Progen2_Kinase_PhosphositeGen_dkz_traindata_250step
This model is a fine-tuned version of hugohrban/progen2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0437
- Perplexity: 7.7194
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 250
Training results
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|---|---|---|---|---|
| 9.8555 | 0.2793 | 100 | 2.1451 | 8.5432 |
| 8.5245 | 0.5587 | 200 | 2.0437 | 7.7194 |
Framework versions
- PEFT 0.13.2
- Transformers 4.47.1
- Pytorch 2.1.0.post301
- Datasets 3.0.2
- Tokenizers 0.21.0
- Downloads last month
- 3
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for mpekey/Progen2_Kinase_PhosphositeGen_dkz_traindata_250step
Base model
hugohrban/progen2-base