# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("ccore/gpt2_ACoT")
model = AutoModelForCausalLM.from_pretrained("ccore/gpt2_ACoT")Quick Links
gpt2_ACoT
This model is a fine-tuned version of facebook/opt-125m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9497
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 21.1265 | 1.0 | 276 | 2.5543 |
| 18.2347 | 2.0 | 552 | 2.2861 |
| 16.8533 | 3.0 | 828 | 2.1435 |
| 15.6224 | 4.0 | 1104 | 2.0605 |
| 14.7096 | 5.0 | 1380 | 2.0051 |
| 14.1231 | 6.0 | 1656 | 1.9733 |
| 13.5673 | 7.0 | 1932 | 1.9566 |
| 13.1727 | 8.0 | 2208 | 1.9493 |
| 13.0597 | 9.0 | 2484 | 1.9492 |
| 12.9195 | 10.0 | 2760 | 1.9497 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 1
Model tree for ccore/gpt2_ACoT
Base model
facebook/opt-125m
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ccore/gpt2_ACoT")