bert-5-epoch-sentiment

README.md

@@ -0,0 +1,91 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+datasets:
+- tweet_eval
+metrics:
+- accuracy
+- precision
+- recall
+model-index:
+- name: bert-5-epoch-sentiment
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: tweet_eval
+      type: tweet_eval
+      config: sentiment
+      split: test
+      args: sentiment
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.6754314555519375
+    - name: Precision
+      type: precision
+      value: 0.6779994190554874
+    - name: Recall
+      type: recall
+      value: 0.6754314555519375
+---
+
+<!-- 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. -->
+
+# bert-5-epoch-sentiment
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the tweet_eval dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5187
+- Accuracy: 0.6754
+- Precision: 0.6780
+- Recall: 0.6754
+- Micro-avg-recall: 0.6754
+- Micro-avg-precision: 0.6754
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:----------------:|:-------------------:|
+| 0.0381        | 1.0   | 2851  | 2.4402          | 0.6588   | 0.6676    | 0.6588 | 0.6588           | 0.6588              |
+| 0.0401        | 2.0   | 5702  | 2.7499          | 0.6527   | 0.6647    | 0.6527 | 0.6527           | 0.6527              |
+| 0.1609        | 3.0   | 8553  | 2.0380          | 0.6687   | 0.6724    | 0.6687 | 0.6687           | 0.6687              |
+| 0.1811        | 4.0   | 11404 | 2.3206          | 0.6679   | 0.6753    | 0.6679 | 0.6679           | 0.6679              |
+| 0.0987        | 5.0   | 14255 | 2.5187          | 0.6754   | 0.6780    | 0.6754 | 0.6754           | 0.6754              |
+
+
+### Framework versions
+
+- Transformers 4.33.0
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.13.3

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ea46bbd5d33238cdae54fc18197b79d63a982c49d317a8ce2b1dff6b201573
+size 4027