End of training

README.md

@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6498
-- Accuracy: 0.8645
-- F1: 0.8634
-- Precision: 0.8632
-- Recall: 0.8645
-- Confusion Matrix: [[50, 8, 0, 2], [7, 53, 12, 0], [0, 8, 60, 0], [0, 0, 0, 73]]
+- Loss: 0.8806
+- Accuracy: 0.7912
+- F1: 0.7772
+- Precision: 0.8022
+- Recall: 0.7912
+- Confusion Matrix: [[59, 1, 1, 2], [20, 35, 22, 0], [2, 7, 68, 0], [2, 0, 0, 54]]
 
 ## Model description
 
@@ -45,7 +45,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 0.0005
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 123
@@ -55,10 +55,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: cosine_with_restarts
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 40
+- mixed_precision_training: Native AMP
 - label_smoothing_factor: 0.1
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Confusion Matrix                                               |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------------------------------------------------------------:|
+| 0.4221        | 22.2222 | 100  | 0.8806          | 0.7912   | 0.7772 | 0.8022    | 0.7912 | [[59, 1, 1, 2], [20, 35, 22, 0], [2, 7, 68, 0], [2, 0, 0, 54]] |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c75935ca7cf6cf2624c007d676c6f4095f4ab57f426f3d85e0a4fe5b16078bb
+oid sha256:8ed67b5dddd7135989bca50b2bd7f1ae2706bde9aeb37f094b6ce438d07d859b
 size 94765560

runs/Sep14_18-24-29_ubumarcos/events.out.tfevents.1726331984.ubumarcos

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fede9fcdd631a8ec2518ba9c9ab15f1bfc3400996d5c026e5f67af3e9fe841
-size 40
+oid sha256:71527561e8f8d63d6436dd8159aacdc49786cea9b70611de93c1c5a0660d6f4b
+size 512

runs/Sep14_18-40-38_ubumarcos/events.out.tfevents.1726332039.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbffbc8e18b2d2bf3799df9e1305693a95d6f801aebbbc37590a1b4ac54da438
+size 5942

runs/Sep14_18-41-24_ubumarcos/events.out.tfevents.1726332085.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adae7658de582025216a07ccf35e150aded54bd2d337878c512160cdcd098e6f
+size 11844

runs/Sep14_18-42-36_ubumarcos/events.out.tfevents.1726332157.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a984ef89202b728fd197d77f34ab76acf73692ffeca0b4b692c1e2bd5c8777
+size 7384

runs/Sep14_18-42-36_ubumarcos/events.out.tfevents.1726333536.ubumarcos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b07b123384b577ea63ef8948f79b92245ed743e50983ab48619a035f39a8464
+size 40

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8b55b425459f7b65521e542a14dc1670fa162e08d497ee83bde1c914e74cf6
+oid sha256:d9839bedd2577d45ec2d926afa2afaab029a2ce1f9a2a58e5d35aee8f2a8266b
 size 5240