Initial Commit

README.md

@@ -0,0 +1,89 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_en
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-kd-po-ner-full_data-univner_full66
+  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. -->
+
+# scenario-kd-po-ner-full_data-univner_full66
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4704
+- Precision: 0.7639
+- Recall: 0.7236
+- F1: 0.7432
+- Accuracy: 0.9788
+
+## 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: 3e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 66
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.9997        | 1.2755  | 500   | 0.7818          | 0.4929    | 0.4286 | 0.4585 | 0.9622   |
+| 0.4472        | 2.5510  | 1000  | 0.5948          | 0.6438    | 0.6398 | 0.6417 | 0.9734   |
+| 0.3048        | 3.8265  | 1500  | 0.5434          | 0.7053    | 0.6936 | 0.6994 | 0.9768   |
+| 0.2301        | 5.1020  | 2000  | 0.5331          | 0.7080    | 0.7205 | 0.7142 | 0.9768   |
+| 0.19          | 6.3776  | 2500  | 0.5176          | 0.7118    | 0.7236 | 0.7177 | 0.9766   |
+| 0.1622        | 7.6531  | 3000  | 0.5157          | 0.7330    | 0.7050 | 0.7187 | 0.9778   |
+| 0.1461        | 8.9286  | 3500  | 0.5090          | 0.7553    | 0.6967 | 0.7248 | 0.9775   |
+| 0.1331        | 10.2041 | 4000  | 0.4857          | 0.7558    | 0.7081 | 0.7312 | 0.9781   |
+| 0.123         | 11.4796 | 4500  | 0.5082          | 0.7566    | 0.7081 | 0.7316 | 0.9784   |
+| 0.1134        | 12.7551 | 5000  | 0.5113          | 0.7440    | 0.7008 | 0.7217 | 0.9775   |
+| 0.109         | 14.0306 | 5500  | 0.5122          | 0.7559    | 0.6925 | 0.7229 | 0.9773   |
+| 0.1045        | 15.3061 | 6000  | 0.4942          | 0.7362    | 0.7164 | 0.7261 | 0.9779   |
+| 0.1005        | 16.5816 | 6500  | 0.4817          | 0.7770    | 0.7143 | 0.7443 | 0.9794   |
+| 0.0967        | 17.8571 | 7000  | 0.4947          | 0.7642    | 0.7081 | 0.7351 | 0.9782   |
+| 0.094         | 19.1327 | 7500  | 0.4737          | 0.7527    | 0.7215 | 0.7368 | 0.9785   |
+| 0.0917        | 20.4082 | 8000  | 0.4815          | 0.7669    | 0.7153 | 0.7402 | 0.9786   |
+| 0.0889        | 21.6837 | 8500  | 0.4797          | 0.7783    | 0.7195 | 0.7477 | 0.9791   |
+| 0.0885        | 22.9592 | 9000  | 0.4824          | 0.7584    | 0.7215 | 0.7395 | 0.9783   |
+| 0.0866        | 24.2347 | 9500  | 0.4557          | 0.7630    | 0.7164 | 0.7389 | 0.9794   |
+| 0.0855        | 25.5102 | 10000 | 0.4618          | 0.7749    | 0.7236 | 0.7484 | 0.9797   |
+| 0.0851        | 26.7857 | 10500 | 0.4466          | 0.7641    | 0.7443 | 0.7541 | 0.9800   |
+| 0.0837        | 28.0612 | 11000 | 0.4526          | 0.7725    | 0.7381 | 0.7549 | 0.9795   |
+| 0.0834        | 29.3367 | 11500 | 0.4704          | 0.7639    | 0.7236 | 0.7432 | 0.9788   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_en",
+  "architectures": [
+    "DebertaForTokenClassificationKD"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.32710280373831774, "recall": 0.7142857142857143, "f1": 0.4487179487179487, "accuracy": 0.9281853281853282}, "en_pud": {"precision": 0.7364798426745329, "recall": 0.6967441860465117, "f1": 0.7160611854684512, "accuracy": 0.9730827351718927}, "de_pud": {"precision": 0.6587982832618026, "recall": 0.5909528392685275, "f1": 0.6230339928970066, "accuracy": 0.962027096713703}, "pt_pud": {"precision": 0.70625, "recall": 0.6169244767970883, "f1": 0.6585721223895095, "accuracy": 0.9655231341051822}, "ru_pud": {"precision": 0.5360501567398119, "recall": 0.4951737451737452, "f1": 0.5148018063221274, "accuracy": 0.9514337380521829}, "sv_pud": {"precision": 0.7566320645905421, "recall": 0.6375121477162293, "f1": 0.6919831223628691, "accuracy": 0.9691235059760956}, "tl_trg": {"precision": 0.2857142857142857, "recall": 0.6956521739130435, "f1": 0.4050632911392405, "accuracy": 0.9277929155313351}, "tl_ugnayan": {"precision": 0.273972602739726, "recall": 0.6060606060606061, "f1": 0.3773584905660377, "accuracy": 0.9361896080218779}, "zh_gsd": {"precision": 0.4166666666666667, "recall": 0.20860495436766624, "f1": 0.27801911381407474, "accuracy": 0.9069264069264069}, "zh_gsdsimp": {"precision": 0.43007915567282323, "recall": 0.21363040629095675, "f1": 0.28546409807355516, "accuracy": 0.9075091575091575}, "hr_set": {"precision": 0.6354166666666666, "recall": 0.5652173913043478, "f1": 0.5982648057336853, "accuracy": 0.9518136850783182}, "da_ddt": {"precision": 0.6771428571428572, "recall": 0.5302013422818792, "f1": 0.5947302383939775, "accuracy": 0.9708670058864611}, "en_ewt": {"precision": 0.7904483430799221, "recall": 0.7454044117647058, "f1": 0.7672658467360455, "accuracy": 0.977009204287365}, "pt_bosque": {"precision": 0.6593521421107628, "recall": 0.5193415637860083, "f1": 0.5810313075506446, "accuracy": 0.9572887987248225}, "sr_set": {"precision": 0.649867374005305, "recall": 0.5785123966942148, "f1": 0.6121174266083698, "accuracy": 0.9438753173977761}, "sk_snk": {"precision": 0.5450346420323325, "recall": 0.5158469945355191, "f1": 0.5300393037619315, "accuracy": 0.9336526381909548}, "sv_talbanken": {"precision": 0.7647058823529411, "recall": 0.7295918367346939, "f1": 0.7467362924281984, "accuracy": 0.9950925062570545}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b67f050bd2c9656479addfe58229a996661f27cd30b3f07ce132d9aaf0f4500
+size 944366708

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb73950b80a539f5d98b5eec0617db3bf6000378a9f888f056c92379099f3791
+size 5304