README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - roneneldan/TinyStories
metrics:
  - accuracy
model-index:
  - name: gpt2_u040_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: 0.6809154122817009

gpt2_u040_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: 1.2015
• Accuracy: 0.6809

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
2.8993	0.0523	1000	2.4128	0.4573
1.9582	0.1046	2000	1.7777	0.5731
1.7164	0.1569	3000	1.5985	0.6049
1.5976	0.2092	4000	1.5014	0.6224
1.5257	0.2615	5000	1.4399	0.6342
1.4723	0.3138	6000	1.3955	0.6425
1.4337	0.3661	7000	1.3618	0.6489
1.4068	0.4184	8000	1.3318	0.6549
1.3766	0.4707	9000	1.3082	0.6594
1.3567	0.5230	10000	1.2884	0.6632
1.3373	0.5753	11000	1.2717	0.6667
1.3231	0.6275	12000	1.2593	0.6692
1.3101	0.6798	13000	1.2451	0.6717
1.2962	0.7321	14000	1.2344	0.6740
1.2842	0.7844	15000	1.2259	0.6759
1.2752	0.8367	16000	1.2178	0.6776
1.2718	0.8890	17000	1.2103	0.6789
1.2628	0.9413	18000	1.2050	0.6803
1.2576	0.9936	19000	1.2016	0.6809

Framework versions

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