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_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-mdeberta_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: 0.1490
+- Precision: 0.8349
+- Recall: 0.8271
+- F1: 0.8310
+- Accuracy: 0.9846
+
+## 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 |
+|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0023        | 1.2755  | 500   | 0.1120          | 0.8158    | 0.8344 | 0.8250 | 0.9851   |
+| 0.0019        | 2.5510  | 1000  | 0.1055          | 0.7790    | 0.8468 | 0.8115 | 0.9840   |
+| 0.0019        | 3.8265  | 1500  | 0.1115          | 0.8134    | 0.8395 | 0.8263 | 0.9847   |
+| 0.0013        | 5.1020  | 2000  | 0.1248          | 0.7938    | 0.8251 | 0.8091 | 0.9835   |
+| 0.0016        | 6.3776  | 2500  | 0.1281          | 0.8302    | 0.8147 | 0.8224 | 0.9845   |
+| 0.0012        | 7.6531  | 3000  | 0.1241          | 0.8179    | 0.8137 | 0.8158 | 0.9841   |
+| 0.001         | 8.9286  | 3500  | 0.1191          | 0.8184    | 0.8302 | 0.8243 | 0.9842   |
+| 0.0005        | 10.2041 | 4000  | 0.1335          | 0.7951    | 0.8395 | 0.8167 | 0.9837   |
+| 0.001         | 11.4796 | 4500  | 0.1376          | 0.8125    | 0.8344 | 0.8233 | 0.9843   |
+| 0.0005        | 12.7551 | 5000  | 0.1282          | 0.8244    | 0.8313 | 0.8278 | 0.9847   |
+| 0.0007        | 14.0306 | 5500  | 0.1247          | 0.8294    | 0.8354 | 0.8324 | 0.9848   |
+| 0.0003        | 15.3061 | 6000  | 0.1440          | 0.8143    | 0.8354 | 0.8247 | 0.9841   |
+| 0.0009        | 16.5816 | 6500  | 0.1456          | 0.8384    | 0.8219 | 0.8301 | 0.9840   |
+| 0.0003        | 17.8571 | 7000  | 0.1401          | 0.8154    | 0.8416 | 0.8283 | 0.9849   |
+| 0.0002        | 19.1327 | 7500  | 0.1478          | 0.8306    | 0.8323 | 0.8314 | 0.9850   |
+| 0.0003        | 20.4082 | 8000  | 0.1448          | 0.8306    | 0.8271 | 0.8288 | 0.9850   |
+| 0.0003        | 21.6837 | 8500  | 0.1416          | 0.8240    | 0.8385 | 0.8312 | 0.9847   |
+| 0.0002        | 22.9592 | 9000  | 0.1501          | 0.8159    | 0.8395 | 0.8276 | 0.9843   |
+| 0.0001        | 24.2347 | 9500  | 0.1457          | 0.8243    | 0.8354 | 0.8298 | 0.9845   |
+| 0.0001        | 25.5102 | 10000 | 0.1474          | 0.8258    | 0.8344 | 0.8301 | 0.9846   |
+| 0.0001        | 26.7857 | 10500 | 0.1493          | 0.8244    | 0.8406 | 0.8324 | 0.9847   |
+| 0.0001        | 28.0612 | 11000 | 0.1497          | 0.8418    | 0.8209 | 0.8312 | 0.9847   |
+| 0.0001        | 29.3367 | 11500 | 0.1490          | 0.8349    | 0.8271 | 0.8310 | 0.9846   |
+
+
+### 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": 0.6666666666666666, "recall": 0.8163265306122449, "f1": 0.7339449541284403, "accuracy": 0.9791505791505791}, "en_pud": {"precision": 0.8105065666041276, "recall": 0.8037209302325582, "f1": 0.8070994862213919, "accuracy": 0.981724593879864}, "de_pud": {"precision": 0.8129218900675024, "recall": 0.8113570741097209, "f1": 0.8121387283236995, "accuracy": 0.9790445830012657}, "pt_pud": {"precision": 0.8486842105263158, "recall": 0.821656050955414, "f1": 0.8349514563106797, "accuracy": 0.9832101508095868}, "ru_pud": {"precision": 0.687382297551789, "recall": 0.7046332046332047, "f1": 0.6959008579599618, "accuracy": 0.9682769310255748}, "sv_pud": {"precision": 0.8492610837438423, "recall": 0.8377065111758989, "f1": 0.8434442270058709, "accuracy": 0.9840113231285385}, "tl_trg": {"precision": 0.84, "recall": 0.9130434782608695, "f1": 0.8749999999999999, "accuracy": 0.989100817438692}, "tl_ugnayan": {"precision": 0.6136363636363636, "recall": 0.8181818181818182, "f1": 0.7012987012987013, "accuracy": 0.9744758432087511}, "zh_gsd": {"precision": 0.6598726114649681, "recall": 0.6753585397653195, "f1": 0.6675257731958762, "accuracy": 0.9562104562104562}, "zh_gsdsimp": {"precision": 0.6817010309278351, "recall": 0.6933158584534731, "f1": 0.6874593892137751, "accuracy": 0.9591242091242091}, "hr_set": {"precision": 0.8415915915915916, "recall": 0.7990021382751248, "f1": 0.819744058500914, "accuracy": 0.9767106347897774}, "da_ddt": {"precision": 0.8055555555555556, "recall": 0.7136465324384788, "f1": 0.7568208778173191, "accuracy": 0.9817419934151451}, "en_ewt": {"precision": 0.8388888888888889, "recall": 0.8327205882352942, "f1": 0.8357933579335795, "accuracy": 0.9824281786667729}, "pt_bosque": {"precision": 0.824693685202639, "recall": 0.720164609053498, "f1": 0.7688927943760985, "accuracy": 0.9762715548471236}, "sr_set": {"precision": 0.8459657701711492, "recall": 0.8170011806375442, "f1": 0.8312312312312311, "accuracy": 0.9731196917958147}, "sk_snk": {"precision": 0.7393800229621125, "recall": 0.7038251366120218, "f1": 0.7211646136618142, "accuracy": 0.9621545226130653}, "sv_talbanken": {"precision": 0.8627450980392157, "recall": 0.8979591836734694, "f1": 0.8799999999999999, "accuracy": 0.9976934779408156}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ef55ea6b4b05b19d0dc78e9ce92319b1602fcddd712592ae6064feced696b00
+size 1112921036

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ebe666b155dc533cdefaadecd228d3fa46262d5d3373a63513628e9d1e8ec1
+size 5304