Initial Commit

README.md

@@ -0,0 +1,89 @@
+---
+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-kd-scr-ner-full-mdeberta_data-univner_full55
+  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-mdeberta_data-univner_full55
+
+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: nan
+- Precision: 0.0
+- Recall: 0.0
+- F1: 0.0
+- Accuracy: 0.9241
+
+## 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: 55
+- 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 |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:---:|:--------:|
+| 72900804.608  | 0.2911 | 500   | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 0.5822 | 1000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 0.8732 | 1500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 1.1643 | 2000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 1.4554 | 2500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 1.7465 | 3000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 2.0375 | 3500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 2.3286 | 4000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 2.6197 | 4500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 2.9108 | 5000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 3.2019 | 5500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 3.4929 | 6000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 3.7840 | 6500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 4.0751 | 7000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 4.3662 | 7500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 4.6573 | 8000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 4.9483 | 8500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 5.2394 | 9000  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 5.5305 | 9500  | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 5.8216 | 10000 | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+| 0.0           | 6.1126 | 10500 | nan             | 0.0       | 0.0    | 0.0 | 0.9241   |
+
+
+### 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_full",
+  "architectures": [
+    "DebertaForTokenClassificationKD"
+  ],
+  "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": 6,
+  "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": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9606177606177606}, "en_pud": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9260955799017756}, "de_pud": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9299142093666495}, "pt_pud": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9310035459477934}, "ru_pud": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9235856367863601}, "sv_pud": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9247221639756762}, "tl_trg": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9673024523160763}, "tl_ugnayan": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9525979945305378}, "zh_gsd": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.8823676323676324}, "zh_gsdsimp": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.8828671328671329}, "hr_set": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9144270403957131}, "da_ddt": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9357477801057568}, "en_ewt": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9330995736542216}, "pt_bosque": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9222576438197363}, "sr_set": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.8929165572191577}, "sk_snk": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.8910961055276382}, "sv_talbanken": {"precision": 0.0, "recall": 0.0, "f1": 0.0, "accuracy": 0.9881729400795014}}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17e1b58722cbfa169073c590fa2d17fb6cba0d515b0020d5211ca6310aad01a
+size 972678148

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7644a8a614266dd19e11dceb31c5a835c7d0995191644c59f9fe70d1f71d7c49
+size 5304