framework versions

  • Transformers 4.46.1
  • Pytorch 2.3.0
  • Datasets 3.1.0
  • Tokenizers 0.20.3
Downloads last month
130
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for mlfoundations-dev/oh-dcft-v3.1-claude-3-5-haiku-20241022

Finetuned
(524)
this model
Quantizations
2 models