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: 0.5634
+- Loss: 0.9274
 - Accuracy: 0.9523
 - 1-f1: 0.0
 - 1-recall: 0.0
@@ -43,24 +43,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 32
+- eval_batch_size: 32
 - 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 |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.0854        | 1.0   | 3484  | 0.6875          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6854        | 2.0   | 6968  | 0.5804          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.4985        | 3.0   | 10452 | 0.5638          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.2701        | 4.0   | 13936 | 0.5563          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5109        | 5.0   | 17420 | 0.6045          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.3593        | 6.0   | 20904 | 0.5634          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
+| 0.5276        | 1.0   | 1742 | 0.6361          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7348        | 2.0   | 3484 | 0.5889          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.7628        | 3.0   | 5226 | 0.7668          | 0.9523   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4249        | 4.0   | 6968 | 0.9274          | 0.9523   | 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 sha256:8b6988deee84ff7362d63e74cf1a4c1782b36c64596186b6e533e889132c098e
+oid sha256:789a88d3170f54db728ccf58b94770c776ef5b2fd7ce471e3be1438ea1206a0d
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5107552f55756bdf5532cf65ccbb37033a211317674f60261757861e3ba1cc9
+oid sha256:ec7c8882c40ad8d9cd8d18bf952415c932d735306755b7b7976da19753a3b14f
 size 5432