Model save

README.md

@@ -0,0 +1,84 @@
+---
+library_name: transformers
+base_model: OMRIDRORI/mbert-tibetan-continual-unicode-240k
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tibetan_code_switching_model
+  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. -->
+
+# tibetan_code_switching_model
+
+This model is a fine-tuned version of [OMRIDRORI/mbert-tibetan-continual-unicode-240k](https://huggingface.co/OMRIDRORI/mbert-tibetan-continual-unicode-240k) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2587
+- Accuracy: 0.9580
+- Switch Precision: 0.9386
+- Switch Recall: 0.9817
+- Switch F1: 0.9596
+- True Switches: 109
+- Pred Switches: 114
+- Tp: 107
+- Fp: 7
+- Fn: 2
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 15
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Switch Precision | Switch Recall | Switch F1 | True Switches | Pred Switches | Tp  | Fp  | Fn |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------------:|:-------------:|:---------:|:-------------:|:-------------:|:---:|:---:|:--:|
+| 4.4519        | 1.0   | 50   | 4.8563          | 0.2905   | 0.0906           | 0.9083        | 0.1647    | 109           | 1093          | 99  | 994 | 10 |
+| 2.0058        | 2.0   | 100  | 1.4230          | 0.5367   | 0.5376           | 0.9174        | 0.6780    | 109           | 186           | 100 | 86  | 9  |
+| 1.249         | 3.0   | 150  | 1.0507          | 0.6400   | 0.6429           | 0.9908        | 0.7798    | 109           | 168           | 108 | 60  | 1  |
+| 0.885         | 4.0   | 200  | 0.8003          | 0.7341   | 0.6488           | 1.0           | 0.7870    | 109           | 168           | 109 | 59  | 0  |
+| 0.734         | 5.0   | 250  | 0.7127          | 0.7770   | 0.6606           | 1.0           | 0.7956    | 109           | 165           | 109 | 56  | 0  |
+| 0.5639        | 6.0   | 300  | 0.6443          | 0.8205   | 0.6728           | 1.0           | 0.8044    | 109           | 162           | 109 | 53  | 0  |
+| 0.3557        | 7.0   | 350  | 0.3794          | 0.9025   | 0.7219           | 1.0           | 0.8385    | 109           | 151           | 109 | 42  | 0  |
+| 0.249         | 8.0   | 400  | 0.2706          | 0.9363   | 0.8120           | 0.9908        | 0.8926    | 109           | 133           | 108 | 25  | 1  |
+| 0.1682        | 9.0   | 450  | 0.2421          | 0.9344   | 0.9              | 0.9908        | 0.9432    | 109           | 120           | 108 | 12  | 1  |
+| 0.0818        | 10.0  | 500  | 0.2537          | 0.9368   | 0.8689           | 0.9725        | 0.9177    | 109           | 122           | 106 | 16  | 3  |
+| 0.0632        | 11.0  | 550  | 0.3495          | 0.9426   | 0.8917           | 0.9817        | 0.9345    | 109           | 120           | 107 | 13  | 2  |
+| 0.0227        | 12.0  | 600  | 0.2392          | 0.9537   | 0.9304           | 0.9817        | 0.9554    | 109           | 115           | 107 | 8   | 2  |
+| 0.0246        | 13.0  | 650  | 0.3026          | 0.9488   | 0.8843           | 0.9817        | 0.9304    | 109           | 121           | 107 | 14  | 2  |
+| 0.0146        | 14.0  | 700  | 0.2463          | 0.9604   | 0.9386           | 0.9817        | 0.9596    | 109           | 114           | 107 | 7   | 2  |
+| 0.0178        | 15.0  | 750  | 0.2587          | 0.9580   | 0.9386           | 0.9817        | 0.9596    | 109           | 114           | 107 | 7   | 2  |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.4.1+cu121
+- Datasets 2.0.0
+- Tokenizers 0.20.3

final_model/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "OMRIDRORI/mbert-tibetan-continual-unicode-240k",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "non_switch_auto",
+    "1": "non_switch_allo",
+    "2": "to_auto",
+    "3": "to_allo"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "non_switch_allo": 1,
+    "non_switch_auto": 0,
+    "to_allo": 3,
+    "to_auto": 2
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf1b1a3889be2747c6052177d7bd7e1dd831be1fa5fbed7b0ca700fec2b5a4b
+size 709087056

final_model/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "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
+  }
+}

final_model/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]"
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9fb47a1b9e042c718e44870c1361222e36ba6ae11efa25444ce8a3e43c2492
+size 5240