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: 0.6684
+- Loss: 0.6802
 - Accuracy: 0.9332
 - 1-f1: 0.0
 - 1-recall: 0.0
@@ -48,20 +48,24 @@ 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
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.7055        | 1.0   | 101  | 0.6621          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6021        | 2.0   | 202  | 0.6646          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.8043        | 3.0   | 303  | 0.6611          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.7283        | 4.0   | 404  | 0.6673          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6756        | 5.0   | 505  | 0.6608          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6906        | 6.0   | 606  | 0.6643          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.3813        | 7.0   | 707  | 0.6684          | 0.9332   | 0.0  | 0.0      | 0.0         | 0.5          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
+| 0.6586        | 1.0   | 101  | 0.6708          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.4749        | 2.0   | 202  | 0.6684          | 0.3416   | 0.1364 | 0.7778   | 0.0747      | 0.5441       |
+| 1.4489        | 3.0   | 303  | 0.6667          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.9142        | 4.0   | 404  | 0.6887          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.6597        | 5.0   | 505  | 0.6467          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.6488        | 6.0   | 606  | 0.6644          | 0.9084   | 0.0    | 0.0      | 0.0         | 0.4867       |
+| 0.246         | 7.0   | 707  | 0.6945          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.67          | 8.0   | 808  | 0.6916          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.8424        | 9.0   | 909  | 0.7135          | 0.9332   | 0.0    | 0.0      | 0.0         | 0.5          |
+| 0.7539        | 10.0  | 1010 | 0.6802          | 0.9332   | 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 sha256:595b2afac99c296c44595703b66a0fc1d3ab48b241ad30d112999b70b9ccaad0
+oid sha256:d0d57c86f9a21cc9b150c0f2608208faa547075f30ffd207950e29b200e2f65a
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cf93e8423da1f8fd0bdfff678de5e9b652139abfaba59a254318e2fb6c9af1
+oid sha256:f4d9db72eb4f011ea3bbd8e1e8287602f392d8d084a90d3b67131fd951669b9c
 size 5432