Initial Commit

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: scenario-KD-PR-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only44
+  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-EN-D2_data-en-cardiff_eng_only44
+
+This model is a fine-tuned version of [haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only](https://huggingface.co/haryoaw/scenario-MDBT-TCR_data-en-cardiff_eng_only) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3472
+- Accuracy: 0.4854
+- F1: 0.4837
+
+## 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: 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 | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| No log        | 1.72  | 100  | 1.2889          | 0.4594   | 0.4362 |
+| No log        | 3.45  | 200  | 1.2863          | 0.4802   | 0.4774 |
+| No log        | 5.17  | 300  | 1.3275          | 0.4612   | 0.4493 |
+| No log        | 6.9   | 400  | 1.3428          | 0.4885   | 0.4874 |
+| 1.1183        | 8.62  | 500  | 1.3395          | 0.4841   | 0.4835 |
+| 1.1183        | 10.34 | 600  | 1.3621          | 0.4705   | 0.4689 |
+| 1.1183        | 12.07 | 700  | 1.3524          | 0.4643   | 0.4624 |
+| 1.1183        | 13.79 | 800  | 1.3665          | 0.4660   | 0.4617 |
+| 1.1183        | 15.52 | 900  | 1.3531          | 0.4793   | 0.4762 |
+| 0.9576        | 17.24 | 1000 | 1.3762          | 0.4669   | 0.4633 |
+| 0.9576        | 18.97 | 1100 | 1.3615          | 0.4718   | 0.4681 |
+| 0.9576        | 20.69 | 1200 | 1.3656          | 0.4691   | 0.4638 |
+| 0.9576        | 22.41 | 1300 | 1.3684          | 0.4722   | 0.4685 |
+| 0.9576        | 24.14 | 1400 | 1.3559          | 0.4740   | 0.4741 |
+| 0.9369        | 25.86 | 1500 | 1.3527          | 0.4753   | 0.4739 |
+| 0.9369        | 27.59 | 1600 | 1.3407          | 0.4762   | 0.4757 |
+| 0.9369        | 29.31 | 1700 | 1.3472          | 0.4854   | 0.4837 |
+
+
+### 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-en-cardiff_eng_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": 0.44794973157501716, "accuracy": 0.4482758620689655, "confusion_matrix": [[112, 130, 48], [73, 164, 53], [32, 144, 114]]}, "english": {"f1": 0.5873796735036003, "accuracy": 0.5908045977011495, "confusion_matrix": [[232, 47, 11], [136, 134, 20], [56, 86, 148]]}, "french": {"f1": 0.44543325045162935, "accuracy": 0.47126436781609193, "confusion_matrix": [[139, 125, 26], [47, 213, 30], [67, 165, 58]]}, "german": {"f1": 0.5398329739690245, "accuracy": 0.5413793103448276, "confusion_matrix": [[131, 98, 61], [53, 180, 57], [45, 85, 160]]}, "hindi": {"f1": 0.4605408891295803, "accuracy": 0.46551724137931033, "confusion_matrix": [[96, 107, 87], [48, 159, 83], [40, 100, 150]]}, "italian": {"f1": 0.524506437596989, "accuracy": 0.5241379310344828, "confusion_matrix": [[133, 78, 79], [37, 168, 85], [40, 95, 155]]}, "portuguese": {"f1": 0.4297719026843427, "accuracy": 0.4413793103448276, "confusion_matrix": [[72, 151, 67], [59, 179, 52], [30, 127, 133]]}, "spanish": {"f1": 0.4976053593700653, "accuracy": 0.5080459770114942, "confusion_matrix": [[161, 72, 57], [111, 89, 90], [54, 44, 192]]}, "all": {"f1": 0.50742138372139, "accuracy": 0.5066091954022989, "confusion_matrix": [[1101, 774, 445], [561, 1285, 474], [354, 826, 1140]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55aa08809bf155bef2b18813931c934d1e4957a0fe49392487f743123a27a53
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31690cc006e05f2dcab832ed9708d23402152c3e665d070ec614adb9bd7d9490
+size 4600