Initial Commit

README.md

@@ -0,0 +1,102 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_full
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-kd-po-ner-full-mdeberta_data-univner_full55
+  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_full55
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_full](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2447
+- Precision: 0.8164
+- Recall: 0.8230
+- F1: 0.8197
+- 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: 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 1.1833        | 0.2911 | 500   | 0.6892          | 0.5129    | 0.4802 | 0.4960 | 0.9543   |
+| 0.5847        | 0.5822 | 1000  | 0.4874          | 0.6855    | 0.6350 | 0.6593 | 0.9673   |
+| 0.4508        | 0.8732 | 1500  | 0.4097          | 0.7055    | 0.7560 | 0.7299 | 0.9734   |
+| 0.373         | 1.1643 | 2000  | 0.3775          | 0.7500    | 0.7422 | 0.7460 | 0.9753   |
+| 0.3179        | 1.4554 | 2500  | 0.3419          | 0.7546    | 0.7756 | 0.7650 | 0.9768   |
+| 0.2999        | 1.7465 | 3000  | 0.3334          | 0.7713    | 0.8019 | 0.7863 | 0.9785   |
+| 0.2786        | 2.0375 | 3500  | 0.3187          | 0.7838    | 0.7883 | 0.7861 | 0.9789   |
+| 0.2448        | 2.3286 | 4000  | 0.3204          | 0.7932    | 0.7777 | 0.7854 | 0.9787   |
+| 0.2332        | 2.6197 | 4500  | 0.3065          | 0.8004    | 0.7833 | 0.7917 | 0.9790   |
+| 0.2267        | 2.9108 | 5000  | 0.2972          | 0.8025    | 0.8029 | 0.8027 | 0.9799   |
+| 0.2114        | 3.2019 | 5500  | 0.2948          | 0.7903    | 0.8046 | 0.7974 | 0.9794   |
+| 0.2006        | 3.4929 | 6000  | 0.2877          | 0.8131    | 0.8045 | 0.8088 | 0.9804   |
+| 0.1941        | 3.7840 | 6500  | 0.2819          | 0.8007    | 0.8018 | 0.8012 | 0.9801   |
+| 0.1885        | 4.0751 | 7000  | 0.2787          | 0.8008    | 0.8058 | 0.8033 | 0.9797   |
+| 0.1798        | 4.3662 | 7500  | 0.2821          | 0.8071    | 0.8061 | 0.8066 | 0.9800   |
+| 0.1768        | 4.6573 | 8000  | 0.2750          | 0.8046    | 0.8061 | 0.8053 | 0.9802   |
+| 0.1742        | 4.9483 | 8500  | 0.2706          | 0.7992    | 0.8231 | 0.8110 | 0.9804   |
+| 0.1651        | 5.2394 | 9000  | 0.2671          | 0.8192    | 0.8130 | 0.8161 | 0.9808   |
+| 0.1619        | 5.5305 | 9500  | 0.2680          | 0.8168    | 0.8097 | 0.8132 | 0.9807   |
+| 0.1616        | 5.8216 | 10000 | 0.2611          | 0.8121    | 0.8188 | 0.8154 | 0.9808   |
+| 0.1604        | 6.1126 | 10500 | 0.2614          | 0.8165    | 0.8074 | 0.8119 | 0.9808   |
+| 0.1542        | 6.4037 | 11000 | 0.2569          | 0.8110    | 0.8247 | 0.8178 | 0.9810   |
+| 0.1534        | 6.6948 | 11500 | 0.2598          | 0.8126    | 0.8152 | 0.8139 | 0.9810   |
+| 0.1507        | 6.9859 | 12000 | 0.2607          | 0.8216    | 0.8124 | 0.8170 | 0.9813   |
+| 0.1467        | 7.2770 | 12500 | 0.2531          | 0.8143    | 0.8227 | 0.8185 | 0.9811   |
+| 0.1455        | 7.5680 | 13000 | 0.2519          | 0.8229    | 0.8147 | 0.8188 | 0.9813   |
+| 0.1457        | 7.8591 | 13500 | 0.2524          | 0.8236    | 0.8152 | 0.8194 | 0.9811   |
+| 0.1454        | 8.1502 | 14000 | 0.2483          | 0.8179    | 0.8194 | 0.8187 | 0.9812   |
