End of training

README.md

@@ -3,8 +3,6 @@ license: apache-2.0
 base_model: google/bert_uncased_L-2_H-128_A-2
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: tiny-bert-sst2-distilled
   results: []
@@ -17,8 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5066
-- Accuracy: 0.8165
+- eval_loss: 0.4358
+- eval_accuracy: 0.7984
+- eval_recall: 0.9335
+- eval_precision: 0.7350
+- eval_f1: 0.8224
+- eval_runtime: 30.8207
+- eval_samples_per_second: 33.16
+- eval_steps_per_second: 1.038
+- epoch: 2.0
+- step: 192
 
 ## Model description
 
@@ -37,23 +43,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.00015135649079170115
-- train_batch_size: 128
-- eval_batch_size: 128
+- learning_rate: 0.00020749603056740112
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 33
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.235         | 1.0   | 527  | 1.2949          | 0.8417   |
-| 0.565         | 2.0   | 1054 | 1.4198          | 0.8303   |
-| 0.4043        | 3.0   | 1581 | 1.5066          | 0.8165   |
-
+- num_epochs: 7
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:419986f87659b65247fdff0e0c36b70fb5c6a2a3dcf2ae0b1384ca611734efed
+oid sha256:a3a75025dd9c90072121cfb7257778cf348e210687840eb3a50bf108d16c101c
 size 17549312