README.md

metadata

license: other
tags:
  - generated_from_trainer
datasets:
  - wikitext
metrics:
  - accuracy
base_model: facebook/opt-350m
model-index:
  - name: ov-opt-350m-8bit-kv-cache
    results:
      - task:
          type: text-generation
          name: Causal Language Modeling
        dataset:
          name: wikitext wikitext-2-raw-v1
          type: wikitext
          config: wikitext-2-raw-v1
          split: validation
          args: wikitext-2-raw-v1
        metrics:
          - type: accuracy
            value: 0.39524275008145976
            name: Accuracy

ov-opt-350m-8bit-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: 3.2990
• Accuracy: 0.3952

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