End of training

README.md

@@ -0,0 +1,81 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: MiniLMv2-L6-H768-sst2
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: glue
+      type: glue
+      args: sst2
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9426605504587156
+---
+
+<!-- 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. -->
+
+# MiniLMv2-L6-H768-sst2
+
+This model is a fine-tuned version of [nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L6-H768-distilled-from-RoBERTa-Large) on the glue dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2013
+- Accuracy: 0.9427
+
+## 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: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.4734        | 1.0   | 264  | 0.2046          | 0.9243   |
+| 0.2399        | 2.0   | 528  | 0.1912          | 0.9346   |
+| 0.1791        | 3.0   | 792  | 0.1943          | 0.9335   |
+| 0.1442        | 4.0   | 1056 | 0.2103          | 0.9369   |
+| 0.1217        | 5.0   | 1320 | 0.2013          | 0.9427   |
+
+
+### 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 = 5.0
+eval_accuracy = 0.9426605504587156
+eval_loss = 0.20133036375045776
+eval_runtime = 0.4843
+eval_samples_per_second = 1800.415
+eval_steps_per_second = 8.259

logs/events.out.tfevents.1649426083.algo-1.543.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988178e8eb282775088c547dceb9d9dbdf08a5425b3d44b9ed12592e20da7653
-size 5864
+oid sha256:089f1a0c70974cef16b51702809c4cbd0858359acf7ba355a82448478be5950b
+size 6218

logs/events.out.tfevents.1649426235.algo-1.543.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6963b462578ca59733f727696b69142d9c9896127045fcc545491ef34952e13
+size 363