Initial Commit

README.md

@@ -0,0 +1,89 @@
+---
+library_name: transformers
+license: mit
+base_model: haryoaw/scenario-TCR-NER_data-univner_en
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: scenario-non-kd-pre-ner-full-xlmr_data-univner_en44
+  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-pre-ner-full-xlmr_data-univner_en44
+
+This model is a fine-tuned version of [haryoaw/scenario-TCR-NER_data-univner_en](https://huggingface.co/haryoaw/scenario-TCR-NER_data-univner_en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1413
+- Precision: 0.7900
+- Recall: 0.8023
+- F1: 0.7961
+- Accuracy: 0.9836
+
+## 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: 44
+- 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0035        | 1.2755  | 500   | 0.1065          | 0.7916    | 0.8023 | 0.7969 | 0.9842   |
+| 0.0036        | 2.5510  | 1000  | 0.1246          | 0.7914    | 0.7619 | 0.7764 | 0.9821   |
+| 0.0027        | 3.8265  | 1500  | 0.1191          | 0.7819    | 0.8054 | 0.7935 | 0.9837   |
+| 0.002         | 5.1020  | 2000  | 0.1324          | 0.7907    | 0.7940 | 0.7924 | 0.9831   |
+| 0.0023        | 6.3776  | 2500  | 0.1197          | 0.7826    | 0.8085 | 0.7953 | 0.9836   |
+| 0.0017        | 7.6531  | 3000  | 0.1390          | 0.7673    | 0.8054 | 0.7859 | 0.9819   |
+| 0.0012        | 8.9286  | 3500  | 0.1371          | 0.7827    | 0.7609 | 0.7717 | 0.9815   |
+| 0.0013        | 10.2041 | 4000  | 0.1459          | 0.7426    | 0.8002 | 0.7703 | 0.9809   |
+| 0.0017        | 11.4796 | 4500  | 0.1345          | 0.7771    | 0.7723 | 0.7747 | 0.9819   |
+| 0.0011        | 12.7551 | 5000  | 0.1327          | 0.7824    | 0.7930 | 0.7877 | 0.9831   |
+| 0.001         | 14.0306 | 5500  | 0.1422          | 0.7591    | 0.7961 | 0.7772 | 0.9813   |
+| 0.0009        | 15.3061 | 6000  | 0.1383          | 0.7715    | 0.7899 | 0.7806 | 0.9819   |
+| 0.0006        | 16.5816 | 6500  | 0.1360          | 0.7827    | 0.8054 | 0.7939 | 0.9831   |
+| 0.0006        | 17.8571 | 7000  | 0.1429          | 0.7889    | 0.7930 | 0.7909 | 0.9834   |
+| 0.0006        | 19.1327 | 7500  | 0.1409          | 0.7933    | 0.7826 | 0.7879 | 0.9827   |
+| 0.0005        | 20.4082 | 8000  | 0.1415          | 0.7886    | 0.7992 | 0.7938 | 0.9835   |
+| 0.0005        | 21.6837 | 8500  | 0.1361          | 0.7913    | 0.7930 | 0.7921 | 0.9832   |
+| 0.0004        | 22.9592 | 9000  | 0.1393          | 0.8069    | 0.8002 | 0.8035 | 0.9839   |
+| 0.0004        | 24.2347 | 9500  | 0.1376          | 0.7784    | 0.8147 | 0.7962 | 0.9835   |
+| 0.0003        | 25.5102 | 10000 | 0.1421          | 0.7862    | 0.7919 | 0.7891 | 0.9833   |
+| 0.0002        | 26.7857 | 10500 | 0.1417          | 0.7882    | 0.8054 | 0.7967 | 0.9834   |
+| 0.0002        | 28.0612 | 11000 | 0.1399          | 0.7900    | 0.7981 | 0.7940 | 0.9835   |
+| 0.0001        | 29.3367 | 11500 | 0.1413          | 0.7900    | 0.8023 | 0.7961 | 0.9836   |
+
+
+### 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_en",
+  "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": 0.37209302325581395, "recall": 0.6530612244897959, "f1": 0.47407407407407404, "accuracy": 0.9405405405405406}, "en_pud": {"precision": 0.8098933074684772, "recall": 0.7767441860465116, "f1": 0.7929724596391263, "accuracy": 0.9789384208537968}, "de_pud": {"precision": 0.781431334622824, "recall": 0.7776708373435997, "f1": 0.7795465508924265, "accuracy": 0.9758098542028034}, "pt_pud": {"precision": 0.8095684803001876, "recall": 0.7852593266606005, "f1": 0.7972286374133949, "accuracy": 0.9798778143290469}, "ru_pud": {"precision": 0.6734496124031008, "recall": 0.6708494208494209, "f1": 0.672147001934236, "accuracy": 0.9661069491087574}, "sv_pud": {"precision": 0.8372781065088757, "recall": 0.8250728862973761, "f1": 0.8311306901615271, "accuracy": 0.9827007758439924}, "tl_trg": {"precision": 0.75, "recall": 0.9130434782608695, "f1": 0.8235294117647057, "accuracy": 0.9863760217983651}, "tl_ugnayan": {"precision": 0.575, "recall": 0.696969696969697, "f1": 0.6301369863013698, "accuracy": 0.9735642661804923}, "zh_gsd": {"precision": 0.5416666666666666, "recall": 0.423728813559322, "f1": 0.4754937820043892, "accuracy": 0.9314019314019314}, "zh_gsdsimp": {"precision": 0.560200668896321, "recall": 0.43905635648754915, "f1": 0.4922850844966936, "accuracy": 0.9354811854811855}, "hr_set": {"precision": 0.800453514739229, "recall": 0.7548111190306486, "f1": 0.7769625825385178, "accuracy": 0.9726298433635614}, "da_ddt": {"precision": 0.8036649214659686, "recall": 0.6868008948545862, "f1": 0.7406513872135103, "accuracy": 0.9798463533872094}, "en_ewt": {"precision": 0.8349802371541502, "recall": 0.7766544117647058, "f1": 0.8047619047619047, "accuracy": 0.9790014742797944}, "pt_bosque": {"precision": 0.8185365853658536, "recall": 0.6905349794238683, "f1": 0.7491071428571429, "accuracy": 0.9733009708737864}, "sr_set": {"precision": 0.8207070707070707, "recall": 0.7674144037780402, "f1": 0.7931665649786455, "accuracy": 0.970492951580422}, "sk_snk": {"precision": 0.7124413145539906, "recall": 0.6633879781420765, "f1": 0.687040181097906, "accuracy": 0.9568153266331658}, "sv_talbanken": {"precision": 0.8082191780821918, "recall": 0.9030612244897959, "f1": 0.8530120481927711, "accuracy": 0.9972518035039505}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904350f19b54a46fd59749a2760963a287e452e0dd5c0c05feebc1dd818c36f3
+size 1109857804

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fce0e83005ed3cac308dc2ae8d4a397cefd831deb51a63102d7a6d77341c1448
+size 5304