tsavage68's picture
End of training
8e5c24c verified
metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: IE_M2_1000steps_1e8rate_SFT
    results: []

IE_M2_1000steps_1e8rate_SFT

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9087

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-08
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss
1.8842 0.4 50 1.9129
1.9556 0.8 100 1.9129
2.0184 1.2 150 1.9122
1.9342 1.6 200 1.9112
1.9748 2.0 250 1.9101
2.0075 2.4 300 1.9096
2.0233 2.8 350 1.9092
1.9096 3.2 400 1.9090
2.0202 3.6 450 1.9091
1.9009 4.0 500 1.9094
2.0555 4.4 550 1.9096
1.9723 4.8 600 1.9090
1.9996 5.2 650 1.9088
1.9609 5.6 700 1.9091
1.8893 6.0 750 1.9090
2.0061 6.4 800 1.9088
1.9079 6.8 850 1.9087
1.9566 7.2 900 1.9087
1.9496 7.6 950 1.9087
1.9817 8.0 1000 1.9087

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.0.0+cu117
  • Datasets 3.0.0
  • Tokenizers 0.19.1