mamiksik/CodeBERTa-commit-message-autocomplete

1---2tags:3- generated_from_trainer4metrics:5- accuracy6model-index:7- name: CodeBERTa-commit-message-autocomplete8  results: []9---10 11<!-- This model card has been generated automatically according to the information the Trainer had access to. You12should probably proofread and complete it, then remove this comment. -->13 14# CodeBERTa-commit-message-autocomplete15 16This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on the None dataset.17It achieves the following results on the evaluation set:18- Loss: 1.890619- Accuracy: 0.634620 21## Model description22 23More information needed24 25## Intended uses & limitations26 27More information needed28 29## Training and evaluation data30 31More information needed32 33## Training procedure34 35### Training hyperparameters36 37The following hyperparameters were used during training:38- learning_rate: 2e-0539- train_batch_size: 6440- eval_batch_size: 6441- seed: 4242- gradient_accumulation_steps: 1643- total_train_batch_size: 102444- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0845- lr_scheduler_type: linear46- lr_scheduler_warmup_steps: 100047- num_epochs: 5048- mixed_precision_training: Native AMP49 50### Training results51 52| Training Loss | Epoch | Step | Validation Loss | Accuracy |53|:-------------:|:-----:|:----:|:---------------:|:--------:|54| No log        | 1.0   | 40   | 4.5523          | 0.3432   |55| No log        | 2.0   | 80   | 3.8711          | 0.3796   |56| No log        | 3.0   | 120  | 3.2419          | 0.4503   |57| No log        | 4.0   | 160  | 2.8709          | 0.4962   |58| No log        | 5.0   | 200  | 2.6999          | 0.5085   |59| No log        | 6.0   | 240  | 2.6622          | 0.5216   |60| No log        | 7.0   | 280  | 2.5048          | 0.5410   |61| No log        | 8.0   | 320  | 2.4249          | 0.5581   |62| No log        | 9.0   | 360  | 2.3727          | 0.5623   |63| No log        | 10.0  | 400  | 2.3625          | 0.5665   |64| No log        | 11.0  | 440  | 2.3320          | 0.5706   |65| No log        | 12.0  | 480  | 2.1704          | 0.5950   |66| 3.081         | 13.0  | 520  | 2.2109          | 0.5893   |67| 3.081         | 14.0  | 560  | 2.2330          | 0.5884   |68| 3.081         | 15.0  | 600  | 2.1454          | 0.5954   |69| 3.081         | 16.0  | 640  | 2.1740          | 0.5951   |70| 3.081         | 17.0  | 680  | 2.1219          | 0.5920   |71| 3.081         | 18.0  | 720  | 2.1136          | 0.6052   |72| 3.081         | 19.0  | 760  | 2.0586          | 0.6127   |73| 3.081         | 20.0  | 800  | 2.0185          | 0.6113   |74| 3.081         | 21.0  | 840  | 2.0493          | 0.6129   |75| 3.081         | 22.0  | 880  | 1.9766          | 0.6217   |76| 3.081         | 23.0  | 920  | 1.9968          | 0.6189   |77| 3.081         | 24.0  | 960  | 1.9567          | 0.6276   |78| 2.122         | 25.0  | 1000 | 1.9611          | 0.6269   |79| 2.122         | 26.0  | 1040 | 1.9437          | 0.6254   |80| 2.122         | 27.0  | 1080 | 1.9865          | 0.6266   |81| 2.122         | 28.0  | 1120 | 1.9112          | 0.6295   |82| 2.122         | 29.0  | 1160 | 1.8903          | 0.6292   |83| 2.122         | 30.0  | 1200 | 1.8992          | 0.6376   |84| 2.122         | 31.0  | 1240 | 1.9122          | 0.6327   |85| 2.122         | 32.0  | 1280 | 1.8906          | 0.6346   |86 87 88### Framework versions89 90- Transformers 4.25.191- Pytorch 1.13.0+cu11792- Datasets 2.7.193- Tokenizers 0.13.294