metadata
license: mit
base_model: gpt2-xl
tags:
- generated_from_trainer
datasets:
- tyzhu/lmind_nq_v1_recite_qa
metrics:
- accuracy
model-index:
- name: lmind_nq_v1_recite_qa_gpt2-xl
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: tyzhu/lmind_nq_v1_recite_qa
type: tyzhu/lmind_nq_v1_recite_qa
metrics:
- name: Accuracy
type: accuracy
value: 0.8079757085020243
lmind_nq_v1_recite_qa_gpt2-xl
This model is a fine-tuned version of gpt2-xl on the tyzhu/lmind_nq_v1_recite_qa dataset. It achieves the following results on the evaluation set:
- Loss: 0.4010
- Accuracy: 0.8080
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| 2.5677 | 1.0 | 44 | 0.5621 | 2.2407 |
| 1.6845 | 2.0 | 88 | 0.6334 | 1.5647 |
| 0.944 | 3.0 | 132 | 0.7006 | 1.0917 |
| 0.5071 | 4.0 | 176 | 0.7509 | 0.7388 |
| 0.3104 | 5.0 | 220 | 0.7798 | 0.5627 |
| 0.2331 | 6.0 | 264 | 0.5108 | 0.7945 |
| 0.1608 | 7.0 | 308 | 0.4221 | 0.8043 |
| 0.1303 | 8.0 | 352 | 0.4075 | 0.8062 |
| 0.1159 | 9.0 | 396 | 0.4029 | 0.8068 |
| 0.1004 | 10.0 | 440 | 0.4010 | 0.8080 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.5
- Tokenizers 0.14.1