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_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-po-ner-full-xlmr_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: 53.5855
+- Precision: 0.7926
+- Recall: 0.7941
+- F1: 0.7934
+- Accuracy: 0.9792
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 94.1316       | 0.5828 | 500  | 77.7639         | 0.7573    | 0.7254 | 0.7410 | 0.9749   |
+| 69.1816       | 1.1655 | 1000 | 70.0861         | 0.7700    | 0.7553 | 0.7626 | 0.9771   |
+| 62.5325       | 1.7483 | 1500 | 66.1010         | 0.7697    | 0.7728 | 0.7712 | 0.9774   |
+| 58.8032       | 2.3310 | 2000 | 63.2843         | 0.7722    | 0.7813 | 0.7767 | 0.9781   |
+| 55.8439       | 2.9138 | 2500 | 61.3899         | 0.7711    | 0.7839 | 0.7774 | 0.9777   |
+| 53.6386       | 3.4965 | 3000 | 59.5744         | 0.7829    | 0.7804 | 0.7816 | 0.9782   |
+| 51.8854       | 4.0793 | 3500 | 58.4745         | 0.7896    | 0.7831 | 0.7864 | 0.9784   |
+| 50.3704       | 4.6620 | 4000 | 57.3648         | 0.7888    | 0.7917 | 0.7902 | 0.9787   |
+| 49.2945       | 5.2448 | 4500 | 56.3673         | 0.8003    | 0.7807 | 0.7904 | 0.9787   |
+| 48.3678       | 5.8275 | 5000 | 55.7695         | 0.7906    | 0.7840 | 0.7873 | 0.9787   |
+| 47.4721       | 6.4103 | 5500 | 55.1454         | 0.7836    | 0.7964 | 0.7900 | 0.9792   |
+| 46.9783       | 6.9930 | 6000 | 54.6410         | 0.7931    | 0.7976 | 0.7953 | 0.9790   |
+| 46.3896       | 7.5758 | 6500 | 54.2132         | 0.8004    | 0.7902 | 0.7953 | 0.9792   |
+| 45.895        | 8.1585 | 7000 | 53.9535         | 0.7906    | 0.7945 | 0.7925 | 0.9792   |
+| 45.6796       | 8.7413 | 7500 | 53.7738         | 0.7918    | 0.7895 | 0.7906 | 0.9788   |
+| 45.4159       | 9.3240 | 8000 | 53.6266         | 0.7904    | 0.7950 | 0.7927 | 0.9793   |
+| 45.3274       | 9.9068 | 8500 | 53.5855         | 0.7926    | 0.7941 | 0.7934 | 0.9792   |
+
+
+### 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": 0.4166666666666667, "recall": 0.6122448979591837, "f1": 0.4958677685950413, "accuracy": 0.9420849420849421}, "en_pud": {"precision": 0.7830637488106565, "recall": 0.7655813953488372, "f1": 0.7742238946378175, "accuracy": 0.9780884019644881}, "de_pud": {"precision": 0.7240740740740741, "recall": 0.7526467757459095, "f1": 0.738084001887683, "accuracy": 0.9709812010688669}, "pt_pud": {"precision": 0.7857142857142857, "recall": 0.7807097361237488, "f1": 0.7832040164308536, "accuracy": 0.9792369803904815}, "ru_pud": {"precision": 0.6836734693877551, "recall": 0.7113899613899614, "f1": 0.6972563859981078, "accuracy": 0.9695169206923275}, "sv_pud": {"precision": 0.8117073170731708, "recall": 0.8085519922254616, "f1": 0.810126582278481, "accuracy": 0.9807087439714824}, "tl_trg": {"precision": 0.7692307692307693, "recall": 0.8695652173913043, "f1": 0.8163265306122449, "accuracy": 0.9863760217983651}, "tl_ugnayan": {"precision": 0.55, "recall": 0.6666666666666666, "f1": 0.6027397260273972, "accuracy": 0.9690063810391978}, "zh_gsd": {"precision": 0.8015364916773368, "recall": 0.8161668839634941, "f1": 0.8087855297157621, "accuracy": 0.9731102231102231}, "zh_gsdsimp": {"precision": 0.8075422626788037, "recall": 0.8138925294888598, "f1": 0.8107049608355091, "accuracy": 0.9722777222777222}, "hr_set": {"precision": 0.8810178817056397, "recall": 0.9130434782608695, "f1": 0.8967448372418622, "accuracy": 0.9874690849134378}, "da_ddt": {"precision": 0.7953488372093023, "recall": 0.7651006711409396, "f1": 0.7799315849486887, "accuracy": 0.9831387808041504}, "en_ewt": {"precision": 0.7700831024930748, "recall": 0.7665441176470589, "f1": 0.7683095347766007, "accuracy": 0.9766505956887277}, "pt_bosque": {"precision": 0.7841918294849023, "recall": 0.7267489711934156, "f1": 0.7543784707390003, "accuracy": 0.9776843935661498}, "sr_set": {"precision": 0.928150765606596, "recall": 0.9303423848878394, "f1": 0.929245283018868, "accuracy": 0.9890552491025304}, "sk_snk": {"precision": 0.6916299559471366, "recall": 0.6863387978142077, "f1": 0.6889742183214482, "accuracy": 0.9603486180904522}, "sv_talbanken": {"precision": 0.8064516129032258, "recall": 0.8928571428571429, "f1": 0.8474576271186439, "accuracy": 0.9971536536290916}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae8e826deff9277c459a92db5798d81583ff667c05c546a7757d445f8accf6d2
+size 939737140

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20fd294096b3102f34e69def2b1951ed45c1f19e8fa7975c10383f9615db9ea6
+size 5304