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: 0.8313
+- Loss: 1.3888
 - Accuracy: 0.9581
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.7117        | 1.0   | 96   | 0.6134          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0535        | 2.0   | 192  | 0.8084          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.9136        | 3.0   | 288  | 0.8313          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8606        | 1.0   | 96   | 0.7305          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0201        | 2.0   | 192  | 0.7517          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.4356        | 3.0   | 288  | 1.4165          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0234        | 4.0   | 384  | 0.9599          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.2795        | 5.0   | 480  | 1.0357          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.993         | 6.0   | 576  | 1.3888          | 0.9581   | 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 sha256:47ef6951f24521f44b4341ac530a13bc23e83777f93d94fb40f1ca4a373b5ca3
+oid sha256:f37445b5612c7cb1a7ab874f81227a2fa4559397c4267be6f9ebe6bcec481974
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4179142cb9dc85e1764c743bffa9aa74945ae00716cb8437a154f56255c8fcd6
+oid sha256:9f41cbc7f5f5812dcb7d242caa4c344dc00cbc65d72f961ea0cc1588b21a6024
 size 5432