mbert-som

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google-bert/bert-base-multilingual-cased
+base_model: google-bert/bert-base-multilingual-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -14,9 +14,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # som
 
-This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3424
+- Loss: 0.3043
+- F1-micro: 0.1964
+- F1-macro: 0.0818
 
 ## Model description
 
@@ -35,22 +37,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
+- learning_rate: 3e-05
 - train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 33
 - num_epochs: 4
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 85   | 0.3474          |
-| No log        | 2.0   | 170  | 0.3450          |
-| No log        | 3.0   | 255  | 0.3426          |
-| No log        | 4.0   | 340  | 0.3424          |
+| Training Loss | Epoch | Step | Validation Loss | F1-micro | F1-macro |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
+| 0.428         | 1.0   | 85   | 0.3427          | 0.0      | 0.0      |
+| 0.3365        | 2.0   | 170  | 0.3249          | 0.0      | 0.0      |
+| 0.3146        | 3.0   | 255  | 0.3108          | 0.0898   | 0.0476   |
+| 0.2924        | 4.0   | 340  | 0.3043          | 0.1964   | 0.0818   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -44,5 +44,5 @@
   "transformers_version": "4.44.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 119547
+  "vocab_size": 105879
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f11612dbdf03439ccf96bdadbb86630cbce0a5f84ff73135d84c96e06495926e
-size 711455760
+oid sha256:fb078ac4697b1c1d492d4792583638ee05a5ce053078627c25f08183a674c7ca
+size 669467664

runs/Jan13_12-06-52_c43d02b615eb/events.out.tfevents.1736770013.c43d02b615eb.40.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad925430145960a6b5bcc6027fe45327e76c6d9f5a00f9e407138e231f7b86c
+size 8028

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6937524f0dbb320d7be431fb771d68ca3e4588b08ab473cca4c987cc10211679
+oid sha256:95bd678d0a9cfd5241f581603fc91ef56d7c401687de30a9de49b3c36c6914b4
 size 5176