End of training

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: bert-base-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: assignment2_attempt11
+  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. -->
+
+# assignment2_attempt11
+
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5518
+- Precision: 0.2708
+- Recall: 0.1102
+- F1: 0.1566
+- Accuracy: 0.9379
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 128  | 0.3036          | 0.2553    | 0.1017 | 0.1455 | 0.9411   |
+| No log        | 2.0   | 256  | 0.3801          | 0.2553    | 0.1017 | 0.1455 | 0.9391   |
+| No log        | 3.0   | 384  | 0.3556          | 0.13      | 0.1102 | 0.1193 | 0.9337   |
+| 0.0586        | 4.0   | 512  | 0.3874          | 0.1806    | 0.1102 | 0.1368 | 0.9368   |
+| 0.0586        | 5.0   | 640  | 0.4519          | 0.2545    | 0.1186 | 0.1618 | 0.9387   |
+| 0.0586        | 6.0   | 768  | 0.4581          | 0.2593    | 0.1186 | 0.1628 | 0.9382   |
+| 0.0586        | 7.0   | 896  | 0.4750          | 0.2222    | 0.1356 | 0.1684 | 0.9368   |
+| 0.0088        | 8.0   | 1024 | 0.5352          | 0.2889    | 0.1102 | 0.1595 | 0.9397   |
+| 0.0088        | 9.0   | 1152 | 0.5362          | 0.2889    | 0.1102 | 0.1595 | 0.9397   |
+| 0.0088        | 10.0  | 1280 | 0.5526          | 0.2826    | 0.1102 | 0.1585 | 0.9385   |
+| 0.0088        | 11.0  | 1408 | 0.5330          | 0.2778    | 0.1271 | 0.1744 | 0.9379   |
+| 0.0022        | 12.0  | 1536 | 0.5490          | 0.2917    | 0.1186 | 0.1687 | 0.9382   |
+| 0.0022        | 13.0  | 1664 | 0.5442          | 0.28      | 0.1186 | 0.1667 | 0.9383   |
+| 0.0022        | 14.0  | 1792 | 0.5502          | 0.2653    | 0.1102 | 0.1557 | 0.9376   |
+| 0.0022        | 15.0  | 1920 | 0.5518          | 0.2708    | 0.1102 | 0.1566 | 0.9379   |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42895cdafd3923d71f6d98f80a961f9c5d64cdfa96631afb27649cb1ebaac6b
+oid sha256:0f152fe91f109b735e2079e86f8cd3aa4890713b679979ad52b49ac817f0a722
 size 430993062