End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- clinc_oos
+metrics:
+- accuracy
+model-index:
+- name: roberta-large-finetuned-clinc-12
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: clinc_oos
+      type: clinc_oos
+      args: plus
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9764516129032258
+---
+
+<!-- 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. -->
+
+# roberta-large-finetuned-clinc-12
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the clinc_oos dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1429
+- Accuracy: 0.9765
+
+## 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
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.8662        | 1.0   | 954  | 0.3441          | 0.9339   |
+| 0.158         | 2.0   | 1908 | 0.1498          | 0.9742   |
+| 0.0469        | 3.0   | 2862 | 0.1429          | 0.9765   |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.10.2+cu113
+- Datasets 1.18.4
+- Tokenizers 0.11.6

eval_results.txt

@@ -0,0 +1,6 @@
+epoch = 3.0
+eval_accuracy = 0.9764516129032258
+eval_loss = 0.14286792278289795
+eval_runtime = 14.7775
+eval_samples_per_second = 209.779
+eval_steps_per_second = 13.128

logs/events.out.tfevents.1649757753.algo-1.53.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b386fe45219042ca886ccfb398d99ccd04d5bf24aae5360a240ae71b4fe3a0e9
-size 12645
+oid sha256:6f2fbb46035f47c32c0ee1a67bb6da7be56f261015ae38e3598b3504d4de6b92
+size 12999

logs/events.out.tfevents.1649758611.algo-1.53.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a904daf25621688f4bf6f0d6b8310bda07b0fe08b3c6dba74093b690623df8
+size 363