Initial Commit

README.md

@@ -0,0 +1,100 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_full
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-non-kd-scr-ner-full_data-univner_full66
+  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-non-kd-scr-ner-full_data-univner_full66
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_full](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_full) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1213
+- Precision: 0.8519
+- Recall: 0.8637
+- F1: 0.8577
+- Accuracy: 0.9843
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 66
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0089        | 0.2910 | 500   | 0.0854          | 0.8477    | 0.8498 | 0.8488 | 0.9839   |
+| 0.0113        | 0.5821 | 1000  | 0.0804          | 0.8488    | 0.8660 | 0.8573 | 0.9846   |
+| 0.0106        | 0.8731 | 1500  | 0.0797          | 0.8506    | 0.8665 | 0.8585 | 0.9845   |
+| 0.0094        | 1.1641 | 2000  | 0.0869          | 0.8584    | 0.8622 | 0.8603 | 0.9847   |
+| 0.0081        | 1.4552 | 2500  | 0.0932          | 0.8417    | 0.8664 | 0.8539 | 0.9839   |
+| 0.0093        | 1.7462 | 3000  | 0.0842          | 0.8416    | 0.8673 | 0.8543 | 0.9842   |
+| 0.0075        | 2.0373 | 3500  | 0.0912          | 0.8355    | 0.8691 | 0.8520 | 0.9838   |
+| 0.0061        | 2.3283 | 4000  | 0.0825          | 0.8491    | 0.8518 | 0.8505 | 0.9842   |
+| 0.007         | 2.6193 | 4500  | 0.0914          | 0.8494    | 0.8569 | 0.8531 | 0.9845   |
+| 0.0072        | 2.9104 | 5000  | 0.0940          | 0.8481    | 0.8619 | 0.8550 | 0.9842   |
+| 0.005         | 3.2014 | 5500  | 0.0922          | 0.8509    | 0.8588 | 0.8548 | 0.9845   |
+| 0.0051        | 3.4924 | 6000  | 0.0985          | 0.8414    | 0.8600 | 0.8506 | 0.9839   |
+| 0.0055        | 3.7835 | 6500  | 0.0878          | 0.8466    | 0.8517 | 0.8491 | 0.9843   |
+| 0.0054        | 4.0745 | 7000  | 0.1042          | 0.8587    | 0.8674 | 0.8630 | 0.9850   |
+| 0.0045        | 4.3655 | 7500  | 0.0981          | 0.8534    | 0.8639 | 0.8586 | 0.9841   |
+| 0.0054        | 4.6566 | 8000  | 0.1017          | 0.8557    | 0.8665 | 0.8611 | 0.9849   |
+| 0.0046        | 4.9476 | 8500  | 0.1031          | 0.8396    | 0.8634 | 0.8513 | 0.9834   |
+| 0.0041        | 5.2386 | 9000  | 0.1015          | 0.8475    | 0.8603 | 0.8539 | 0.9842   |
+| 0.0039        | 5.5297 | 9500  | 0.1053          | 0.8500    | 0.8628 | 0.8564 | 0.9846   |
+| 0.0037        | 5.8207 | 10000 | 0.1113          | 0.8478    | 0.8654 | 0.8565 | 0.9845   |
+| 0.0045        | 6.1118 | 10500 | 0.1221          | 0.8432    | 0.8714 | 0.8571 | 0.9841   |
+| 0.0041        | 6.4028 | 11000 | 0.1001          | 0.8518    | 0.8639 | 0.8578 | 0.9844   |
+| 0.0031        | 6.6938 | 11500 | 0.1068          | 0.8564    | 0.8632 | 0.8598 | 0.9846   |
+| 0.0037        | 6.9849 | 12000 | 0.1108          | 0.8450    | 0.8613 | 0.8531 | 0.9841   |
+| 0.0027        | 7.2759 | 12500 | 0.1184          | 0.8463    | 0.8647 | 0.8554 | 0.9838   |
+| 0.0031        | 7.5669 | 13000 | 0.1205          | 0.8460    | 0.8611 | 0.8535 | 0.9837   |
+| 0.0031        | 7.8580 | 13500 | 0.1132          | 0.8486    | 0.8719 | 0.8601 | 0.9845   |
+| 0.003         | 8.1490 | 14000 | 0.1104          | 0.8440    | 0.8600 | 0.8519 | 0.9840   |
