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-po-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-po-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: 63.9106
+- Precision: 0.7647
+- Recall: 0.7671
+- F1: 0.7659
+- Accuracy: 0.9812
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 115.4337      | 1.28  | 500  | 89.9508         | 0.6039    | 0.5114 | 0.5538 | 0.9672   |
+| 81.5056       | 2.55  | 1000 | 78.2589         | 0.7137    | 0.7019 | 0.7077 | 0.9781   |
+| 73.2299       | 3.83  | 1500 | 72.9013         | 0.7153    | 0.7360 | 0.7255 | 0.9791   |
+| 68.3008       | 5.1   | 2000 | 69.0462         | 0.7313    | 0.7692 | 0.7497 | 0.9806   |
+| 64.8932       | 6.38  | 2500 | 66.5653         | 0.7296    | 0.7516 | 0.7404 | 0.9796   |
+| 62.7315       | 7.65  | 3000 | 64.7790         | 0.7677    | 0.7526 | 0.7601 | 0.9808   |
+| 61.2637       | 8.93  | 3500 | 63.9106         | 0.7647    | 0.7671 | 0.7659 | 0.9812   |
+
+
+### 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": 0.29523809523809524, "recall": 0.6326530612244898, "f1": 0.4025974025974026, "accuracy": 0.911969111969112}, "en_pud": {"precision": 0.7563499529633114, "recall": 0.747906976744186, "f1": 0.7521047708138447, "accuracy": 0.9768133736305251}, "de_pud": {"precision": 0.6998972250770812, "recall": 0.6554379210779596, "f1": 0.6769383697813122, "accuracy": 0.9674651915053208}, "pt_pud": {"precision": 0.7214217098943324, "recall": 0.6833484986351228, "f1": 0.7018691588785048, "accuracy": 0.9708206946639895}, "ru_pud": {"precision": 0.5908667287977633, "recall": 0.611969111969112, "f1": 0.6012328117591276, "accuracy": 0.9593386721777318}, "sv_pud": {"precision": 0.7737603305785123, "recall": 0.7278911564625851, "f1": 0.7501251877816724, "accuracy": 0.9761480394212623}, "tl_trg": {"precision": 0.33962264150943394, "recall": 0.782608695652174, "f1": 0.47368421052631576, "accuracy": 0.9455040871934605}, "tl_ugnayan": {"precision": 0.3787878787878788, "recall": 0.7575757575757576, "f1": 0.5050505050505051, "accuracy": 0.9480401093892434}, "zh_gsd": {"precision": 0.517503805175038, "recall": 0.44328552803129073, "f1": 0.47752808988764045, "accuracy": 0.9324009324009324}, "zh_gsdsimp": {"precision": 0.51698670605613, "recall": 0.45871559633027525, "f1": 0.4861111111111111, "accuracy": 0.9324009324009324}, "hr_set": {"precision": 0.6844319775596073, "recall": 0.6956521739130435, "f1": 0.6899964651820432, "accuracy": 0.962366034624897}, "da_ddt": {"precision": 0.7105263157894737, "recall": 0.6040268456375839, "f1": 0.652962515114873, "accuracy": 0.9746582859423326}, "en_ewt": {"precision": 0.8021133525456292, "recall": 0.7674632352941176, "f1": 0.7844058243306717, "accuracy": 0.9790811650794916}, "pt_bosque": {"precision": 0.6679069767441861, "recall": 0.5909465020576131, "f1": 0.6270742358078601, "accuracy": 0.9638458194464571}, "sr_set": {"precision": 0.6817653890824622, "recall": 0.693034238488784, "f1": 0.6873536299765808, "accuracy": 0.9556956483670431}, "sk_snk": {"precision": 0.5825027685492802, "recall": 0.5748633879781421, "f1": 0.5786578657865786, "accuracy": 0.9433888190954773}, "sv_talbanken": {"precision": 0.7387387387387387, "recall": 0.8367346938775511, "f1": 0.784688995215311, "accuracy": 0.9957795553810669}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c823cef76ff683971ac9ba2e392a47dd8c9f1162a8f673f6a07d2dde02d45b7c
+size 944389666

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833c34e45df2255e1cc0e9090b09edf735c1aa5bf257fc0a6c2834465484b698
+size 4600