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_half44
+  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_half44
+
+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: 364.7336
+- Precision: 0.3918
+- Recall: 0.4292
+- F1: 0.4096
+- Accuracy: 0.9267
+
+## 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: 44
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 637.6988      | 0.5828 | 500  | 570.9927        | 0.6154    | 0.0012 | 0.0023 | 0.9241   |
+| 541.2212      | 1.1655 | 1000 | 524.6858        | 0.3571    | 0.0353 | 0.0643 | 0.9251   |
+| 490.5141      | 1.7483 | 1500 | 492.2816        | 0.3048    | 0.1754 | 0.2227 | 0.9310   |
+| 455.7006      | 2.3310 | 2000 | 474.9406        | 0.3064    | 0.2626 | 0.2828 | 0.9273   |
+| 430.062       | 2.9138 | 2500 | 452.2111        | 0.3632    | 0.3073 | 0.3329 | 0.9298   |
+| 408.0248      | 3.4965 | 3000 | 434.8791        | 0.3994    | 0.3220 | 0.3566 | 0.9341   |
+| 390.2744      | 4.0793 | 3500 | 424.2673        | 0.3727    | 0.3444 | 0.3580 | 0.9307   |
+| 374.3932      | 4.6620 | 4000 | 411.0975        | 0.4020    | 0.3979 | 0.3999 | 0.9328   |
+| 362.2752      | 5.2448 | 4500 | 403.7659        | 0.3614    | 0.3963 | 0.3781 | 0.9239   |
+| 350.9508      | 5.8275 | 5000 | 392.9673        | 0.3736    | 0.3855 | 0.3795 | 0.9296   |
+| 341.7654      | 6.4103 | 5500 | 385.3136        | 0.4030    | 0.3972 | 0.4001 | 0.9302   |
+| 334.4205      | 6.9930 | 6000 | 380.2038        | 0.3773    | 0.4142 | 0.3949 | 0.9263   |
+| 327.3654      | 7.5758 | 6500 | 375.4951        | 0.3694    | 0.4276 | 0.3964 | 0.9227   |
+| 322.1269      | 8.1585 | 7000 | 372.3464        | 0.3650    | 0.4338 | 0.3965 | 0.9209   |
+| 318.558       | 8.7413 | 7500 | 366.4694        | 0.3970    | 0.4191 | 0.4078 | 0.9295   |
+| 315.4182      | 9.3240 | 8000 | 365.6752        | 0.3861    | 0.4409 | 0.4117 | 0.9260   |
+| 314.0958      | 9.9068 | 8500 | 364.7336        | 0.3918    | 0.4292 | 0.4096 | 0.9267   |
+
+
+### 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": 0.25925925925925924, "recall": 0.2857142857142857, "f1": 0.2718446601941748, "accuracy": 0.938996138996139}, "en_pud": {"precision": 0.4773561811505508, "recall": 0.3627906976744186, "f1": 0.41226215644820297, "accuracy": 0.9457404608991311}, "de_pud": {"precision": 0.07544449783757809, "recall": 0.15110683349374399, "f1": 0.10064102564102564, "accuracy": 0.8120106886690732}, "pt_pud": {"precision": 0.13522267206477734, "recall": 0.15195632393084624, "f1": 0.14310197086546703, "accuracy": 0.8880676720639125}, "ru_pud": {"precision": 0.0129926375054136, "recall": 0.02895752895752896, "f1": 0.017937219730941704, "accuracy": 0.7211573236889692}, "sv_pud": {"precision": 0.09177927927927929, "recall": 0.15840621963070942, "f1": 0.1162210338680927, "accuracy": 0.8084504088907528}, "tl_trg": {"precision": 0.3235294117647059, "recall": 0.4782608695652174, "f1": 0.3859649122807018, "accuracy": 0.946866485013624}, "tl_ugnayan": {"precision": 0.09302325581395349, "recall": 0.12121212121212122, "f1": 0.10526315789473685, "accuracy": 0.9288969917958068}, "zh_gsd": {"precision": 0.6184738955823293, "recall": 0.6023468057366362, "f1": 0.6103038309114928, "accuracy": 0.9463869463869464}, "zh_gsdsimp": {"precision": 0.6358839050131926, "recall": 0.6317169069462647, "f1": 0.6337935568704799, "accuracy": 0.9500499500499501}, "hr_set": {"precision": 0.7299787384833452, "recall": 0.7341411261582323, "f1": 0.7320540156361052, "accuracy": 0.9683429513602638}, "da_ddt": {"precision": 0.12991452991452992, "recall": 0.17002237136465326, "f1": 0.1472868217054264, "accuracy": 0.8922478299910207}, "en_ewt": {"precision": 0.6374722838137472, "recall": 0.5284926470588235, "f1": 0.5778894472361809, "accuracy": 0.9600749093517154}, "pt_bosque": {"precision": 0.14318706697459585, "recall": 0.15308641975308643, "f1": 0.1479713603818616, "accuracy": 0.8951238950876684}, "sr_set": {"precision": 0.7095238095238096, "recall": 0.7036599763872491, "f1": 0.7065797273266153, "accuracy": 0.9556080903598634}, "sk_snk": {"precision": 0.15594541910331383, "recall": 0.17486338797814208, "f1": 0.1648634724368882, "accuracy": 0.8487751256281407}, "sv_talbanken": {"precision": 0.024229074889867842, "recall": 0.1683673469387755, "f1": 0.04236200256739409, "accuracy": 0.8741227854934485}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f64e90687e9be3f80a0f472cd2603be746373a2913a1e37089364dd54a7cc5
+size 972678148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b983faa5186ba22fee5695761b3c78fa9280a735dbcfc971cf574fa4ace3f39
+size 5304