Hugging Face's logo

jdeklerk10
/
DS-6.7B-schema_2

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
DS-6.7B-schema_2 / README.md
jdeklerk10's picture
jdeklerk10
End of training
c49ac52 verified
preview code
|
raw
history blame
1.7 kB
metadata
license: other
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
model-index:
  - name: DS-6.7B-schema_2
    results: []

DS-6.7B-schema_2

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1718

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.0235 0.19 50 0.2107
0.0528 0.38 100 0.1890
0.055 0.57 150 0.1867
0.053 0.76 200 0.1722
0.0843 0.95 250 0.1718

Framework versions

  • PEFT 0.10.0
  • Transformers 4.40.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2