README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - roneneldan/TinyStories
metrics:
  - accuracy
model-index:
  - name: gpt2_u090_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: 0.6847785435700166

gpt2_u090_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: 1.1862
• Accuracy: 0.6848

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
2.8979	0.0516	1000	2.4237	0.4552
1.9485	0.1032	2000	1.7736	0.5751
1.6997	0.1548	3000	1.5877	0.6077
1.579	0.2063	4000	1.4891	0.6261
1.5078	0.2579	5000	1.4237	0.6382
1.457	0.3095	6000	1.3794	0.6467
1.4178	0.3611	7000	1.3463	0.6529
1.3857	0.4127	8000	1.3157	0.6587
1.3583	0.4643	9000	1.2949	0.6626
1.3406	0.5158	10000	1.2756	0.6667
1.3224	0.5674	11000	1.2575	0.6701
1.3063	0.6190	12000	1.2455	0.6725
1.2955	0.6706	13000	1.2323	0.6752
1.278	0.7222	14000	1.2199	0.6777
1.2714	0.7738	15000	1.2117	0.6794
1.2587	0.8253	16000	1.2042	0.6810
1.2527	0.8769	17000	1.1961	0.6826
1.2469	0.9285	18000	1.1906	0.6838
1.2434	0.9801	19000	1.1872	0.6846

Framework versions

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