|
--- |
|
license: bsd-3-clause |
|
base_model: Salesforce/codegen-350M-mono |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: codegen-350M-mono-measurement_pred-diamonds-seed1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# codegen-350M-mono-measurement_pred-diamonds-seed1 |
|
|
|
This model is a fine-tuned version of [Salesforce/codegen-350M-mono](https://huggingface.co/Salesforce/codegen-350M-mono) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4208 |
|
- Accuracy: 0.9039 |
|
- Accuracy Sensor 0: 0.8951 |
|
- Auroc Sensor 0: 0.9544 |
|
- Accuracy Sensor 1: 0.9114 |
|
- Auroc Sensor 1: 0.9468 |
|
- Accuracy Sensor 2: 0.9304 |
|
- Auroc Sensor 2: 0.9752 |
|
- Accuracy Aggregated: 0.8787 |
|
- Auroc Aggregated: 0.9601 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 64 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Accuracy Sensor 0 | Auroc Sensor 0 | Accuracy Sensor 1 | Auroc Sensor 1 | Accuracy Sensor 2 | Auroc Sensor 2 | Accuracy Aggregated | Auroc Aggregated | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-------------------:|:----------------:| |
|
| 0.2957 | 0.9997 | 781 | 0.3062 | 0.8755 | 0.8833 | 0.8927 | 0.8724 | 0.8925 | 0.8966 | 0.9193 | 0.8494 | 0.8893 | |
|
| 0.1972 | 1.9994 | 1562 | 0.2602 | 0.8922 | 0.8898 | 0.9341 | 0.9076 | 0.9355 | 0.9133 | 0.9617 | 0.8582 | 0.9350 | |
|
| 0.1195 | 2.9990 | 2343 | 0.2889 | 0.8943 | 0.8747 | 0.9475 | 0.9022 | 0.9347 | 0.9168 | 0.9700 | 0.8835 | 0.9516 | |
|
| 0.0784 | 4.0 | 3125 | 0.3078 | 0.9104 | 0.9084 | 0.9574 | 0.9125 | 0.9486 | 0.9380 | 0.9760 | 0.8828 | 0.9611 | |
|
| 0.0347 | 4.9984 | 3905 | 0.4208 | 0.9039 | 0.8951 | 0.9544 | 0.9114 | 0.9468 | 0.9304 | 0.9752 | 0.8787 | 0.9601 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
