lillian039's picture
End of training
0d751da verified
metadata
library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - >-
    barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
model-index:
  - name: google_cloude_test_20k_transduction-gpt4omini_lr1e-5_epoch2_2
    results: []

google_cloude_test_20k_transduction-gpt4omini_lr1e-5_epoch2_2

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0622

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: 8
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • 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

Training results

Training Loss Epoch Step Validation Loss
0.0949 0.9966 145 0.0753
0.065 1.9931 290 0.0622

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.4.0+cu121
  • Datasets 3.0.0
  • Tokenizers 0.19.1