End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: mit
-base_model: FacebookAI/xlm-roberta-base
+base_model: FacebookAI/xlm-roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -16,14 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # populism_classifier_105
 
-This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the None dataset.
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6883
-- Accuracy: 0.9412
-- 1-f1: 0.5085
-- 1-recall: 0.4839
-- 1-precision: 0.5357
-- Balanced Acc: 0.7279
+- Loss: 0.5066
+- Accuracy: 0.9602
+- 1-f1: 0.6365
+- 1-recall: 0.7293
+- 1-precision: 0.5646
+- Balanced Acc: 0.8506
 
 ## Model description
 
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | 1-f1   | 1-recall | 1-precision | Balanced Acc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------:|:-----------:|:------------:|
-| 0.2713        | 1.0   | 16   | 0.2399          | 0.8925   | 0.5310 | 0.9677   | 0.3659      | 0.9276       |
-| 0.1188        | 2.0   | 32   | 0.1922          | 0.9249   | 0.6105 | 0.9355   | 0.4531      | 0.9299       |
-| 0.1791        | 3.0   | 48   | 0.1927          | 0.9087   | 0.5714 | 0.9677   | 0.4054      | 0.9363       |
-| 0.2754        | 4.0   | 64   | 0.6883          | 0.9412   | 0.5085 | 0.4839   | 0.5357      | 0.7279       |
+| 0.0683        | 1.0   | 1742 | 0.3066          | 0.9614   | 0.5991 | 0.6045   | 0.5938      | 0.7919       |
+| 0.3732        | 2.0   | 3484 | 0.2559          | 0.9332   | 0.5530 | 0.8662   | 0.4062      | 0.9014       |
+| 0.0593        | 3.0   | 5226 | 0.4048          | 0.9637   | 0.6312 | 0.6511   | 0.6124      | 0.8152       |
+| 0.0033        | 4.0   | 6968 | 0.5066          | 0.9602   | 0.6365 | 0.7293   | 0.5646      | 0.8506       |
 
 
 ### Framework versions

config.json

@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43e57d534ff33ad0b22a252b7818e98d6ffb263fa7e780df495205050ba27c66
-size 1112205008
+oid sha256:ad3b320fe2eabadd7a560f2a066e3c7d43b6d76654e687e25e176e11f0883881
+size 2239618672

runs/Aug26_02-53-08_d387e51826a2/events.out.tfevents.1756176791.d387e51826a2.4133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8972c2f07604d2e8e46fe32ab83e29c35003d20c5b35fe1bbe84cfc33430abb4
+size 5015

runs/Aug26_02-54-02_d387e51826a2/events.out.tfevents.1756176843.d387e51826a2.4133.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398cc2e8f7e4f47db93bc86bc71b9f5eb8266ee1f30bbf6c162ec628f27ad127
+size 5013

runs/Aug26_02-55-12_d387e51826a2/events.out.tfevents.1756176913.d387e51826a2.4133.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d540baf7a595587d2fa1a6095415f76bf1d9252e4a7754ce7b7c24b9317206d5
+size 742375

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7808e7225a88dede6ddad4f6afc1e4ef04a2b262488699ec50060703f24aa78e
+oid sha256:c74fcc93b9b59b2c431adad56a979086c431f386bdb0b4595c7223a1ea8a36af
 size 5777