fine_tuned_cb_croslo

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [EMBEDDIA/crosloengual-bert](https://huggingface.co/EMBEDDIA/crosloengual-bert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4661
-- Accuracy: 0.3182
-- F1: 0.1536
+- Loss: 0.5829
+- Accuracy: 0.8636
+- F1: 0.8452
 
 ## Model description
 
@@ -39,7 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.003
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -51,14 +51,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
-| 1.4444        | 3.5714  | 50   | 2.6262          | 0.3182   | 0.1536 |
-| 1.1504        | 7.1429  | 100  | 1.5617          | 0.3182   | 0.1536 |
-| 0.89          | 10.7143 | 150  | 1.9886          | 0.3182   | 0.1536 |
-| 0.794         | 14.2857 | 200  | 1.4233          | 0.3182   | 0.1536 |
-| 0.823         | 17.8571 | 250  | 2.1017          | 0.3182   | 0.1536 |
-| 0.7967        | 21.4286 | 300  | 1.3764          | 0.3182   | 0.1536 |
-| 0.7459        | 25.0    | 350  | 1.5568          | 0.3182   | 0.1536 |
-| 0.7448        | 28.5714 | 400  | 1.4661          | 0.3182   | 0.1536 |
+| 0.5945        | 3.5714  | 50   | 0.9554          | 0.4091   | 0.3208 |
+| 0.1464        | 7.1429  | 100  | 0.5574          | 0.8182   | 0.8024 |
+| 0.0128        | 10.7143 | 150  | 0.5869          | 0.8182   | 0.8024 |
+| 0.0036        | 14.2857 | 200  | 0.5764          | 0.8636   | 0.8452 |
+| 0.0024        | 17.8571 | 250  | 0.5659          | 0.8636   | 0.8452 |
+| 0.0018        | 21.4286 | 300  | 0.5763          | 0.8636   | 0.8452 |
+| 0.0015        | 25.0    | 350  | 0.5791          | 0.8636   | 0.8452 |
+| 0.0014        | 28.5714 | 400  | 0.5829          | 0.8636   | 0.8452 |
 
 
 ### Framework versions

config.json

@@ -31,6 +31,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.40.1",
   "type_vocab_size": 2,
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 49601
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1ebe9366efb480c4aeb13a06a986a0399be428400e5f464be06b0872a53836c
+oid sha256:5a93a970d6e09aea4300793258dc78f5376b1909c85402fefe470dee85ec18d9
 size 496572420

special_tokens_map.json

@@ -1,7 +1,37 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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
+  }
 }

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -47,12 +47,16 @@
   "do_lower_case": false,
   "mask_token": "[MASK]",
   "max_len": 512,
+  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
   "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]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8bf9812b3e1ac68b94ff19b344e83cea62417aca3d68f395f258d95e1abff1
+oid sha256:1d3f39ec1d1195a786276f7272ffcbab4296d1d20e3592ab8a6baf585f5bed45
 size 4984