End of training

README.md

@@ -0,0 +1,74 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- emotion
+metrics:
+- accuracy
+model-index:
+- name: sagemaker-distilbert-emotion
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: emotion
+      type: emotion
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.919
+---
+
+<!-- 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. -->
+
+# sagemaker-distilbert-emotion
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2402
+- Accuracy: 0.919
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 64
+- 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: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9163        | 1.0   | 500  | 0.2402          | 0.919    |
+
+
+### Framework versions
+
+- Transformers 4.12.3
+- Pytorch 1.9.1
+- Datasets 1.15.1
+- Tokenizers 0.10.3

eval_results.txt

@@ -0,0 +1,6 @@
+epoch = 1.0
+eval_accuracy = 0.919
+eval_loss = 0.24016787111759186
+eval_runtime = 5.0705
+eval_samples_per_second = 394.44
+eval_steps_per_second = 6.311