Initial Commit

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: scenario-KD-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only55
+  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-PR-CDF-EN-FROM-CL-D2_data-en-cardiff_eng_only55
+
+This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3279
+- Accuracy: 0.4881
+- F1: 0.4855
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 55
+- 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 | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.72  | 100  | 1.3136          | 0.4599   | 0.4267 |
+| No log        | 3.45  | 200  | 1.4057          | 0.4506   | 0.4056 |
+| No log        | 5.17  | 300  | 1.3382          | 0.4797   | 0.4752 |
+| No log        | 6.9   | 400  | 1.3472          | 0.4890   | 0.4858 |
+| 1.1235        | 8.62  | 500  | 1.3400          | 0.4863   | 0.4865 |
+| 1.1235        | 10.34 | 600  | 1.3593          | 0.4837   | 0.4776 |
+| 1.1235        | 12.07 | 700  | 1.3787          | 0.4638   | 0.4526 |
+| 1.1235        | 13.79 | 800  | 1.3508          | 0.4868   | 0.4853 |
+| 1.1235        | 15.52 | 900  | 1.3393          | 0.4912   | 0.4895 |
+| 0.9596        | 17.24 | 1000 | 1.3570          | 0.4802   | 0.4693 |
+| 0.9596        | 18.97 | 1100 | 1.3359          | 0.4929   | 0.4905 |
+| 0.9596        | 20.69 | 1200 | 1.3386          | 0.4846   | 0.4816 |
+| 0.9596        | 22.41 | 1300 | 1.3372          | 0.4916   | 0.4903 |
+| 0.9596        | 24.14 | 1400 | 1.3271          | 0.4956   | 0.4932 |
+| 0.9384        | 25.86 | 1500 | 1.3313          | 0.4921   | 0.4913 |
+| 0.9384        | 27.59 | 1600 | 1.3341          | 0.4907   | 0.4897 |
+| 0.9384        | 29.31 | 1700 | 1.3279          | 0.4881   | 0.4855 |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "haryoaw/scenario-MDBT-TCR_data-cl-cardiff_cl_only",
+  "architectures": [
+    "DebertaForSequenceClassificationKD"
+  ],
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.33.3",
+  "type_vocab_size": 0,
+  "vocab_size": 251000
+}

eval_results_cardiff.json

@@ -0,0 +1 @@
+{"arabic": {"f1": 0.4971009552168196, "accuracy": 0.5, "confusion_matrix": [[191, 81, 18], [132, 135, 23], [103, 78, 109]]}, "english": {"f1": 0.59591337327029, "accuracy": 0.6011494252873564, "confusion_matrix": [[231, 43, 16], [118, 134, 38], [57, 75, 158]]}, "french": {"f1": 0.42712253677008477, "accuracy": 0.45517241379310347, "confusion_matrix": [[135, 135, 20], [60, 208, 22], [72, 165, 53]]}, "german": {"f1": 0.5737966513684558, "accuracy": 0.5770114942528736, "confusion_matrix": [[155, 101, 34], [42, 214, 34], [45, 112, 133]]}, "hindi": {"f1": 0.48973802418661555, "accuracy": 0.49195402298850577, "confusion_matrix": [[118, 105, 67], [57, 169, 64], [56, 93, 141]]}, "italian": {"f1": 0.5685132027618679, "accuracy": 0.5781609195402299, "confusion_matrix": [[230, 35, 25], [74, 149, 67], [108, 58, 124]]}, "portuguese": {"f1": 0.4978849681994417, "accuracy": 0.49885057471264366, "confusion_matrix": [[121, 134, 35], [70, 183, 37], [58, 102, 130]]}, "spanish": {"f1": 0.5209822031739703, "accuracy": 0.5183908045977011, "confusion_matrix": [[169, 96, 25], [107, 136, 47], [66, 78, 146]]}, "all": {"f1": 0.5284687008618958, "accuracy": 0.5298850574712644, "confusion_matrix": [[1379, 706, 235], [661, 1321, 338], [597, 735, 988]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cde461882acda862782975160da1875570758bbc881a8b5f643dded021f137
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4b256f02938f1e11a8c26c7f4129bb3ac647b45445df28513c3ee01ae7baca
+size 4600