Initial Commit

README.md

@@ -0,0 +1,95 @@
+---
+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-non-kd-pre-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-non-kd-pre-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: 0.1060
+- Precision: 0.8557
+- Recall: 0.8888
+- F1: 0.8719
+- Accuracy: 0.9853
+
+## 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: 55
+- 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0144        | 0.2910 | 500   | 0.0681          | 0.8603    | 0.8727 | 0.8665 | 0.9851   |
+| 0.015         | 0.5821 | 1000  | 0.0669          | 0.8459    | 0.8798 | 0.8625 | 0.9847   |
+| 0.0152        | 0.8731 | 1500  | 0.0716          | 0.8427    | 0.8813 | 0.8616 | 0.9845   |
+| 0.0114        | 1.1641 | 2000  | 0.0766          | 0.8529    | 0.8710 | 0.8619 | 0.9849   |
+| 0.0099        | 1.4552 | 2500  | 0.0759          | 0.8416    | 0.8971 | 0.8685 | 0.9846   |
+| 0.012         | 1.7462 | 3000  | 0.0746          | 0.8609    | 0.8768 | 0.8688 | 0.9854   |
+| 0.0092        | 2.0373 | 3500  | 0.0841          | 0.8575    | 0.8766 | 0.8669 | 0.9853   |
+| 0.009         | 2.3283 | 4000  | 0.0788          | 0.8515    | 0.8820 | 0.8665 | 0.9849   |
+| 0.0085        | 2.6193 | 4500  | 0.0837          | 0.8699    | 0.8787 | 0.8742 | 0.9858   |
+| 0.009         | 2.9104 | 5000  | 0.0728          | 0.8649    | 0.8801 | 0.8724 | 0.9858   |
+| 0.0075        | 3.2014 | 5500  | 0.0868          | 0.8663    | 0.8730 | 0.8696 | 0.9857   |
+| 0.0063        | 3.4924 | 6000  | 0.0856          | 0.8689    | 0.8742 | 0.8715 | 0.9858   |
+| 0.0071        | 3.7835 | 6500  | 0.0847          | 0.8589    | 0.8811 | 0.8699 | 0.9857   |
+| 0.0063        | 4.0745 | 7000  | 0.0927          | 0.8668    | 0.8748 | 0.8707 | 0.9857   |
+| 0.0046        | 4.3655 | 7500  | 0.0961          | 0.8619    | 0.8628 | 0.8624 | 0.9849   |
+| 0.0061        | 4.6566 | 8000  | 0.0863          | 0.8565    | 0.8738 | 0.8650 | 0.9852   |
+| 0.006         | 4.9476 | 8500  | 0.0896          | 0.8623    | 0.8752 | 0.8687 | 0.9856   |
+| 0.0039        | 5.2386 | 9000  | 0.0883          | 0.8535    | 0.8869 | 0.8699 | 0.9852   |
+| 0.0044        | 5.5297 | 9500  | 0.0973          | 0.8636    | 0.8753 | 0.8694 | 0.9856   |
+| 0.0044        | 5.8207 | 10000 | 0.1008          | 0.8550    | 0.8689 | 0.8619 | 0.9844   |
+| 0.005         | 6.1118 | 10500 | 0.1016          | 0.8481    | 0.8730 | 0.8604 | 0.9844   |
+| 0.0036        | 6.4028 | 11000 | 0.1034          | 0.8393    | 0.8759 | 0.8572 | 0.9841   |
+| 0.0036        | 6.6938 | 11500 | 0.1101          | 0.8478    | 0.8795 | 0.8634 | 0.9850   |
+| 0.0038        | 6.9849 | 12000 | 0.1020          | 0.8538    | 0.8782 | 0.8659 | 0.9848   |
+| 0.0027        | 7.2759 | 12500 | 0.1029          | 0.8502    | 0.8843 | 0.8669 | 0.9852   |
+| 0.0027        | 7.5669 | 13000 | 0.1047          | 0.8636    | 0.8807 | 0.8721 | 0.9858   |
+| 0.003         | 7.8580 | 13500 | 0.1086          | 0.8625    | 0.8800 | 0.8712 | 0.9857   |
+| 0.0035        | 8.1490 | 14000 | 0.1059          | 0.8657    | 0.8752 | 0.8704 | 0.9854   |
+| 0.0027        | 8.4400 | 14500 | 0.1060          | 0.8557    | 0.8888 | 0.8719 | 0.9853   |
+
+
+### 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": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "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": 12,
+  "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": 0.7540983606557377, "recall": 0.9387755102040817, "f1": 0.8363636363636363, "accuracy": 0.9861003861003861}, "en_pud": {"precision": 0.8334901222953904, "recall": 0.8241860465116279, "f1": 0.8288119738072965, "accuracy": 0.9837079712882508}, "de_pud": {"precision": 0.8020257826887661, "recall": 0.8383060635226179, "f1": 0.819764705882353, "accuracy": 0.9803103464441423}, "pt_pud": {"precision": 0.89937106918239, "recall": 0.910828025477707, "f1": 0.9050632911392406, "accuracy": 0.990045712820951}, "ru_pud": {"precision": 0.7242314647377939, "recall": 0.7731660231660231, "f1": 0.7478991596638656, "accuracy": 0.9744252131232239}, "sv_pud": {"precision": 0.8659003831417624, "recall": 0.8785228377065112, "f1": 0.8721659430776653, "accuracy": 0.9869993709373034}, "tl_trg": {"precision": 0.7096774193548387, "recall": 0.9565217391304348, "f1": 0.8148148148148149, "accuracy": 0.9863760217983651}, "tl_ugnayan": {"precision": 0.625, "recall": 0.7575757575757576, "f1": 0.6849315068493151, "accuracy": 0.9744758432087511}, "zh_gsd": {"precision": 0.8431876606683805, "recall": 0.8552803129074316, "f1": 0.849190938511327, "accuracy": 0.9792707292707292}, "zh_gsdsimp": {"precision": 0.8591916558018253, "recall": 0.8636959370904325, "f1": 0.8614379084967321, "accuracy": 0.9808524808524809}, "hr_set": {"precision": 0.9257703081232493, "recall": 0.9422665716322167, "f1": 0.9339456022606853, "accuracy": 0.9911376751854906}, "da_ddt": {"precision": 0.8909512761020881, "recall": 0.8590604026845637, "f1": 0.8747152619589977, "accuracy": 0.990222488276963}, "en_ewt": {"precision": 0.8376681614349776, "recall": 0.8584558823529411, "f1": 0.8479346345891965, "accuracy": 0.9841016854604135}, "pt_bosque": {"precision": 0.8909836065573771, "recall": 0.8946502057613168, "f1": 0.8928131416837782, "accuracy": 0.9889871033183597}, "sr_set": {"precision": 0.9550827423167849, "recall": 0.9539551357733176, "f1": 0.9545186060248081, "accuracy": 0.9905437352245863}, "sk_snk": {"precision": 0.8300865800865801, "recall": 0.8382513661202186, "f1": 0.8341489940184883, "accuracy": 0.9755810301507538}, "sv_talbanken": {"precision": 0.8551401869158879, "recall": 0.9336734693877551, "f1": 0.8926829268292682, "accuracy": 0.9978897776905334}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5de29fd489e84af371da08d783149df911fb57c9c54eada7d713a20d3945a57
+size 1112921036

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb809d58c892484a0b7ea895f0f3a8469b8c8fa2c8cfdbebcb9fdcc48b9b5e75
+size 5304