Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: bert-base-multilingual-cased
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: guj-eng-code-switch-bert-multilingual-data3
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# guj-eng-code-switch-bert-multilingual-data3
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0766
+- Precision: 0.9528
+- Recall: 0.9679
+- F1: 0.9603
+- Accuracy: 0.9815
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.167         | 1.0   | 247  | 0.1051          | 0.9109    | 0.9497 | 0.9299 | 0.9729   |
+| 0.0701        | 2.0   | 494  | 0.0791          | 0.9501    | 0.9684 | 0.9592 | 0.9803   |
+| 0.0487        | 3.0   | 741  | 0.0766          | 0.9528    | 0.9679 | 0.9603 | 0.9815   |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.9.0+cu126
+- Datasets 4.4.1
+- Tokenizers 0.22.1

config.json

@@ -0,0 +1,44 @@
+{
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-GUJ",
+    "2": "I-GUJ",
+    "3": "B-ENG",
+    "4": "I-ENG"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ENG": 3,
+    "B-GUJ": 1,
+    "I-ENG": 4,
+    "I-GUJ": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

logs/events.out.tfevents.1763828435.f0da10c9a12b.3876.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60804c4ed4da2276ac0d8675461f64bdd5bc45cab23c47811a1dcb2c7cbc666
+size 10387

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cefcadb823017cd5ab85d91a2f54757b13a87658aa4babffe6a91738c67674e
+size 709090132

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 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1910aa2b71c88d62cd3d4044b07137d939a4122dc42b4bf1746847d7668d83
+size 5969