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-scr-ner-full-xlmr-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-scr-ner-full-xlmr-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: 250.6721
+- Precision: 0.4368
+- Recall: 0.2754
+- F1: 0.3378
+- Accuracy: 0.9532
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 426.5331      | 1.28  | 500  | 343.1131        | 0.4717    | 0.0259 | 0.0491 | 0.9413   |
+| 317.8317      | 2.55  | 1000 | 306.4857        | 0.3815    | 0.1066 | 0.1667 | 0.9449   |
+| 288.4479      | 3.83  | 1500 | 285.8158        | 0.4429    | 0.1284 | 0.1990 | 0.9461   |
+| 270.6268      | 5.1   | 2000 | 271.5317        | 0.3921    | 0.2050 | 0.2692 | 0.9494   |
+| 257.3109      | 6.38  | 2500 | 260.7265        | 0.3853    | 0.2381 | 0.2943 | 0.9517   |
+| 248.4864      | 7.65  | 3000 | 253.9278        | 0.3950    | 0.2940 | 0.3371 | 0.9527   |
+| 242.8456      | 8.93  | 3500 | 250.6721        | 0.4368    | 0.2754 | 0.3378 | 0.9532   |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

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": "4.33.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.3191489361702128, "recall": 0.30612244897959184, "f1": 0.3125, "accuracy": 0.9451737451737452}, "en_pud": {"precision": 0.34501845018450183, "recall": 0.173953488372093, "f1": 0.2312925170068027, "accuracy": 0.935681904042312}, "de_pud": {"precision": 0.1561938958707361, "recall": 0.08373435996150144, "f1": 0.10902255639097745, "accuracy": 0.9213820261591111}, "pt_pud": {"precision": 0.271356783919598, "recall": 0.04913557779799818, "f1": 0.08320493066255777, "accuracy": 0.9331396590763447}, "ru_pud": {"precision": 0.046511627906976744, "recall": 0.0019305019305019305, "f1": 0.0037071362372567192, "accuracy": 0.9222939808834927}, "sv_pud": {"precision": 0.28879310344827586, "recall": 0.06511175898931001, "f1": 0.10626486915146709, "accuracy": 0.9270287271964772}, "tl_trg": {"precision": 0.3, "recall": 0.391304347826087, "f1": 0.33962264150943394, "accuracy": 0.946866485013624}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9443938012762079}, "zh_gsd": {"precision": 0.2, "recall": 0.002607561929595828, "f1": 0.005148005148005148, "accuracy": 0.8827006327006327}, "zh_gsdsimp": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.883033633033633}, "hr_set": {"precision": 0.14622641509433962, "recall": 0.022095509622238062, "f1": 0.03839009287925697, "accuracy": 0.9139323990107172}, "da_ddt": {"precision": 0.21238938053097345, "recall": 0.053691275167785234, "f1": 0.08571428571428573, "accuracy": 0.9365459443280455}, "en_ewt": {"precision": 0.4687022900763359, "recall": 0.2821691176470588, "f1": 0.35226620768789446, "accuracy": 0.9482806709965335}, "pt_bosque": {"precision": 0.18303571428571427, "recall": 0.03374485596707819, "f1": 0.05698401667824879, "accuracy": 0.9232357629329083}, "sr_set": {"precision": 0.09090909090909091, "recall": 0.009445100354191263, "f1": 0.017112299465240642, "accuracy": 0.8927414412047981}, "sk_snk": {"precision": 0.20093457943925233, "recall": 0.046994535519125684, "f1": 0.07617360496014171, "accuracy": 0.8885050251256281}, "sv_talbanken": {"precision": 0.14184397163120568, "recall": 0.10204081632653061, "f1": 0.11869436201780416, "accuracy": 0.9839034205231388}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e59418b10636e37f48616986ad14d5a450ea33d0c06d0785fa6cb3ece76c38
+size 939760294

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0e47657862944a57e76da62acfc0e88e816bc193a752c941ddf71caf5780e4
+size 4600