Hugging Face's logo

deb101
/
mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify / README.md
deb101's picture
deb101
Model save
64f479e verified
preview code
|
raw
history blame
9.24 kB
metadata
library_name: transformers
license: apache-2.0
base_model: mistralai/Mistral-7B-Instruct-v0.3
tags:
  - generated_from_trainer
model-index:
  - name: mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify
    results: []

mistral-7b-instruct-v0.3-mimic4-adapt-multilabel-classify

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the None dataset. It achieves the following results on the evaluation set:

  • F1 Micro: 0.0
  • F1 Macro: 0.0
  • Precision At 5: 0.2765
  • Recall At 5: 0.1167
  • Precision At 8: 0.2353
  • Recall At 8: 0.1441
  • Precision At 15: 0.1627
  • Recall At 15: 0.1927
  • Rare F1 Micro: 0.0
  • Rare F1 Macro: 0.0
  • Rare Precision: 0.0
  • Rare Recall: 0.0
  • Rare Precision At 5: 0.2397
  • Rare Recall At 5: 0.1023
  • Rare Precision At 8: 0.1967
  • Rare Recall At 8: 0.1289
  • Rare Precision At 15: 0.1397
  • Rare Recall At 15: 0.1722
  • Not Rare F1 Micro: 0.5956
  • Not Rare F1 Macro: 0.3733
  • Not Rare Precision: 0.5956
  • Not Rare Recall: 0.5956
  • Not Rare Precision At 5: 0.0809
  • Not Rare Recall At 5: 0.4044
  • Not Rare Precision At 8: 0.0506
  • Not Rare Recall At 8: 0.4044
  • Not Rare Precision At 15: 0.0270
  • Not Rare Recall At 15: 0.4044
  • Loss: 0.1031

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step F1 Micro F1 Macro Precision At 5 Recall At 5 Precision At 8 Recall At 8 Precision At 15 Recall At 15 Rare F1 Micro Rare F1 Macro Rare Precision Rare Recall Rare Precision At 5 Rare Recall At 5 Rare Precision At 8 Rare Recall At 8 Rare Precision At 15 Rare Recall At 15 Not Rare F1 Micro Not Rare F1 Macro Not Rare Precision Not Rare Recall Not Rare Precision At 5 Not Rare Recall At 5 Not Rare Precision At 8 Not Rare Recall At 8 Not Rare Precision At 15 Not Rare Recall At 15 Validation Loss
0.699 1.0 18 0.0 0.0 0.0588 0.0135 0.0506 0.0182 0.0441 0.0300 0.0 0.0 0.0 0.0 0.0559 0.0128 0.0506 0.0183 0.0426 0.0294 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.2374
0.1279 2.0 36 0.0 0.0 0.0529 0.0128 0.0432 0.0164 0.0436 0.0315 0.0 0.0 0.0 0.0 0.0515 0.0120 0.0487 0.0188 0.0446 0.0320 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1224
0.1087 3.0 54 0.0 0.0 0.0588 0.0136 0.0551 0.0206 0.0525 0.0404 0.0 0.0 0.0 0.0 0.0632 0.0152 0.0551 0.0210 0.0466 0.0325 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1073
0.1027 4.0 72 0.0 0.0 0.1485 0.0500 0.1278 0.0666 0.1025 0.0982 0.0 0.0 0.0 0.0 0.1162 0.0336 0.0938 0.0423 0.0789 0.0657 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1043
0.0973 5.0 90 0.0 0.0 0.25 0.0952 0.2105 0.1256 0.1505 0.1609 0.0 0.0 0.0 0.0 0.2044 0.0795 0.1682 0.1019 0.1299 0.1405 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1041
0.1023 6.0 108 0.0 0.0 0.2735 0.1098 0.2206 0.1379 0.1637 0.1803 0.0 0.0 0.0 0.0 0.2279 0.0975 0.1811 0.1157 0.1417 0.1629 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1036
0.1027 7.0 126 0.0 0.0 0.2838 0.1165 0.2325 0.1423 0.1588 0.1861 0.0 0.0 0.0 0.0 0.2353 0.0997 0.1893 0.1234 0.1387 0.1698 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1038
0.0994 8.0 144 0.0 0.0 0.2809 0.1176 0.2353 0.1441 0.1583 0.1850 0.0 0.0 0.0 0.0 0.2426 0.1042 0.1930 0.1245 0.1382 0.1696 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1033
0.1019 9.0 162 0.0 0.0 0.2809 0.1179 0.2353 0.1441 0.1618 0.1915 0.0 0.0 0.0 0.0 0.2412 0.1026 0.1912 0.1240 0.1412 0.1725 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1035
0.0961 9.4507 170 0.0 0.0 0.2765 0.1167 0.2353 0.1441 0.1627 0.1927 0.0 0.0 0.0 0.0 0.2397 0.1023 0.1967 0.1289 0.1397 0.1722 0.5956 0.3733 0.5956 0.5956 0.0809 0.4044 0.0506 0.4044 0.0270 0.4044 0.1031

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0
  • Datasets 3.6.0
  • Tokenizers 0.21.1