End of training

README.md

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.2634
-- Validation Loss: 0.4040
-- Train Accuracy: 0.8125
+- Train Loss: 0.0140
+- Validation Loss: 0.4773
+- Train Accuracy: 0.8958
 - Epoch: 13
 
 ## Model description
@@ -43,25 +43,25 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Accuracy | Epoch |
 |:----------:|:---------------:|:--------------:|:-----:|
-| 0.7133     | 0.6935          | 0.5            | 0     |
-| 0.6888     | 0.6926          | 0.5            | 1     |
-| 0.7065     | 0.6924          | 0.5            | 2     |
-| 0.6875     | 0.6922          | 0.5            | 3     |
-| 0.6950     | 0.6918          | 0.5            | 4     |
-| 0.6945     | 0.6915          | 0.5            | 5     |
-| 0.6865     | 0.6899          | 0.7292         | 6     |
-| 0.6838     | 0.6877          | 0.7708         | 7     |
-| 0.6909     | 0.6825          | 0.8542         | 8     |
-| 0.6786     | 0.6691          | 0.8333         | 9     |
-| 0.5574     | 0.4069          | 0.8542         | 10    |
-| 0.4274     | 0.8131          | 0.6042         | 11    |
-| 0.4728     | 0.3997          | 0.7708         | 12    |
-| 0.2634     | 0.4040          | 0.8125         | 13    |
+| 0.1762     | 0.3984          | 0.875          | 0     |
+| 0.1873     | 0.3250          | 0.8542         | 1     |
+| 0.1339     | 0.4448          | 0.875          | 2     |
+| 0.0316     | 0.4015          | 0.8958         | 3     |
+| 0.0226     | 0.4410          | 0.875          | 4     |
+| 0.0166     | 0.4586          | 0.8958         | 5     |
+| 0.0157     | 0.4710          | 0.8958         | 6     |
+| 0.0113     | 0.4772          | 0.8958         | 7     |
+| 0.0159     | 0.4773          | 0.8958         | 8     |
+| 0.0105     | 0.4773          | 0.8958         | 9     |
+| 0.0119     | 0.4773          | 0.8958         | 10    |
+| 0.0120     | 0.4773          | 0.8958         | 11    |
+| 0.0135     | 0.4773          | 0.8958         | 12    |
+| 0.0140     | 0.4773          | 0.8958         | 13    |
 
 
 ### Framework versions
 
-- Transformers 4.27.3
-- TensorFlow 2.10.0
-- Datasets 2.10.1
-- Tokenizers 0.13.2
+- Transformers 4.28.1
+- TensorFlow 2.10.1
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -28,7 +28,7 @@
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.27.3",
+  "transformers_version": "4.28.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da391a6a0050764bee47bcb14079ab9a07d545e5c33b5eb23ff52b5a91f4e74e
+oid sha256:462b5892b19e7228c29f67ff27711984c5c69d8df7a8b4007a02f1691fbac3ce
 size 1112470336

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
-size 17082660
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -1,5 +1,6 @@
 {
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
@@ -13,7 +14,6 @@
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": null,
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }