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-mdeberta_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-non-kd-pre-ner-full-mdeberta_data-univner_en66
+
+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: 0.1455
+- Precision: 0.8256
+- Recall: 0.8333
+- F1: 0.8295
+- Accuracy: 0.9850
+
+## 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0025        | 1.2755  | 500   | 0.1138          | 0.8395    | 0.8230 | 0.8312 | 0.9849   |
+| 0.002         | 2.5510  | 1000  | 0.1150          | 0.8157    | 0.8292 | 0.8224 | 0.9849   |
+| 0.0023        | 3.8265  | 1500  | 0.1137          | 0.8212    | 0.8416 | 0.8313 | 0.9852   |
+| 0.0015        | 5.1020  | 2000  | 0.1171          | 0.8197    | 0.8520 | 0.8355 | 0.9851   |
+| 0.001         | 6.3776  | 2500  | 0.1206          | 0.7990    | 0.8437 | 0.8207 | 0.9839   |
+| 0.0013        | 7.6531  | 3000  | 0.1177          | 0.8233    | 0.8251 | 0.8242 | 0.9849   |
+| 0.001         | 8.9286  | 3500  | 0.1177          | 0.8399    | 0.8199 | 0.8298 | 0.9855   |
+| 0.0005        | 10.2041 | 4000  | 0.1209          | 0.8253    | 0.8313 | 0.8283 | 0.9851   |
+| 0.0007        | 11.4796 | 4500  | 0.1285          | 0.8175    | 0.8116 | 0.8145 | 0.9843   |
+| 0.0003        | 12.7551 | 5000  | 0.1335          | 0.8445    | 0.8095 | 0.8266 | 0.9850   |
+| 0.0006        | 14.0306 | 5500  | 0.1371          | 0.7810    | 0.8344 | 0.8068 | 0.9829   |
+| 0.0008        | 15.3061 | 6000  | 0.1322          | 0.8173    | 0.8427 | 0.8298 | 0.9844   |
+| 0.0005        | 16.5816 | 6500  | 0.1271          | 0.8203    | 0.8364 | 0.8283 | 0.9850   |
+| 0.0007        | 17.8571 | 7000  | 0.1200          | 0.8153    | 0.8499 | 0.8322 | 0.9854   |
+| 0.0002        | 19.1327 | 7500  | 0.1321          | 0.8193    | 0.8354 | 0.8273 | 0.9846   |
+| 0.0003        | 20.4082 | 8000  | 0.1355          | 0.8050    | 0.8375 | 0.8209 | 0.9846   |
+| 0.0002        | 21.6837 | 8500  | 0.1413          | 0.808     | 0.8364 | 0.8220 | 0.9841   |
+| 0.0003        | 22.9592 | 9000  | 0.1327          | 0.8321    | 0.8416 | 0.8369 | 0.9855   |
+| 0.0001        | 24.2347 | 9500  | 0.1412          | 0.8276    | 0.8251 | 0.8263 | 0.9847   |
+| 0.0001        | 25.5102 | 10000 | 0.1427          | 0.8199    | 0.8344 | 0.8271 | 0.9849   |
+| 0.0001        | 26.7857 | 10500 | 0.1429          | 0.8304    | 0.8261 | 0.8282 | 0.9852   |
+| 0.0001        | 28.0612 | 11000 | 0.1446          | 0.8250    | 0.8344 | 0.8296 | 0.9852   |
+| 0.0001        | 29.3367 | 11500 | 0.1455          | 0.8256    | 0.8333 | 0.8295 | 0.9850   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "haryoaw/scenario-TCR-NER_data-univner_en",
+  "architectures": [
+    "DebertaV2ForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

eval_result_ner.json

@@ -0,0 +1 @@
+{"ceb_gja": {"precision": 0.7818181818181819, "recall": 0.8775510204081632, "f1": 0.8269230769230769, "accuracy": 0.9861003861003861}, "en_pud": {"precision": 0.8064211520302171, "recall": 0.7944186046511628, "f1": 0.8003748828491095, "accuracy": 0.9805440120891575}, "de_pud": {"precision": 0.7988338192419825, "recall": 0.7911453320500481, "f1": 0.7949709864603483, "accuracy": 0.9771693779007079}, "pt_pud": {"precision": 0.8453510436432637, "recall": 0.8107370336669699, "f1": 0.8276823037621922, "accuracy": 0.98167214935703}, "ru_pud": {"precision": 0.6912751677852349, "recall": 0.6959459459459459, "f1": 0.6936026936026937, "accuracy": 0.9666752777060191}, "sv_pud": {"precision": 0.8497512437810946, "recall": 0.8299319727891157, "f1": 0.8397246804326451, "accuracy": 0.9829104634095198}, "tl_trg": {"precision": 0.9130434782608695, "recall": 0.9130434782608695, "f1": 0.9130434782608695, "accuracy": 0.9945504087193461}, "tl_ugnayan": {"precision": 0.675, "recall": 0.8181818181818182, "f1": 0.7397260273972603, "accuracy": 0.9790337283500455}, "zh_gsd": {"precision": 0.6057347670250897, "recall": 0.6610169491525424, "f1": 0.6321695760598505, "accuracy": 0.9517149517149517}, "zh_gsdsimp": {"precision": 0.6147342995169082, "recall": 0.6671035386631717, "f1": 0.6398491514770585, "accuracy": 0.9512154512154513}, "hr_set": {"precision": 0.8172205438066465, "recall": 0.7712045616535994, "f1": 0.7935460212687936, "accuracy": 0.9731244847485573}, "da_ddt": {"precision": 0.7960199004975125, "recall": 0.7158836689038032, "f1": 0.7538280329799765, "accuracy": 0.9813429113040008}, "en_ewt": {"precision": 0.8409728718428437, "recall": 0.8262867647058824, "f1": 0.833565136764024, "accuracy": 0.9823484878670757}, "pt_bosque": {"precision": 0.8317843866171004, "recall": 0.7366255144032922, "f1": 0.7813182016586644, "accuracy": 0.9756919287059846}, "sr_set": {"precision": 0.8424317617866005, "recall": 0.8016528925619835, "f1": 0.821536600120992, "accuracy": 0.9718938796952982}, "sk_snk": {"precision": 0.7617924528301887, "recall": 0.7060109289617487, "f1": 0.7328417470221215, "accuracy": 0.9621545226130653}, "sv_talbanken": {"precision": 0.8564356435643564, "recall": 0.8826530612244898, "f1": 0.8693467336683417, "accuracy": 0.9973008784413799}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18ba9beded0a1ce9d4711da2b71551cc8a0aa0912210513c1eb0d55e72d966f0
+size 1112921036

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e90903c94486eb940ceacd15f6c68e9e901be4577d270bf4a07f3f1bd631c27a
+size 5304