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: 0.6186
+- Loss: 1.3130
 - Accuracy: 0.9471
 - 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
 
@@ -55,11 +56,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.5588        | 1.0   | 104  | 0.6212          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5413        | 2.0   | 208  | 0.6281          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.717         | 3.0   | 312  | 0.6173          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5122        | 4.0   | 416  | 0.6363          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.9325        | 5.0   | 520  | 0.6186          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4644        | 1.0   | 104  | 0.6159          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.3564        | 2.0   | 208  | 1.2336          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.287         | 3.0   | 312  | 0.7551          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.8016        | 4.0   | 416  | 0.9063          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.9181        | 5.0   | 520  | 0.8294          | 0.9471   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0308        | 6.0   | 624  | 1.3130          | 0.9471   | 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 sha256:3f3469de9ed0b33162292ee2ec7d7b14bd991f55c36e81ef997530cf1d664696
+oid sha256:cba0ae00708ee20fd5a656cf4676e65deb86cd8bcd6cf30f221ba6325d154960
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877a00ffc8a74f48daf692d8892d71b2f7416a03f0358f202a7d3dbb7ee93cb3
+oid sha256:b25a40df82a6282ed1ca7fc08996eaecb1713b9a22ef1ec3c18ac62cf4be7058
 size 5432