Hugging Face's logo

vuiseng9
/
ov-opt-350m-fp32-kv-cache

Text Generation
Transformers
PyTorch
OpenVINO
opt
generated_from_trainer
Eval Results
Inference Endpoints
text-generation-inference
Model card Files Community
1
ov-opt-350m-fp32-kv-cache / README.md
Vui Seng Chua
Add content
e1db940
preview code
|
raw history blame contribute delete
No virus
1.51 kB
metadata
license: other
tags:
  - generated_from_trainer
datasets:
  - wikitext
metrics:
  - accuracy
model-index:
  - name: ov-opt-350m-fp32-kv-cache
    results:
      - task:
          name: Causal Language Modeling
          type: text-generation
        dataset:
          name: wikitext wikitext-2-raw-v1
          type: wikitext
          config: wikitext-2-raw-v1
          split: validation
          args: wikitext-2-raw-v1
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.1335940045617465

ov-opt-350m-fp32-kv-cache

This model is a fine-tuned version of facebook/opt-350m on the wikitext wikitext-2-raw-v1 dataset. It achieves the following results on the evaluation set:

  • Loss: 6.2368
  • Accuracy: 0.1336

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: 8
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 1

Training results

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3