README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - roneneldan/TinyStories
metrics:
  - accuracy
model-index:
  - name: gpt2_u100_tiny-stories_1024_dpos
    results:
      - task:
          name: Causal Language Modeling
          type: text-generation
        dataset:
          name: roneneldan/TinyStories
          type: roneneldan/TinyStories
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.6900891972857721

gpt2_u100_tiny-stories_1024_dpos

This model is a fine-tuned version of on the roneneldan/TinyStories dataset. It achieves the following results on the evaluation set:

• Loss: 1.1688
• Accuracy: 0.6901

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.8305	0.0505	1000	2.3790	0.4650
1.9272	0.1009	2000	1.7501	0.5809
1.6793	0.1514	3000	1.5689	0.6136
1.5605	0.2018	4000	1.4699	0.6316
1.4891	0.2523	5000	1.4112	0.6422
1.4391	0.3028	6000	1.3646	0.6514
1.3995	0.3532	7000	1.3317	0.6575
1.3707	0.4037	8000	1.3021	0.6631
1.3424	0.4541	9000	1.2806	0.6675
1.3242	0.5046	10000	1.2613	0.6714
1.3058	0.5551	11000	1.2435	0.6748
1.2888	0.6055	12000	1.2291	0.6777
1.2748	0.6560	13000	1.2178	0.6801
1.2654	0.7064	14000	1.2077	0.6821
1.2549	0.7569	15000	1.1964	0.6843
1.2459	0.8073	16000	1.1878	0.6860
1.2385	0.8578	17000	1.1819	0.6873
1.2286	0.9083	18000	1.1756	0.6886
1.2246	0.9587	19000	1.1708	0.6896

Framework versions

• Transformers 4.42.3
• Pytorch 2.2.2+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1