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 [AnonymousCS/populism_xlmr_large](https://huggingface.co/AnonymousCS/populism_xlmr_large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5793
+- Loss: 0.2072
 - Accuracy: 0.9581
 - 1-f1: 0.0
 - 1-recall: 0.0
@@ -42,9 +42,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 64
-- eval_batch_size: 64
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
 - 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
@@ -55,15 +55,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1 | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:----:|:--------:|:-----------:|:------------:|
-| 0.6997        | 1.0   | 24   | 0.5882          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5428        | 2.0   | 48   | 0.5808          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6787        | 3.0   | 72   | 0.5793          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.7025        | 4.0   | 96   | 0.5798          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.6538        | 5.0   | 120  | 0.5792          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.676         | 6.0   | 144  | 0.5793          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.4549        | 7.0   | 168  | 0.5791          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5427        | 8.0   | 192  | 0.5802          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
-| 0.5667        | 9.0   | 216  | 0.5793          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.4109        | 1.0   | 96   | 0.2241          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0126        | 2.0   | 192  | 0.2105          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3376        | 3.0   | 288  | 0.2040          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0187        | 4.0   | 384  | 0.1921          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.3191        | 5.0   | 480  | 0.2003          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.173         | 6.0   | 576  | 0.2228          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
+| 0.0172        | 7.0   | 672  | 0.2072          | 0.9581   | 0.0  | 0.0      | 0.0         | 0.5          |
 
 
 ### Framework versions

config.json

@@ -3,12 +3,12 @@
   "architectures": [
     "XLMRobertaForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0.2,
   "bos_token_id": 0,
-  "classifier_dropout": null,
+  "classifier_dropout": 0.2,
   "eos_token_id": 2,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "hidden_dropout_prob": 0.2,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53cfe6545576bd7552f5ff704dc26222d8e45494b78a8d7600500b5d0dffb372
+oid sha256:7215806bc2afef900a2be9a2eba55c23ca31bb27ff70065db9cc900874c3f46a
 size 2239618672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac14b7c59eb8b949cb4061316fcc01638d62653ffd8a67703ed2be70fef2e30d
+oid sha256:00cd2c8a48c6f0fbfa8a3c197f14b7bfc1d67a9c35e66d3995274beb8897be0d
 size 5432