End of training

README.md

@@ -0,0 +1,81 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: roberta-large-sst2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9644495412844036
+---
+
+<!-- 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-sst2
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1400
+- Accuracy: 0.9644
+
+## 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: 32
+- seed: 42
+- distributed_type: sagemaker_data_parallel
+- num_devices: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.3688        | 1.0   | 264  | 0.1444          | 0.9564   |
+| 0.1529        | 2.0   | 528  | 0.1502          | 0.9518   |
+| 0.107         | 3.0   | 792  | 0.1388          | 0.9530   |
+| 0.0666        | 4.0   | 1056 | 0.1400          | 0.9644   |
+
+
+### 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 = 4.0
+eval_accuracy = 0.9644495412844036
+eval_loss = 0.13998015224933624
+eval_runtime = 0.8129
+eval_samples_per_second = 1072.698
+eval_steps_per_second = 4.921

logs/events.out.tfevents.1649404000.algo-1.599.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17995c9299bf38f0a3b63ad4bc5497b6429e7a6b0754ab1b912ce0e426858715
-size 4844
+oid sha256:a4dd80f8f3c6acd0bbc9a5db8c9f6405f260d97c33faf61d6ace66b7026ead8d
+size 5678

logs/events.out.tfevents.1649404434.algo-1.599.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7211b3a05ba425a719d95d1596281328c893210d785c9712ac593daf3a85479d
+size 363

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ea7b1faf747506e2f89a277290821eeb36ed7c5aaa2c9aa2c497d5cc1c379b
+oid sha256:26b88613113fabd49aa922c4759d2c50e837073e8356e4e3609e8f7c1b5036f3
 size 1421613229