|
--- |
|
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-seed3 |
|
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-seed3 |
|
|
|
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: 0.3757 |
|
- Accuracy: 0.9134 |
|
- Accuracy Sensor 0: 0.9235 |
|
- Auroc Sensor 0: 0.9559 |
|
- Accuracy Sensor 1: 0.8989 |
|
- Auroc Sensor 1: 0.9539 |
|
- Accuracy Sensor 2: 0.9486 |
|
- Auroc Sensor 2: 0.9653 |
|
- Accuracy Aggregated: 0.8826 |
|
- Auroc Aggregated: 0.9553 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-------------------:|:----------------:| |
|
| 0.287 | 0.9997 | 781 | 0.4392 | 0.8094 | 0.8151 | 0.8977 | 0.8235 | 0.9036 | 0.8395 | 0.9106 | 0.7594 | 0.8793 | |
|
| 0.2108 | 1.9994 | 1562 | 0.2409 | 0.9058 | 0.9011 | 0.9242 | 0.9062 | 0.9344 | 0.9238 | 0.9424 | 0.8920 | 0.9178 | |
|
| 0.1549 | 2.9990 | 2343 | 0.2347 | 0.9119 | 0.9185 | 0.9519 | 0.8929 | 0.9546 | 0.9481 | 0.9605 | 0.8883 | 0.9476 | |
|
| 0.0887 | 4.0 | 3125 | 0.2867 | 0.9139 | 0.9243 | 0.9558 | 0.9057 | 0.9547 | 0.9473 | 0.9653 | 0.8785 | 0.9543 | |
|
| 0.0444 | 4.9984 | 3905 | 0.3757 | 0.9134 | 0.9235 | 0.9559 | 0.8989 | 0.9539 | 0.9486 | 0.9653 | 0.8826 | 0.9553 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
