bert-russian

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: Priyanka-Balivada/bert-3-epoch-sentiment
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # russian-BERT
 
-This model is a fine-tuned version of [Priyanka-Balivada/bert-3-epoch-sentiment](https://huggingface.co/Priyanka-Balivada/bert-3-epoch-sentiment) on the None dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0910
-- Accuracy: 0.869
-- Precision: 0.8687
-- Recall: 0.869
-- Micro-avg-recall: 0.869
-- Micro-avg-precision: 0.869
+- Loss: 0.8570
+- Accuracy: 0.8753
+- Precision: 0.8754
+- Recall: 0.8753
+- Micro-avg-recall: 0.8753
+- Micro-avg-precision: 0.8753
 
 ## Model description
 
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Micro-avg-recall | Micro-avg-precision |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:----------------:|:-------------------:|
-| 0.1014        | 1.0   | 750  | 0.8994          | 0.845    | 0.8457    | 0.845  | 0.845            | 0.845               |
-| 0.1351        | 2.0   | 1500 | 1.0207          | 0.858    | 0.8629    | 0.858  | 0.858            | 0.858               |
-| 0.0001        | 3.0   | 2250 | 1.1304          | 0.8563   | 0.8566    | 0.8563 | 0.8563           | 0.8563              |
-| 0.0733        | 4.0   | 3000 | 1.0855          | 0.862    | 0.8624    | 0.862  | 0.862            | 0.862               |
-| 0.0005        | 5.0   | 3750 | 1.0910          | 0.869    | 0.8687    | 0.869  | 0.869            | 0.869               |
+| 0.0736        | 1.0   | 750  | 0.6635          | 0.8743   | 0.8750    | 0.8743 | 0.8743           | 0.8743              |
+| 0.1031        | 2.0   | 1500 | 0.7665          | 0.8753   | 0.8761    | 0.8753 | 0.8753           | 0.8753              |
+| 0.0008        | 3.0   | 2250 | 0.7654          | 0.8813   | 0.8817    | 0.8813 | 0.8813           | 0.8813              |
+| 0.0007        | 4.0   | 3000 | 0.8571          | 0.8737   | 0.8742    | 0.8737 | 0.8737           | 0.8737              |
+| 0.079         | 5.0   | 3750 | 0.8570          | 0.8753   | 0.8754    | 0.8753 | 0.8753           | 0.8753              |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Priyanka-Balivada/bert-3-epoch-sentiment",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d2de9b23217763abe94c7f93a9041878b44e17d77fc84948104053fe6d070e
+oid sha256:411d98db74587ed4ec6e8071bfe5d73b8861c7ec84fc1f0747958f419ba4bcf2
 size 437961724

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -45,15 +45,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }