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: 0.6031
+- Loss: 0.9330
 - Accuracy: 0.9588
 - 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 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.4638        | 1.0   | 97   | 0.5629          | 0.9588   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.197         | 2.0   | 194  | 0.5801          | 0.9588   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.8193        | 3.0   | 291  | 0.6031          | 0.9588   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8271        | 1.0   | 97   | 0.5781          | 0.9588   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0213        | 2.0   | 194  | 1.1170          | 0.9588   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.7847        | 3.0   | 291  | 0.9330          | 0.9588   | 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:b521fc6a768a7cfed5b209e8aa292bc9d2cf950ae5850c2608c0a45850765859
+oid sha256:3afe58e27ce7acb114c2aff227485248bc04c77c24bee719e670f10755bf5d6d
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f3eb0e1a5c56a73127b359fba2d37d211a98ad0b95262d4c32529a22a03f18
+oid sha256:fa3df537443007c81f5491eebc180fef7cb7fd4411f0f3b4986da4b96bf19799
 size 5432