---
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-seed0
  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-seed0

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: 0.3804
- Accuracy: 0.9146
- Accuracy Sensor 0: 0.9046
- Auroc Sensor 0: 0.9551
- Accuracy Sensor 1: 0.9170
- Auroc Sensor 1: 0.9423
- Accuracy Sensor 2: 0.9398
- Auroc Sensor 2: 0.9764
- Accuracy Aggregated: 0.8970
- Auroc Aggregated: 0.9614

## 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 |
|:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-----------------:|:--------------:|:-------------------:|:----------------:|
| 0.2892        | 0.9997 | 781  | 0.3250          | 0.8582   | 0.8459            | 0.8992         | 0.8448            | 0.8967         | 0.8836            | 0.9420         | 0.8584              | 0.9095           |
| 0.1886        | 1.9994 | 1562 | 0.3029          | 0.8740   | 0.8822            | 0.9276         | 0.8798            | 0.9227         | 0.9057            | 0.9626         | 0.8284              | 0.9363           |
| 0.1237        | 2.9990 | 2343 | 0.2722          | 0.9012   | 0.8803            | 0.9463         | 0.9087            | 0.9354         | 0.9390            | 0.9761         | 0.8767              | 0.9562           |
| 0.0683        | 4.0    | 3125 | 0.3122          | 0.9088   | 0.8871            | 0.9520         | 0.9166            | 0.9417         | 0.9334            | 0.9757         | 0.8980              | 0.9590           |
| 0.0322        | 4.9984 | 3905 | 0.3804          | 0.9146   | 0.9046            | 0.9551         | 0.9170            | 0.9423         | 0.9398            | 0.9764         | 0.8970              | 0.9614           |


### Framework versions

- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1