End of training

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+base_model: t5-base
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: t5-base_sst2_dense_epochs-6_exp_size_16
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      config: sst2
+      split: validation
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9185779816513762
+---
+
+<!-- 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. -->
+
+# t5-base_sst2_dense_epochs-6_exp_size_16
+
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2618
+- Accuracy: 0.9186
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6583        | 0.02  | 50   | 0.6411          | 0.6193   |
+| 0.328         | 0.05  | 100  | 0.2547          | 0.9106   |
+| 0.263         | 0.07  | 150  | 0.2392          | 0.9140   |
+| 0.2337        | 0.1   | 200  | 0.2295          | 0.9197   |
+| 0.216         | 0.12  | 250  | 0.2372          | 0.9255   |
+| 0.2194        | 0.14  | 300  | 0.2485          | 0.9186   |
+| 0.2214        | 0.17  | 350  | 0.2209          | 0.9220   |
+| 0.2094        | 0.19  | 400  | 0.2270          | 0.9220   |
+| 0.226         | 0.21  | 450  | 0.2156          | 0.9209   |
+| 0.1687        | 0.24  | 500  | 0.2618          | 0.9186   |
+| 0.1758        | 0.26  | 550  | 0.2279          | 0.9186   |
+| 0.2362        | 0.29  | 600  | 0.2314          | 0.9220   |
+| 0.2323        | 0.31  | 650  | 0.2442          | 0.9197   |
+| 0.1809        | 0.33  | 700  | 0.2065          | 0.9300   |
+| 0.2871        | 0.36  | 750  | 0.2135          | 0.9289   |
+| 0.16          | 0.38  | 800  | 0.2115          | 0.9243   |
+| 0.1438        | 0.4   | 850  | 0.2287          | 0.9255   |
+| 0.1732        | 0.43  | 900  | 0.2153          | 0.9255   |
+| 0.1847        | 0.45  | 950  | 0.3193          | 0.9278   |
+| 0.257         | 0.48  | 1000 | 0.3176          | 0.9289   |
+| 0.127         | 0.5   | 1050 | 0.1962          | 0.9300   |
+| 0.1791        | 0.52  | 1100 | 0.1928          | 0.9346   |
+| 0.2533        | 0.55  | 1150 | 0.1890          | 0.9335   |
+| 0.0762        | 0.57  | 1200 | 0.2866          | 0.9335   |
+| 0.1358        | 0.59  | 1250 | 0.4125          | 0.9335   |
+| 0.1385        | 0.62  | 1300 | 0.4090          | 0.9323   |
+| 0.184         | 0.64  | 1350 | 0.5092          | 0.9369   |
+| 0.1213        | 0.67  | 1400 | 0.5033          | 0.9404   |
+| 0.1597        | 0.69  | 1450 | 0.5152          | 0.9381   |
+| 0.1179        | 0.71  | 1500 | 0.3992          | 0.9381   |
+| 0.1689        | 0.74  | 1550 | 0.5163          | 0.9381   |
+| 0.1678        | 0.76  | 1600 | 0.5114          | 0.9404   |
+| 0.1673        | 0.78  | 1650 | 0.2786          | 0.9369   |
+
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.9.0
+- Tokenizers 0.14.1

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5407176d04b4d782f95cb79033e2df0117750b7c060476c2f33149973914cb25
+oid sha256:d703a628bae786b9e354bb197b046f318f646b0333fe542de5e4f1dab92a2261
 size 894094241