Initial Commit

README.md

@@ -0,0 +1,85 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_half
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-kd-po-ner-full-mdeberta_data-univner_half55
+  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-mdeberta_data-univner_half55
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_half](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_half) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 61.3798
+- Precision: 0.7820
+- Recall: 0.7775
+- F1: 0.7798
+- Accuracy: 0.9778
+
+## 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: 8
+- eval_batch_size: 32
+- seed: 55
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 134.7409      | 0.5828 | 500  | 105.3598        | 0.6084    | 0.4377 | 0.5091 | 0.9490   |
+| 96.012        | 1.1655 | 1000 | 90.6475         | 0.6858    | 0.7153 | 0.7003 | 0.9708   |
+| 85.0907       | 1.7483 | 1500 | 84.2206         | 0.7177    | 0.7448 | 0.7310 | 0.9739   |
+| 78.2732       | 2.3310 | 2000 | 79.7850         | 0.7312    | 0.7697 | 0.7500 | 0.9752   |
+| 73.6913       | 2.9138 | 2500 | 76.1999         | 0.7601    | 0.7527 | 0.7564 | 0.9760   |
+| 69.7676       | 3.4965 | 3000 | 73.2988         | 0.7666    | 0.7575 | 0.7620 | 0.9765   |
+| 66.6414       | 4.0793 | 3500 | 70.8495         | 0.7711    | 0.7563 | 0.7636 | 0.9766   |
+| 64.0181       | 4.6620 | 4000 | 68.8880         | 0.7808    | 0.7560 | 0.7682 | 0.9770   |
+| 61.881        | 5.2448 | 4500 | 67.1248         | 0.7702    | 0.7703 | 0.7703 | 0.9771   |
+| 60.1233       | 5.8275 | 5000 | 65.7057         | 0.7849    | 0.7521 | 0.7681 | 0.9766   |
+| 58.4747       | 6.4103 | 5500 | 64.4473         | 0.7744    | 0.7736 | 0.7740 | 0.9774   |
+| 57.511        | 6.9930 | 6000 | 63.5221         | 0.7731    | 0.7808 | 0.7770 | 0.9776   |
+| 56.432        | 7.5758 | 6500 | 62.8477         | 0.7803    | 0.7723 | 0.7763 | 0.9776   |
+| 55.7061       | 8.1585 | 7000 | 62.2029         | 0.7715    | 0.7794 | 0.7754 | 0.9776   |
+| 55.1513       | 8.7413 | 7500 | 61.7137         | 0.7808    | 0.7797 | 0.7802 | 0.9783   |
+| 54.7004       | 9.3240 | 8000 | 61.5394         | 0.7824    | 0.7817 | 0.7820 | 0.9782   |
+| 54.5449       | 9.9068 | 8500 | 61.3798         | 0.7820    | 0.7775 | 0.7798 | 0.9778   |
+
+
+### 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_half",
+  "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": 0.4794520547945205, "recall": 0.7142857142857143, "f1": 0.5737704918032787, "accuracy": 0.9606177606177606}, "en_pud": {"precision": 0.7709707822808671, "recall": 0.7609302325581395, "f1": 0.7659176029962548, "accuracy": 0.9775689459765773}, "de_pud": {"precision": 0.7391304347826086, "recall": 0.7362848893166506, "f1": 0.7377049180327868, "accuracy": 0.9730908068069946}, "pt_pud": {"precision": 0.7661870503597122, "recall": 0.7752502274795269, "f1": 0.7706919945725915, "accuracy": 0.9776562566753535}, "ru_pud": {"precision": 0.6534195933456562, "recall": 0.6824324324324325, "f1": 0.667610953729934, "accuracy": 0.9671919400671661}, "sv_pud": {"precision": 0.8121272365805169, "recall": 0.793974732750243, "f1": 0.802948402948403, "accuracy": 0.9806039001887188}, "tl_trg": {"precision": 0.4482758620689655, "recall": 0.5652173913043478, "f1": 0.4999999999999999, "accuracy": 0.9673024523160763}, "tl_ugnayan": {"precision": 0.5106382978723404, "recall": 0.7272727272727273, "f1": 0.5999999999999999, "accuracy": 0.96718322698268}, "zh_gsd": {"precision": 0.8, "recall": 0.7926988265971316, "f1": 0.796332678454486, "accuracy": 0.9735264735264735}, "zh_gsdsimp": {"precision": 0.8057742782152231, "recall": 0.8047182175622543, "f1": 0.8052459016393442, "accuracy": 0.9744422244422244}, "hr_set": {"precision": 0.8626110731373889, "recall": 0.8995010691375623, "f1": 0.8806699232379623, "accuracy": 0.9859439406430338}, "da_ddt": {"precision": 0.7753086419753087, "recall": 0.7024608501118568, "f1": 0.7370892018779341, "accuracy": 0.9802454354983537}, "en_ewt": {"precision": 0.8057692307692308, "recall": 0.7702205882352942, "f1": 0.7875939849624061, "accuracy": 0.9787225564808543}, "pt_bosque": {"precision": 0.7489102005231038, "recall": 0.7069958847736626, "f1": 0.7273497036409823, "accuracy": 0.9737356904796406}, "sr_set": {"precision": 0.9015240328253223, "recall": 0.9079102715466352, "f1": 0.9047058823529412, "accuracy": 0.9855529288153402}, "sk_snk": {"precision": 0.7052980132450332, "recall": 0.6983606557377049, "f1": 0.7018121911037891, "accuracy": 0.9613693467336684}, "sv_talbanken": {"precision": 0.7916666666666666, "recall": 0.8724489795918368, "f1": 0.8300970873786407, "accuracy": 0.9969573538793738}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966f5a05575fccc1caeff3851ef1923b33251163c7e7582bb55e8f568e50347b
+size 944366708

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a846d7263d31df179c277ac6671598ab91331609384cc03867aab88c6e1f68c
+size 5304