openmathinstruct2-llama-3.1-8B-Instruct-lr5-ep2

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the openmathinstruct2_cot_20k_train dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7634

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: 1e-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • total_eval_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2.0

Training results

Training Loss Epoch Step Validation Loss
0.8177 0.4808 500 0.7823
0.7708 0.9615 1000 0.7572
0.5513 1.4423 1500 0.7693
0.5059 1.9231 2000 0.7637

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.20.1
Downloads last month
4
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for Lorraine013/openmathinstruct2-llama-3.1-8B-Instruct-lr5-ep2

Finetuned
(938)
this model
Quantizations
1 model