Initial Commit

README.md

@@ -0,0 +1,74 @@
+---
+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-scr-ner-full-mdeberta-halfen_data-univner_en66
+  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-scr-ner-full-mdeberta-halfen_data-univner_en66
+
+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: 392.9234
+- Precision: 0.5127
+- Recall: 0.3975
+- F1: 0.4478
+- Accuracy: 0.9594
+
+## 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: 66
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 603.5902      | 1.28  | 500  | 532.0310        | 0.7568    | 0.0290 | 0.0558 | 0.9414   |
+| 497.4866      | 2.55  | 1000 | 479.9597        | 0.2891    | 0.1646 | 0.2098 | 0.9463   |
+| 451.2688      | 3.83  | 1500 | 443.6332        | 0.4884    | 0.2619 | 0.3410 | 0.9526   |
+| 420.4378      | 5.1   | 2000 | 421.6972        | 0.4431    | 0.3789 | 0.4085 | 0.9567   |
+| 400.9749      | 6.38  | 2500 | 408.6700        | 0.5306    | 0.3230 | 0.4015 | 0.9574   |
+| 388.4506      | 7.65  | 3000 | 398.0555        | 0.5026    | 0.4037 | 0.4478 | 0.9596   |
+| 380.4155      | 8.93  | 3500 | 392.9234        | 0.5127    | 0.3975 | 0.4478 | 0.9594   |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

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": "4.33.3",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.09876543209876543, "recall": 0.16326530612244897, "f1": 0.12307692307692308, "accuracy": 0.9011583011583012}, "en_pud": {"precision": 0.4186704384724187, "recall": 0.2753488372093023, "f1": 0.3322109988776656, "accuracy": 0.9407820173781639}, "de_pud": {"precision": 0.0755750273822563, "recall": 0.13282001924927817, "f1": 0.09633507853403142, "accuracy": 0.8466551029018798}, "pt_pud": {"precision": 0.11568409343715239, "recall": 0.09463148316651501, "f1": 0.1041041041041041, "accuracy": 0.9050711325671807}, "ru_pud": {"precision": 0.011221122112211221, "recall": 0.016409266409266408, "f1": 0.013328106624852998, "accuracy": 0.8327563936967192}, "sv_pud": {"precision": 0.10925196850393701, "recall": 0.10787172011661808, "f1": 0.10855745721271394, "accuracy": 0.8861396519186412}, "tl_trg": {"precision": 0.14634146341463414, "recall": 0.2608695652173913, "f1": 0.1875, "accuracy": 0.9182561307901907}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9079307201458523}, "zh_gsd": {"precision": 0.050314465408805034, "recall": 0.010430247718383311, "f1": 0.01727861771058315, "accuracy": 0.8734598734598734}, "zh_gsdsimp": {"precision": 0.013793103448275862, "recall": 0.002621231979030144, "f1": 0.004405286343612335, "accuracy": 0.8736263736263736}, "hr_set": {"precision": 0.058290888511601587, "recall": 0.07341411261582323, "f1": 0.06498422712933755, "accuracy": 0.8544105523495465}, "da_ddt": {"precision": 0.1284153005464481, "recall": 0.10514541387024609, "f1": 0.11562115621156213, "accuracy": 0.9146961987428913}, "en_ewt": {"precision": 0.6038415366146459, "recall": 0.46231617647058826, "f1": 0.523685580426861, "accuracy": 0.9579631031597402}, "pt_bosque": {"precision": 0.10960334029227557, "recall": 0.08641975308641975, "f1": 0.09664058904739989, "accuracy": 0.9020794087813361}, "sr_set": {"precision": 0.04332129963898917, "recall": 0.04250295159386069, "f1": 0.04290822407628129, "accuracy": 0.8328517642938447}, "sk_snk": {"precision": 0.07249466950959488, "recall": 0.07431693989071038, "f1": 0.07339449541284404, "accuracy": 0.8283605527638191}, "sv_talbanken": {"precision": 0.029216467463479414, "recall": 0.11224489795918367, "f1": 0.04636459430979979, "accuracy": 0.9420915738332434}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1815713744dd8490762373c8a8e22c2e16989dc32b4b3461345b7ca0cc18366a
+size 972701090

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb837cd1ca60159e1c11c033c4d2853dc7ef9f8165b28443b5d9fc23db380bc
+size 4600