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: 0.8421
+- Loss: 0.8476
 - Accuracy: 0.9658
 - 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 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.0298        | 1.0   | 212  | 0.8023          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 1.5391        | 2.0   | 424  | 0.7184          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.4833        | 3.0   | 636  | 0.5257          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0248        | 4.0   | 848  | 0.8640          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.0248        | 5.0   | 1060 | 0.8421          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0311        | 1.0   | 212  | 0.4956          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 1.7774        | 2.0   | 424  | 0.6162          | 0.9658   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.6774        | 3.0   | 636  | 0.8476          | 0.9658   | 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:acaaad5f613cac7c2b5c629c75bfac72c6a297e978afa2d93559fce35b5297ce
+oid sha256:3eb94d82ae436feb88d04f2cec46eb8719283d15f2297a43d6c3dffc0c7bd66c
 size 2303755328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea00ddca9b4c8260088a2379df40dc659175fec5590f00decc7ea23cc886e039
+oid sha256:2f43d552e5b42a902a33886ea332b1c209eed2b801b77d8175d7ffd2e16726be
 size 5432