README.md

metadata

tags:
  - generated_from_trainer
datasets:
  - roneneldan/TinyStories
metrics:
  - accuracy
model-index:
  - name: gpt2_u070_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: 0.6825075944405236

gpt2_u070_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: 1.1951
• Accuracy: 0.6825

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
2.9077	0.0520	1000	2.4249	0.4548
1.9481	0.1040	2000	1.7689	0.5757
1.7051	0.1560	3000	1.5897	0.6072
1.5909	0.2081	4000	1.4959	0.6243
1.5165	0.2601	5000	1.4326	0.6359
1.4645	0.3121	6000	1.3880	0.6441
1.4312	0.3641	7000	1.3518	0.6512
1.3952	0.4161	8000	1.3251	0.6562
1.3699	0.4681	9000	1.3029	0.6608
1.3497	0.5202	10000	1.2838	0.6643
1.3312	0.5722	11000	1.2663	0.6680
1.3141	0.6242	12000	1.2515	0.6708
1.3035	0.6762	13000	1.2400	0.6731
1.2874	0.7282	14000	1.2295	0.6752
1.28	0.7802	15000	1.2204	0.6772
1.2689	0.8322	16000	1.2115	0.6791
1.2625	0.8843	17000	1.2051	0.6805
1.2536	0.9363	18000	1.1992	0.6817
1.2535	0.9883	19000	1.1952	0.6824

Framework versions

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