|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: crest-data-systems/gitlab-mr-analysis-default-model |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: gitlab-mr-analysis-default-model_07112024T144546 |
|
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. --> |
|
|
|
# gitlab-mr-analysis-default-model_07112024T144546 |
|
|
|
This model is a fine-tuned version of [crest-data-systems/gitlab-mr-analysis-default-model](https://huggingface.co/crest-data-systems/gitlab-mr-analysis-default-model) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.8027 |
|
- F1: 0.6073 |
|
- Learning Rate: 0.0 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 | Rate | |
|
|:-------------:|:-------:|:----:|:---------------:|:------:|:------:| |
|
| No log | 0.9943 | 87 | 1.4164 | 0.4734 | 0.0000 | |
|
| No log | 2.0 | 175 | 1.1559 | 0.5633 | 0.0000 | |
|
| No log | 2.9943 | 262 | 1.1174 | 0.5783 | 0.0000 | |
|
| No log | 4.0 | 350 | 1.1657 | 0.5926 | 0.0000 | |
|
| No log | 4.9943 | 437 | 1.2393 | 0.5971 | 0.0000 | |
|
| 1.1987 | 6.0 | 525 | 1.3274 | 0.5808 | 0.0000 | |
|
| 1.1987 | 6.9943 | 612 | 1.4004 | 0.5978 | 0.0000 | |
|
| 1.1987 | 8.0 | 700 | 1.5053 | 0.5934 | 0.0000 | |
|
| 1.1987 | 8.9943 | 787 | 1.5536 | 0.5977 | 0.0000 | |
|
| 1.1987 | 10.0 | 875 | 1.6054 | 0.6014 | 0.0000 | |
|
| 1.1987 | 10.9943 | 962 | 1.6829 | 0.5987 | 0.0000 | |
|
| 0.2146 | 12.0 | 1050 | 1.7637 | 0.6054 | 0.0000 | |
|
| 0.2146 | 12.9943 | 1137 | 1.7628 | 0.6033 | 0.0000 | |
|
| 0.2146 | 14.0 | 1225 | 1.7768 | 0.6056 | 0.0000 | |
|
| 0.2146 | 14.9143 | 1305 | 1.8027 | 0.6073 | 0.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.1+cu124 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.19.1 |
|
|
