GaetanMichelet's picture
End of training
439cd33 verified
metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - GaetanMichelet/chat-60_ft_task-3_auto
  - GaetanMichelet/chat-120_ft_task-3_auto
  - GaetanMichelet/chat-180_ft_task-3_auto
library_name: peft
license: llama3.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Llama-31-8B_task-3_180-samples_config-1_auto
    results: []

Llama-31-8B_task-3_180-samples_config-1_auto

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the GaetanMichelet/chat-60_ft_task-3_auto, the GaetanMichelet/chat-120_ft_task-3_auto and the GaetanMichelet/chat-180_ft_task-3_auto datasets. It achieves the following results on the evaluation set:

  • Loss: 0.3313

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 8
  • total_train_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: 50

Training results

Training Loss Epoch Step Validation Loss
1.7081 1.0 17 1.5542
0.509 2.0 34 0.4773
0.3144 3.0 51 0.3656
0.2899 4.0 68 0.3454
0.2162 5.0 85 0.3313
0.3465 6.0 102 0.3374
0.2498 7.0 119 0.3556
0.1023 8.0 136 0.4104
0.0862 9.0 153 0.4676
0.0549 10.0 170 0.4978
0.032 11.0 187 0.5856
0.0072 12.0 204 0.5623

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1