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-po-ner-full-xlmr_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-kd-po-ner-full-xlmr_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: 53.5934
+- Precision: 0.7914
+- Recall: 0.7922
+- F1: 0.7918
+- Accuracy: 0.9789
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 93.9811       | 0.5828 | 500  | 77.1719         | 0.7802    | 0.7262 | 0.7522 | 0.9755   |
+| 69.0206       | 1.1655 | 1000 | 70.2429         | 0.7554    | 0.7718 | 0.7635 | 0.9766   |
+| 62.467        | 1.7483 | 1500 | 66.3316         | 0.7886    | 0.7455 | 0.7664 | 0.9767   |
+| 58.5858       | 2.3310 | 2000 | 63.5450         | 0.7970    | 0.7396 | 0.7672 | 0.9768   |
+| 55.7072       | 2.9138 | 2500 | 61.1857         | 0.7871    | 0.7772 | 0.7821 | 0.9783   |
+| 53.5041       | 3.4965 | 3000 | 59.5353         | 0.7816    | 0.7843 | 0.7829 | 0.9783   |
+| 51.8153       | 4.0793 | 3500 | 58.3157         | 0.7938    | 0.7863 | 0.7900 | 0.9786   |
+| 50.327        | 4.6620 | 4000 | 57.1124         | 0.7914    | 0.7905 | 0.7910 | 0.9788   |
+| 49.2402       | 5.2448 | 4500 | 56.3184         | 0.7844    | 0.7986 | 0.7914 | 0.9789   |
+| 48.2334       | 5.8275 | 5000 | 55.7867         | 0.7922    | 0.7862 | 0.7892 | 0.9787   |
+| 47.4646       | 6.4103 | 5500 | 55.2770         | 0.7955    | 0.7818 | 0.7886 | 0.9785   |
+| 46.8764       | 6.9930 | 6000 | 54.6109         | 0.7958    | 0.7826 | 0.7891 | 0.9788   |
+| 46.3099       | 7.5758 | 6500 | 54.2702         | 0.8051    | 0.7830 | 0.7939 | 0.9792   |
+| 45.8877       | 8.1585 | 7000 | 53.9679         | 0.7953    | 0.7917 | 0.7935 | 0.9792   |
+| 45.5735       | 8.7413 | 7500 | 53.7160         | 0.7935    | 0.7907 | 0.7921 | 0.9787   |
+| 45.3573       | 9.3240 | 8000 | 53.6114         | 0.7886    | 0.7919 | 0.7903 | 0.9791   |
+| 45.2644       | 9.9068 | 8500 | 53.5934         | 0.7914    | 0.7922 | 0.7918 | 0.9789   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_half",
+  "architectures": [
+    "XLMRobertaForTokenClassificationKD"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.43283582089552236, "recall": 0.5918367346938775, "f1": 0.5, "accuracy": 0.9505791505791505}, "en_pud": {"precision": 0.7855750487329435, "recall": 0.7497674418604651, "f1": 0.7672536887196573, "accuracy": 0.9778522856063468}, "de_pud": {"precision": 0.736231884057971, "recall": 0.7333974975938402, "f1": 0.734811957569913, "accuracy": 0.9713562420889785}, "pt_pud": {"precision": 0.8007699711260827, "recall": 0.7570518653321201, "f1": 0.7782974742750234, "accuracy": 0.9796642030161917}, "ru_pud": {"precision": 0.6793893129770993, "recall": 0.6872586872586872, "f1": 0.6833013435700576, "accuracy": 0.9680185998450013}, "sv_pud": {"precision": 0.8328298086606244, "recall": 0.8036929057337221, "f1": 0.8180019782393669, "accuracy": 0.9813902285594465}, "tl_trg": {"precision": 0.7777777777777778, "recall": 0.9130434782608695, "f1": 0.84, "accuracy": 0.9877384196185286}, "tl_ugnayan": {"precision": 0.5, "recall": 0.6363636363636364, "f1": 0.56, "accuracy": 0.9644484958979034}, "zh_gsd": {"precision": 0.835820895522388, "recall": 0.803129074315515, "f1": 0.8191489361702127, "accuracy": 0.9751082251082251}, "zh_gsdsimp": {"precision": 0.8128342245989305, "recall": 0.7968545216251638, "f1": 0.8047650562541363, "accuracy": 0.974025974025974}, "hr_set": {"precision": 0.8972554539057002, "recall": 0.9087669280114041, "f1": 0.9029745042492918, "accuracy": 0.9885408079142621}, "da_ddt": {"precision": 0.8188585607940446, "recall": 0.738255033557047, "f1": 0.7764705882352941, "accuracy": 0.9829392397485782}, "en_ewt": {"precision": 0.7942028985507247, "recall": 0.7555147058823529, "f1": 0.7743758831841733, "accuracy": 0.977009204287365}, "pt_bosque": {"precision": 0.7873510540788268, "recall": 0.7069958847736626, "f1": 0.7450130095403296, "accuracy": 0.9764889146500507}, "sr_set": {"precision": 0.9333333333333333, "recall": 0.9256198347107438, "f1": 0.9294605809128631, "accuracy": 0.9887925750809912}, "sk_snk": {"precision": 0.70193401592719, "recall": 0.6743169398907104, "f1": 0.6878483835005574, "accuracy": 0.9597989949748744}, "sv_talbanken": {"precision": 0.8413461538461539, "recall": 0.8928571428571429, "f1": 0.8663366336633663, "accuracy": 0.9973499533788095}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b899ffd6df4230d5ce526116fb3d2e9f3407241d28822e644bc0129bf12b28
+size 939737140

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c66de5ee674c97e25239956a9a18f184f0ceee23281d66a8240eaa34cf8474
+size 5304