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_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-CL-D2_data-en-cardiff_eng_only44
+
+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: 1.3448
+- Accuracy: 0.4780
+- F1: 0.4765
+
+## 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  | 1.3140          | 0.4810   | 0.4710 |
+| No log        | 3.45  | 200  | 1.3058          | 0.4859   | 0.4712 |
+| No log        | 5.17  | 300  | 1.3692          | 0.4810   | 0.4758 |
+| No log        | 6.9   | 400  | 1.3751          | 0.4872   | 0.4822 |
+| 1.1234        | 8.62  | 500  | 1.3743          | 0.4780   | 0.4771 |
+| 1.1234        | 10.34 | 600  | 1.3539          | 0.4757   | 0.4743 |
+| 1.1234        | 12.07 | 700  | 1.3873          | 0.4709   | 0.4680 |
+| 1.1234        | 13.79 | 800  | 1.3612          | 0.4819   | 0.4821 |
+| 1.1234        | 15.52 | 900  | 1.3503          | 0.4956   | 0.4957 |
+| 0.9609        | 17.24 | 1000 | 1.3617          | 0.4841   | 0.4841 |
+| 0.9609        | 18.97 | 1100 | 1.3602          | 0.4877   | 0.4849 |
+| 0.9609        | 20.69 | 1200 | 1.3520          | 0.4881   | 0.4864 |
+| 0.9609        | 22.41 | 1300 | 1.3598          | 0.4802   | 0.4738 |
+| 0.9609        | 24.14 | 1400 | 1.3580          | 0.4722   | 0.4679 |
+| 0.9422        | 25.86 | 1500 | 1.3409          | 0.4797   | 0.4797 |
+| 0.9422        | 27.59 | 1600 | 1.3385          | 0.4903   | 0.4888 |
+| 0.9422        | 29.31 | 1700 | 1.3448          | 0.4780   | 0.4765 |
+
+
+### 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": 0.5241583746342374, "accuracy": 0.5333333333333333, "confusion_matrix": [[160, 59, 71], [103, 103, 84], [55, 34, 201]]}, "english": {"f1": 0.6211458947087118, "accuracy": 0.6229885057471264, "confusion_matrix": [[218, 54, 18], [91, 147, 52], [36, 77, 177]]}, "french": {"f1": 0.45101839231782376, "accuracy": 0.46781609195402296, "confusion_matrix": [[139, 124, 27], [49, 197, 44], [76, 143, 71]]}, "german": {"f1": 0.5601124993407652, "accuracy": 0.5597701149425287, "confusion_matrix": [[156, 88, 46], [55, 178, 57], [50, 87, 153]]}, "hindi": {"f1": 0.45527997069726256, "accuracy": 0.46436781609195404, "confusion_matrix": [[98, 72, 120], [49, 115, 126], [35, 64, 191]]}, "italian": {"f1": 0.5645135270940971, "accuracy": 0.5666666666666667, "confusion_matrix": [[195, 47, 48], [59, 149, 82], [78, 63, 149]]}, "portuguese": {"f1": 0.46822152728258803, "accuracy": 0.4747126436781609, "confusion_matrix": [[93, 145, 52], [56, 185, 49], [43, 112, 135]]}, "spanish": {"f1": 0.536485743383544, "accuracy": 0.5367816091954023, "confusion_matrix": [[140, 102, 48], [70, 145, 75], [41, 67, 182]]}, "all": {"f1": 0.5318703062000898, "accuracy": 0.5311781609195402, "confusion_matrix": [[1204, 684, 432], [514, 1251, 555], [412, 666, 1242]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b0c94e800cc757d3f7fa576bfffde4dd3589ee88b955fd8701bbf5f08a2aef
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f2be308e27b01a78c542169a93dbc2261ef9922ab6ecee63d2413e1f5559b2
+size 4600