GaetanMichelet's picture
End of training
2b46a8f verified
|
raw
history blame
2.42 kB
metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
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: apache-2.0
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Mistral-7B_task-3_180-samples_config-2_auto
    results: []

Mistral-7B_task-3_180-samples_config-2_auto

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 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: 0.2898

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: 16
  • total_train_batch_size: 16
  • 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
2.4492 0.9412 8 1.9220
0.637 2.0 17 0.5030
0.3581 2.9412 25 0.3322
0.2132 4.0 34 0.2934
0.1909 4.9412 42 0.2898
0.1449 6.0 51 0.3128
0.0826 6.9412 59 0.3488
0.0486 8.0 68 0.4204
0.0329 8.9412 76 0.4306
0.0163 10.0 85 0.4600
0.0215 10.9412 93 0.4499
0.0048 12.0 102 0.4926

Framework versions

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