Training completed!

README.md

@@ -1,5 +1,6 @@
 ---
 license: mit
+base_model: xlm-roberta-base
 tags:
 - generated_from_trainer
 datasets:
@@ -21,7 +22,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.8340325557979527
+      value: 0.8472175379426645
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +32,8 @@ should 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 the xtreme dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2723
-- F1: 0.8340
+- Loss: 0.2827
+- F1: 0.8472
 
 ## Model description
 
@@ -63,14 +64,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.5909        | 1.0   | 191  | 0.3404          | 0.7891 |
-| 0.2594        | 2.0   | 382  | 0.2919          | 0.8152 |
-| 0.1752        | 3.0   | 573  | 0.2723          | 0.8340 |
+| 0.5561        | 1.0   | 191  | 0.3632          | 0.7653 |
+| 0.2608        | 2.0   | 382  | 0.2838          | 0.8290 |
+| 0.1772        | 3.0   | 573  | 0.2827          | 0.8472 |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
-- Pytorch 1.13.1+cu116
-- Datasets 2.10.1
-- Tokenizers 0.13.2
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "</s>": 2,
+  "<mask>": 250001,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}

config.json

@@ -40,7 +40,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.34.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5298e707ccbd24ecca195326831b1288de324878fea3627bb19822b952fe4ffa
-size 1109909549
+oid sha256:5a3b0d175206a9ac544a7b63a71857fdb69fc4ab6688cabac8962722b63a52a6
+size 1109905129

special_tokens_map.json

@@ -2,13 +2,7 @@
   "bos_token": "<s>",
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "unk_token": "<unk>"

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:003498ab0695fbf35aedc8bbbae1e20a6033a1b3914e49c6d2fbe1d54d7d93b9
+size 17082786

tokenizer_config.json

@@ -1,20 +1,55 @@
 {
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "name_or_path": "xlm-roberta-base",
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "special_tokens_map_file": null,
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e6a055aff141d5618d398801e1facd651a02db792a5942822bf1924dc24221f
-size 3579
+oid sha256:6881439bb2616415788e4126cf57b04e5b6da73f17670f492aaf55c86cca7c6f
+size 4155