README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - eli5
metrics:
  - accuracy
model-index:
  - name: layer_9,10,11,12,13
    results:
      - task:
          type: text-generation
          name: Causal Language Modeling
        dataset:
          name: eli5
          type: eli5
          split: None
        metrics:
          - type: accuracy
            value: 0.49515362035225047
            name: Accuracy

layer_9,10,11,12,13

This model is a fine-tuned version of EleutherAI/pythia-1b-deduped on the eli5 dataset. It achieves the following results on the evaluation set:

• Loss: 2.4496
• Accuracy: 0.4952

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: 1
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.3186	5.93	200	4.3850	0.1399
2.7653	11.85	400	2.7820	0.4294

Framework versions

• Transformers 4.28.1
• Pytorch 2.0.1+rocm5.4.2
• Datasets 2.11.0
• Tokenizers 0.13.3

Wandb Report

https://wandb.ai/ontocord/jason-test-pythia-1b-deduped-layer-test-eli5/runs/eecbe79c