metadata
license: mit
base_model: clefourrier/pcqm4mv2_graphormer_base
tags:
- generated_from_trainer
model-index:
- name: graph-regression
results: []
graph-regression
This model is a fine-tuned version of clefourrier/pcqm4mv2_graphormer_base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.6828
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 640
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2485 | 0.9375 | 3 | 5.1142 |
| 6.8919 | 1.875 | 6 | 4.8364 |
| 5.2272 | 2.8125 | 9 | 4.6828 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1