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: 0.6077
+- Loss: 1.0316
 - Accuracy: 0.9475
 - 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 +56,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.6724        | 1.0   | 167  | 0.6042          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5698        | 2.0   | 334  | 0.6119          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5147        | 3.0   | 501  | 0.6077          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7657        | 1.0   | 167  | 0.5924          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3731        | 2.0   | 334  | 0.5964          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7384        | 3.0   | 501  | 0.7634          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.9117        | 4.0   | 668  | 0.7163          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7798        | 5.0   | 835  | 1.1236          | 0.9475   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8696        | 6.0   | 1002 | 1.0316          | 0.9475   | 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:e6a3ef04d14382bf86f97f7d8568b43059ec09964fcdd34f82a0409e52f03838
+oid sha256:badc3092dc3a68593d5a0ac32dbf94f14bf68f69911ef69ac69b29d2885de917
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87330e2d07daf9b3762259bfd72761b690a9cff6eb77b316af4416e7fe51338d
+oid sha256:d8189286bf27d78a2cb2f5926726b4ab113dff30d6a2dbb163707c0519751eeb
 size 5432