+| 0.1416        | 8.4413 | 14500 | 0.2478          | 0.8188    | 0.8248 | 0.8218 | 0.9814   |
+| 0.1419        | 8.7324 | 15000 | 0.2484          | 0.8224    | 0.8298 | 0.8261 | 0.9814   |
+| 0.1404        | 9.0234 | 15500 | 0.2482          | 0.8222    | 0.8201 | 0.8211 | 0.9812   |
+| 0.1406        | 9.3145 | 16000 | 0.2474          | 0.8227    | 0.8224 | 0.8226 | 0.9816   |
+| 0.1377        | 9.6056 | 16500 | 0.2448          | 0.8212    | 0.8211 | 0.8212 | 0.9815   |
+| 0.1401        | 9.8967 | 17000 | 0.2447          | 0.8164    | 0.8230 | 0.8197 | 0.9815   |
+
+
+### 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_full",
+  "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": 0.6515151515151515, "recall": 0.8775510204081632, "f1": 0.7478260869565216, "accuracy": 0.9776061776061776}, "en_pud": {"precision": 0.7810707456978967, "recall": 0.76, "f1": 0.7703913248467703, "accuracy": 0.9782300717793728}, "de_pud": {"precision": 0.7436619718309859, "recall": 0.7622714148219442, "f1": 0.752851711026616, "accuracy": 0.9738877689747316}, "pt_pud": {"precision": 0.8168402777777778, "recall": 0.8562329390354868, "f1": 0.8360728565082185, "accuracy": 0.9841500405861494}, "ru_pud": {"precision": 0.6722222222222223, "recall": 0.7007722007722008, "f1": 0.6862003780718338, "accuracy": 0.9693619219839835}, "sv_pud": {"precision": 0.8212180746561886, "recall": 0.8124392614188533, "f1": 0.8168050806057645, "accuracy": 0.9822814007129377}, "tl_trg": {"precision": 0.625, "recall": 0.8695652173913043, "f1": 0.7272727272727273, "accuracy": 0.9822888283378747}, "tl_ugnayan": {"precision": 0.55, "recall": 0.6666666666666666, "f1": 0.6027397260273972, "accuracy": 0.9690063810391978}, "zh_gsd": {"precision": 0.8027989821882952, "recall": 0.8226857887874837, "f1": 0.8126207340631035, "accuracy": 0.9757742257742258}, "zh_gsdsimp": {"precision": 0.8126614987080103, "recall": 0.8243774574049804, "f1": 0.8184775536759923, "accuracy": 0.9741924741924742}, "hr_set": {"precision": 0.8802228412256268, "recall": 0.9009265858873842, "f1": 0.8904543853469532, "accuracy": 0.9870981038746909}, "da_ddt": {"precision": 0.8412322274881516, "recall": 0.7941834451901566, "f1": 0.8170310701956272, "accuracy": 0.9857328145265889}, "en_ewt": {"precision": 0.8152069297401348, "recall": 0.7784926470588235, "f1": 0.7964268923366243, "accuracy": 0.9786030202813085}, "pt_bosque": {"precision": 0.8409461663947798, "recall": 0.848559670781893, "f1": 0.8447357640311347, "accuracy": 0.9854006665700623}, "sr_set": {"precision": 0.92, "recall": 0.9232585596221959, "f1": 0.9216263995285799, "accuracy": 0.9887050170738114}, "sk_snk": {"precision": 0.7766323024054983, "recall": 0.740983606557377, "f1": 0.7583892617449665, "accuracy": 0.9682003768844221}, "sv_talbanken": {"precision": 0.8390243902439024, "recall": 0.8775510204081632, "f1": 0.85785536159601, "accuracy": 0.997399028316239}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad55e94f5d1b9a6243bc6acec39856571bfc08c3712bf3f1b5b169053296c27c
+size 944366708

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bee3d7833d7d66415518fc44b3d66ac0fa59485a54d83b8f75fb782922dc425
+size 5304