Initial Commit

README.md

@@ -0,0 +1,87 @@
+---
+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-non-kd-po-ner-full-mdeberta_data-univner_half66
+  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-po-ner-full-mdeberta_data-univner_half66
+
+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: 0.1199
+- Precision: 0.8560
+- Recall: 0.8660
+- F1: 0.8609
+- Accuracy: 0.9848
+
+## 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0064        | 0.5828  | 500   | 0.0946          | 0.8530    | 0.8696 | 0.8612 | 0.9847   |
+| 0.0072        | 1.1655  | 1000  | 0.0935          | 0.8563    | 0.8531 | 0.8547 | 0.9844   |
+| 0.0058        | 1.7483  | 1500  | 0.0977          | 0.8394    | 0.8530 | 0.8461 | 0.9836   |
+| 0.005         | 2.3310  | 2000  | 0.1050          | 0.8492    | 0.8609 | 0.8550 | 0.9840   |
+| 0.0054        | 2.9138  | 2500  | 0.1081          | 0.8503    | 0.8422 | 0.8462 | 0.9834   |
+| 0.0043        | 3.4965  | 3000  | 0.1210          | 0.8273    | 0.8775 | 0.8516 | 0.9830   |
+| 0.0049        | 4.0793  | 3500  | 0.1118          | 0.8413    | 0.8590 | 0.8501 | 0.9836   |
+| 0.0035        | 4.6620  | 4000  | 0.1137          | 0.8465    | 0.8647 | 0.8555 | 0.9837   |
+| 0.0031        | 5.2448  | 4500  | 0.1150          | 0.8430    | 0.8551 | 0.8490 | 0.9832   |
+| 0.0027        | 5.8275  | 5000  | 0.1169          | 0.8401    | 0.8590 | 0.8495 | 0.9836   |
+| 0.0027        | 6.4103  | 5500  | 0.1147          | 0.8517    | 0.8678 | 0.8597 | 0.9847   |
+| 0.0034        | 6.9930  | 6000  | 0.1163          | 0.8457    | 0.8651 | 0.8553 | 0.9842   |
+| 0.0024        | 7.5758  | 6500  | 0.1133          | 0.8523    | 0.8652 | 0.8587 | 0.9846   |
+| 0.0031        | 8.1585  | 7000  | 0.1170          | 0.8399    | 0.8577 | 0.8487 | 0.9834   |
+| 0.0019        | 8.7413  | 7500  | 0.1243          | 0.8413    | 0.8673 | 0.8541 | 0.9840   |
+| 0.0019        | 9.3240  | 8000  | 0.1230          | 0.8393    | 0.8726 | 0.8556 | 0.9841   |
+| 0.002         | 9.9068  | 8500  | 0.1218          | 0.8444    | 0.8549 | 0.8496 | 0.9839   |
+| 0.002         | 10.4895 | 9000  | 0.1205          | 0.8518    | 0.8651 | 0.8584 | 0.9846   |
+| 0.0017        | 11.0723 | 9500  | 0.1184          | 0.8643    | 0.8553 | 0.8598 | 0.9846   |
+| 0.0014        | 11.6550 | 10000 | 0.1316          | 0.8363    | 0.8717 | 0.8536 | 0.9838   |
+| 0.0016        | 12.2378 | 10500 | 0.1199          | 0.8560    | 0.8660 | 0.8609 | 0.9848   |
+
+
+### 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": [
+    "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": 0.92, "recall": 0.9387755102040817, "f1": 0.9292929292929293, "accuracy": 0.9945945945945946}, "en_pud": {"precision": 0.8208955223880597, "recall": 0.8186046511627907, "f1": 0.8197484862598975, "accuracy": 0.9821023800528901}, "de_pud": {"precision": 0.8106343283582089, "recall": 0.836381135707411, "f1": 0.8233064898152536, "accuracy": 0.9807791477192818}, "pt_pud": {"precision": 0.8678057553956835, "recall": 0.8780709736123748, "f1": 0.8729081863410221, "accuracy": 0.9870124321784082}, "ru_pud": {"precision": 0.7212669683257918, "recall": 0.7693050193050193, "f1": 0.7445119103222794, "accuracy": 0.9737535520537329}, "sv_pud": {"precision": 0.8760724499523356, "recall": 0.8931000971817298, "f1": 0.8845043310875842, "accuracy": 0.9881002306563221}, "tl_trg": {"precision": 0.9166666666666666, "recall": 0.9565217391304348, "f1": 0.9361702127659574, "accuracy": 0.9959128065395095}, "tl_ugnayan": {"precision": 0.6923076923076923, "recall": 0.8181818181818182, "f1": 0.7500000000000001, "accuracy": 0.9799453053783045}, "zh_gsd": {"precision": 0.8637532133676092, "recall": 0.8761408083441982, "f1": 0.8699029126213592, "accuracy": 0.9816017316017316}, "zh_gsdsimp": {"precision": 0.8795811518324608, "recall": 0.8807339449541285, "f1": 0.8801571709233792, "accuracy": 0.9816849816849816}, "hr_set": {"precision": 0.9084022038567493, "recall": 0.940128296507484, "f1": 0.9239929947460596, "accuracy": 0.9907254740313273}, "da_ddt": {"precision": 0.8811188811188811, "recall": 0.8456375838926175, "f1": 0.863013698630137, "accuracy": 0.9890252419435299}, "en_ewt": {"precision": 0.8257777777777778, "recall": 0.8538602941176471, "f1": 0.8395842747401717, "accuracy": 0.9828664780651074}, "pt_bosque": {"precision": 0.8714893617021277, "recall": 0.842798353909465, "f1": 0.8569037656903765, "accuracy": 0.9862338791479496}, "sr_set": {"precision": 0.9471210340775558, "recall": 0.9515938606847698, "f1": 0.9493521790341578, "accuracy": 0.9908064092461255}, "sk_snk": {"precision": 0.8280739934711643, "recall": 0.8316939890710382, "f1": 0.8298800436205016, "accuracy": 0.9757380653266332}, "sv_talbanken": {"precision": 0.7763713080168776, "recall": 0.9387755102040817, "f1": 0.8498845265588915, "accuracy": 0.9969082789419443}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db88cb86a311aae6ec60c1198104225cd05ce1d1411d5d33d511a042c22e0100
+size 1112921036

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51bd005480e902064d9aa6698e9beee40a5a78534f9e0f2701ac0d38d2e52c8
+size 5304