+| 0.0021        | 8.4400 | 14500 | 0.1214          | 0.8529    | 0.8469 | 0.8499 | 0.9838   |
+| 0.0029        | 8.7311 | 15000 | 0.1154          | 0.8408    | 0.8559 | 0.8483 | 0.9837   |
+| 0.0028        | 9.0221 | 15500 | 0.1117          | 0.8460    | 0.8686 | 0.8571 | 0.9845   |
+| 0.0021        | 9.3132 | 16000 | 0.1253          | 0.8347    | 0.8694 | 0.8517 | 0.9836   |
+| 0.0018        | 9.6042 | 16500 | 0.1239          | 0.8487    | 0.8663 | 0.8574 | 0.9844   |
+| 0.0021        | 9.8952 | 17000 | 0.1213          | 0.8519    | 0.8637 | 0.8577 | 0.9843   |
+
+
+### 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_full",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": 12,
+  "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": 0.647887323943662, "recall": 0.9387755102040817, "f1": 0.7666666666666667, "accuracy": 0.9768339768339769}, "en_pud": {"precision": 0.8066985645933015, "recall": 0.7841860465116279, "f1": 0.7952830188679246, "accuracy": 0.9802134491877598}, "de_pud": {"precision": 0.7927844588344126, "recall": 0.8248315688161694, "f1": 0.8084905660377358, "accuracy": 0.9777319394308752}, "pt_pud": {"precision": 0.8751099384344767, "recall": 0.905368516833485, "f1": 0.8899821109123435, "accuracy": 0.9885077113683941}, "ru_pud": {"precision": 0.7248628884826326, "recall": 0.7654440154440154, "f1": 0.7446009389671362, "accuracy": 0.9741152157065358}, "sv_pud": {"precision": 0.8679802955665025, "recall": 0.8561710398445093, "f1": 0.8620352250489237, "accuracy": 0.9866848395890123}, "tl_trg": {"precision": 0.9565217391304348, "recall": 0.9565217391304348, "f1": 0.9565217391304348, "accuracy": 0.997275204359673}, "tl_ugnayan": {"precision": 0.6666666666666666, "recall": 0.7272727272727273, "f1": 0.6956521739130435, "accuracy": 0.9790337283500455}, "zh_gsd": {"precision": 0.8480519480519481, "recall": 0.8513689700130378, "f1": 0.8497072218607677, "accuracy": 0.9779387279387279}, "zh_gsdsimp": {"precision": 0.8434670116429496, "recall": 0.854521625163827, "f1": 0.8489583333333334, "accuracy": 0.9784382284382285}, "hr_set": {"precision": 0.918580375782881, "recall": 0.9408410548823949, "f1": 0.9295774647887324, "accuracy": 0.9909727947238253}, "da_ddt": {"precision": 0.8844339622641509, "recall": 0.8389261744966443, "f1": 0.8610792192881745, "accuracy": 0.9892247829991021}, "en_ewt": {"precision": 0.8191287878787878, "recall": 0.7950367647058824, "f1": 0.8069029850746269, "accuracy": 0.9801569908754034}, "pt_bosque": {"precision": 0.8886118038237739, "recall": 0.8798353909465021, "f1": 0.8842018196856908, "accuracy": 0.9883350239095783}, "sr_set": {"precision": 0.9558998808104887, "recall": 0.9468713105076741, "f1": 0.9513641755634639, "accuracy": 0.9911566412748446}, "sk_snk": {"precision": 0.8399558498896247, "recall": 0.8316939890710382, "f1": 0.8358045030203185, "accuracy": 0.9747958542713567}, "sv_talbanken": {"precision": 0.8984771573604061, "recall": 0.9030612244897959, "f1": 0.900763358778626, "accuracy": 0.9980860774402512}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698d9787a2491c98c9c5a091158f8434c70978082594c3cb294fa56d7cb301e7
+size 1109857804

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d1de551ed75db9cc8b86cf55b5d2c07888f8c39944d8eaf31b5e336ad71546
+size 5304