Hugging Face's logo

tsavage68
/
v1_1000_STEPS_1e6_SFT_SFT

Text Generation
Transformers
Safetensors
mistral
trl
sft
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
v1_1000_STEPS_1e6_SFT_SFT / README.md
tsavage68's picture
tsavage68
End of training
cec980d verified
preview code
|
raw
history blame contribute delete
2.43 kB
metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.1
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: v1_1000_STEPS_1e6_SFT_SFT
    results: []

v1_1000_STEPS_1e6_SFT_SFT

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2933

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-06
  • 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
0.3991 0.05 50 0.3739
0.3268 0.1 100 0.3451
0.3446 0.15 150 0.3264
0.3487 0.2 200 0.3183
0.3122 0.24 250 0.3140
0.3208 0.29 300 0.3103
0.307 0.34 350 0.3073
0.2965 0.39 400 0.3053
0.3101 0.44 450 0.3030
0.305 0.49 500 0.3001
0.2937 0.54 550 0.2985
0.3034 0.59 600 0.2967
0.2898 0.64 650 0.2953
0.282 0.68 700 0.2946
0.2846 0.73 750 0.2938
0.2969 0.78 800 0.2935
0.3073 0.83 850 0.2933
0.2792 0.88 900 0.2933
0.2837 0.93 950 0.2933
0.299 0.98 1000 0.2933

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.0.0+cu117
  • Datasets 2.18.0
  • Tokenizers 0.15.2