Initial Commit

README.md

@@ -0,0 +1,85 @@
+---
+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-kd-scr-ner-full-mdeberta_data-univner_half55
+  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_data-univner_half55
+
+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: 369.5634
+- Precision: 0.3741
+- Recall: 0.4149
+- F1: 0.3935
+- Accuracy: 0.9238
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 638.1208      | 0.5828 | 500  | 570.1356        | 1.0       | 0.0004 | 0.0009 | 0.9241   |
+| 540.7434      | 1.1655 | 1000 | 524.2383        | 0.2886    | 0.0521 | 0.0882 | 0.9253   |
+| 490.1496      | 1.7483 | 1500 | 493.6944        | 0.2927    | 0.1682 | 0.2137 | 0.9297   |
+| 454.2343      | 2.3310 | 2000 | 471.6737        | 0.3338    | 0.2411 | 0.2800 | 0.9293   |
+| 429.0546      | 2.9138 | 2500 | 450.0691        | 0.4515    | 0.2450 | 0.3176 | 0.9362   |
+| 407.3853      | 3.4965 | 3000 | 436.8550        | 0.3570    | 0.2877 | 0.3186 | 0.9304   |
+| 390.9232      | 4.0793 | 3500 | 424.0557        | 0.3848    | 0.3245 | 0.3521 | 0.9313   |
+| 376.2085      | 4.6620 | 4000 | 417.5171        | 0.3349    | 0.3800 | 0.3561 | 0.9216   |
+| 364.3876      | 5.2448 | 4500 | 404.9495        | 0.3708    | 0.3766 | 0.3737 | 0.9276   |
+| 354.1139      | 5.8275 | 5000 | 398.9413        | 0.3534    | 0.3877 | 0.3697 | 0.9226   |
+| 344.7845      | 6.4103 | 5500 | 394.6783        | 0.3273    | 0.4193 | 0.3676 | 0.9143   |
+| 337.8201      | 6.9930 | 6000 | 382.1873        | 0.3881    | 0.3900 | 0.3891 | 0.9289   |
+| 330.94        | 7.5758 | 6500 | 381.2287        | 0.3480    | 0.4074 | 0.3754 | 0.9188   |
+| 326.2092      | 8.1585 | 7000 | 372.6259        | 0.4087    | 0.3877 | 0.3979 | 0.9306   |
+| 322.0348      | 8.7413 | 7500 | 374.2613        | 0.3530    | 0.4144 | 0.3812 | 0.9184   |
+| 319.0297      | 9.3240 | 8000 | 370.3267        | 0.3774    | 0.4131 | 0.3944 | 0.9239   |
+| 317.8106      | 9.9068 | 8500 | 369.5634        | 0.3741    | 0.4149 | 0.3935 | 0.9238   |
+
+
+### 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": [
+    "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": 0.22857142857142856, "recall": 0.16326530612244897, "f1": 0.19047619047619044, "accuracy": 0.9428571428571428}, "en_pud": {"precision": 0.49299719887955185, "recall": 0.32744186046511625, "f1": 0.39351593068753493, "accuracy": 0.9451265583679638}, "de_pud": {"precision": 0.10109465550547328, "recall": 0.15110683349374399, "f1": 0.121141975308642, "accuracy": 0.8431859734658478}, "pt_pud": {"precision": 0.14026236125126135, "recall": 0.1264786169244768, "f1": 0.13301435406698564, "accuracy": 0.9017387960866408}, "ru_pud": {"precision": 0.008284023668639054, "recall": 0.013513513513513514, "f1": 0.010271460014673514, "accuracy": 0.7553087057607853}, "sv_pud": {"precision": 0.10943695479777954, "recall": 0.13411078717201166, "f1": 0.1205240174672489, "accuracy": 0.8570979240931013}, "tl_trg": {"precision": 0.2, "recall": 0.17391304347826086, "f1": 0.18604651162790697, "accuracy": 0.94141689373297}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9152233363719234}, "zh_gsd": {"precision": 0.5997229916897507, "recall": 0.5645371577574967, "f1": 0.5815983881799864, "accuracy": 0.9458874458874459}, "zh_gsdsimp": {"precision": 0.6257142857142857, "recall": 0.5740498034076016, "f1": 0.5987696514012304, "accuracy": 0.9476356976356977}, "hr_set": {"precision": 0.724320241691843, "recall": 0.6835352815395581, "f1": 0.7033370003667034, "accuracy": 0.9643033800494641}, "da_ddt": {"precision": 0.18484848484848485, "recall": 0.13646532438478748, "f1": 0.157014157014157, "accuracy": 0.9196847251321959}, "en_ewt": {"precision": 0.6408629441624365, "recall": 0.4641544117647059, "f1": 0.5383795309168444, "accuracy": 0.9570466589632227}, "pt_bosque": {"precision": 0.16447368421052633, "recall": 0.1440329218106996, "f1": 0.153576129881527, "accuracy": 0.9027677148239386}, "sr_set": {"precision": 0.6807692307692308, "recall": 0.6269185360094451, "f1": 0.6527350952673633, "accuracy": 0.9487785657998424}, "sk_snk": {"precision": 0.11686746987951807, "recall": 0.10601092896174863, "f1": 0.11117478510028653, "accuracy": 0.8539572864321608}, "sv_talbanken": {"precision": 0.026892430278884463, "recall": 0.1377551020408163, "f1": 0.045, "accuracy": 0.9065613191343181}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1012b0d7ead0a7616c4e9ed9931d60672e96c843ed3a2f820015514cfff24f86
+size 972678148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9889b896eefaf20fc908045abc2ed7d650ca0b49efbb0e4a60ac9c80c9de12b8
+size 5304