End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/rembert](https://huggingface.co/google/rembert) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6510
+- Loss: 0.6585
 - Accuracy: 0.9371
 - 1-f1: 0.0
 - 1-recall: 0.0
@@ -48,6 +48,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.06
 - num_epochs: 20
 - mixed_precision_training: Native AMP
 
@@ -55,9 +56,21 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.43          | 1.0   | 124  | 0.6327          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5814        | 2.0   | 248  | 0.6407          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5448        | 3.0   | 372  | 0.6510          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.1819        | 1.0   | 124  | 0.6633          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4154        | 2.0   | 248  | 0.6913          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.6373        | 3.0   | 372  | 0.6449          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4658        | 4.0   | 496  | 0.6969          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.0914        | 5.0   | 620  | 0.7048          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3045        | 6.0   | 744  | 0.6476          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7046        | 7.0   | 868  | 0.6569          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3645        | 8.0   | 992  | 0.6368          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.2303        | 9.0   | 1116 | 0.6604          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.5905        | 10.0  | 1240 | 0.6307          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3306        | 11.0  | 1364 | 0.6332          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.2381        | 12.0  | 1488 | 0.6957          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4752        | 13.0  | 1612 | 0.6574          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.6578        | 14.0  | 1736 | 0.6515          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.5788        | 15.0  | 1860 | 0.6585          | 0.9371   | 0.0  | 0.0      | 0.0         | 0.5          |
 
 
 ### Framework versions

config.json

@@ -3,14 +3,14 @@
   "architectures": [
     "RemBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0,
+  "attention_probs_dropout_prob": 0.2,
   "bos_token_id": 312,
   "classifier_dropout_prob": 0.1,
   "embedding_dropout_prob": 0,
   "embedding_size": 256,
   "eos_token_id": 313,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 1152,
   "initializer_range": 0.02,
   "input_embedding_size": 256,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56122c57aa8d627a36964236181554bf52ea2ba6155b05e7c4d153bb18466979
+oid sha256:0b52f41c648258bd622d718cbcaf1bffb87fa8a1337137e59c55befc099fcc4f
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ffd96c5575bea43da45d8e91344327c9849a763e54fade752033eb95639db1c
+oid sha256:88a93aef96e9be89c74acfbe31c0156c8ffbc475055ec6cf913d66c99f78d9c9
 size 5432