binh230
/

mamba2-370m

+---
+license: apache-2.0
+base_model: state-spaces/mamba2-370m
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: mamba2-370m
+  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. -->
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/truonggiabjnh2003-fpt-university/Detect%20AI%20Generated%20Text/runs/i395kdop)
+# mamba2-370m
+This model is a fine-tuned version of [state-spaces/mamba2-370m](https://huggingface.co/state-spaces/mamba2-370m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1519
+- Accuracy: 0.9732
+- Precision: 0.9731
+- Recall: 0.9732
+- F1: 0.9732
+- Auroc: 0.9959
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- label_smoothing_factor: 0.03
+### Training results
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | Precision | Recall | F1     | Auroc  |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 0.5634        | 0.0241 | 500   | 0.4878          | 0.7683   | 0.8162    | 0.7683 | 0.7829 | 0.8277 |
+| 0.4106        | 0.0483 | 1000  | 0.2883          | 0.9124   | 0.9108    | 0.9124 | 0.9083 | 0.9483 |
+| 0.3316        | 0.0724 | 1500  | 0.3786          | 0.8827   | 0.8906    | 0.8827 | 0.8855 | 0.9322 |
+| 0.3096        | 0.0965 | 2000  | 0.3116          | 0.9160   | 0.9193    | 0.9160 | 0.9097 | 0.9578 |
+| 0.3098        | 0.1207 | 2500  | 0.2203          | 0.9333   | 0.9320    | 0.9333 | 0.9322 | 0.9755 |
+| 0.2798        | 0.1448 | 3000  | 0.1952          | 0.9434   | 0.9457    | 0.9434 | 0.9442 | 0.9835 |
+| 0.2769        | 0.1689 | 3500  | 0.2441          | 0.9321   | 0.9372    | 0.9321 | 0.9336 | 0.9776 |
+| 0.2777        | 0.1930 | 4000  | 0.2501          | 0.9291   | 0.9309    | 0.9291 | 0.9251 | 0.9852 |
+| 0.2523        | 0.2172 | 4500  | 0.2257          | 0.9381   | 0.9435    | 0.9381 | 0.9395 | 0.9843 |
+| 0.2406        | 0.2413 | 5000  | 0.2144          | 0.9381   | 0.9379    | 0.9381 | 0.9358 | 0.9846 |
+| 0.2272        | 0.2654 | 5500  | 0.1996          | 0.9535   | 0.9548    | 0.9535 | 0.9540 | 0.9783 |
+| 0.2514        | 0.2896 | 6000  | 0.2980          | 0.9124   | 0.9141    | 0.9124 | 0.9063 | 0.9768 |
+| 0.2363        | 0.3137 | 6500  | 0.2164          | 0.9482   | 0.9476    | 0.9482 | 0.9471 | 0.9821 |
+| 0.2329        | 0.3378 | 7000  | 0.1715          | 0.9589   | 0.9588    | 0.9589 | 0.9588 | 0.9906 |
+| 0.2149        | 0.3620 | 7500  | 0.1885          | 0.9601   | 0.9597    | 0.9601 | 0.9598 | 0.9884 |
+| 0.2061        | 0.3861 | 8000  | 0.2838          | 0.9196   | 0.9372    | 0.9196 | 0.9232 | 0.9859 |
+| 0.2114        | 0.4102 | 8500  | 0.1913          | 0.9506   | 0.9543    | 0.9506 | 0.9516 | 0.9898 |
+| 0.2001        | 0.4343 | 9000  | 0.2427          | 0.9369   | 0.9470    | 0.9369 | 0.9391 | 0.9897 |
+| 0.2053        | 0.4585 | 9500  | 0.2179          | 0.9506   | 0.9503    | 0.9506 | 0.9493 | 0.9809 |
+| 0.1942        | 0.4826 | 10000 | 0.1698          | 0.9643   | 0.9640    | 0.9643 | 0.9641 | 0.9897 |
+| 0.1829        | 0.5067 | 10500 | 0.2037          | 0.9541   | 0.9537    | 0.9541 | 0.9532 | 0.9890 |
+| 0.2006        | 0.5309 | 11000 | 0.1571          | 0.9637   | 0.9661    | 0.9637 | 0.9643 | 0.9944 |
+| 0.1735        | 0.5550 | 11500 | 0.1747          | 0.9655   | 0.9655    | 0.9655 | 0.9655 | 0.9899 |
+| 0.1782        | 0.5791 | 12000 | 0.1538          | 0.9708   | 0.9711    | 0.9708 | 0.9709 | 0.9934 |
+| 0.1719        | 0.6033 | 12500 | 0.1561          | 0.9714   | 0.9714    | 0.9714 | 0.9714 | 0.9935 |
+| 0.1566        | 0.6274 | 13000 | 0.1620          | 0.9702   | 0.9701    | 0.9702 | 0.9702 | 0.9944 |
+| 0.169         | 0.6515 | 13500 | 0.1695          | 0.9655   | 0.9652    | 0.9655 | 0.9652 | 0.9948 |
+| 0.1623        | 0.6756 | 14000 | 0.1487          | 0.9726   | 0.9727    | 0.9726 | 0.9726 | 0.9955 |
+| 0.162         | 0.6998 | 14500 | 0.1515          | 0.9726   | 0.9725    | 0.9726 | 0.9725 | 0.9942 |
+| 0.152         | 0.7239 | 15000 | 0.1528          | 0.9738   | 0.9736    | 0.9738 | 0.9737 | 0.9940 |
+| 0.1627        | 0.7480 | 15500 | 0.1458          | 0.9762   | 0.9763    | 0.9762 | 0.9762 | 0.9954 |
+| 0.1522        | 0.7722 | 16000 | 0.1613          | 0.9672   | 0.9680    | 0.9672 | 0.9675 | 0.9955 |
+| 0.1504        | 0.7963 | 16500 | 0.1547          | 0.9738   | 0.9738    | 0.9738 | 0.9738 | 0.9954 |
+| 0.1429        | 0.8204 | 17000 | 0.1582          | 0.9732   | 0.9730    | 0.9732 | 0.9731 | 0.9948 |
+| 0.1371        | 0.8446 | 17500 | 0.1630          | 0.9696   | 0.9696    | 0.9696 | 0.9696 | 0.9951 |
+| 0.1397        | 0.8687 | 18000 | 0.1573          | 0.9696   | 0.9700    | 0.9696 | 0.9698 | 0.9959 |
+| 0.1395        | 0.8928 | 18500 | 0.1580          | 0.9708   | 0.9710    | 0.9708 | 0.9709 | 0.9959 |
+| 0.1432        | 0.9169 | 19000 | 0.1552          | 0.9732   | 0.9733    | 0.9732 | 0.9732 | 0.9958 |
+| 0.1438        | 0.9411 | 19500 | 0.1539          | 0.9726   | 0.9725    | 0.9726 | 0.9725 | 0.9958 |
+| 0.145         | 0.9652 | 20000 | 0.1521          | 0.9732   | 0.9731    | 0.9732 | 0.9732 | 0.9959 |
+| 0.1475        | 0.9893 | 20500 | 0.1519          | 0.9732   | 0.9731    | 0.9732 | 0.9732 | 0.9959 |
+### Framework versions
+- Transformers 4.43.0.dev0
+- Pytorch 2.4.0+cu124
+- Datasets 2.19.1
+- Tokenizers 0.19.1