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-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66
+  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-PO-CDF-EN-FROM-EN-D2_data-en-cardiff_eng_only66
+
+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: 24.7382
+- Accuracy: 0.4550
+- F1: 0.4534
+
+## 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: 66
+- 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  | 15.4704         | 0.4568   | 0.4535 |
+| No log        | 3.45  | 200  | 16.0314         | 0.4669   | 0.4628 |
+| No log        | 5.17  | 300  | 19.1999         | 0.4568   | 0.4479 |
+| No log        | 6.9   | 400  | 21.8826         | 0.4546   | 0.4456 |
+| 9.984         | 8.62  | 500  | 21.4137         | 0.4572   | 0.4573 |
+| 9.984         | 10.34 | 600  | 23.3766         | 0.4396   | 0.4365 |
+| 9.984         | 12.07 | 700  | 24.2726         | 0.4475   | 0.4365 |
+| 9.984         | 13.79 | 800  | 24.3246         | 0.4502   | 0.4440 |
+| 9.984         | 15.52 | 900  | 24.9899         | 0.4634   | 0.4616 |
+| 1.9269        | 17.24 | 1000 | 24.6384         | 0.4616   | 0.4583 |
+| 1.9269        | 18.97 | 1100 | 24.3379         | 0.4493   | 0.4454 |
+| 1.9269        | 20.69 | 1200 | 24.6032         | 0.4625   | 0.4577 |
+| 1.9269        | 22.41 | 1300 | 24.1732         | 0.4608   | 0.4572 |
+| 1.9269        | 24.14 | 1400 | 25.5374         | 0.4493   | 0.4448 |
+| 0.6962        | 25.86 | 1500 | 24.3690         | 0.4563   | 0.4553 |
+| 0.6962        | 27.59 | 1600 | 24.9417         | 0.4515   | 0.4488 |
+| 0.6962        | 29.31 | 1700 | 24.7382         | 0.4550   | 0.4534 |
+
+
+### 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": 0.4324071475275681, "accuracy": 0.43908045977011495, "confusion_matrix": [[131, 137, 22], [84, 171, 35], [53, 157, 80]]}, "english": {"f1": 0.6057946230524159, "accuracy": 0.6080459770114942, "confusion_matrix": [[204, 61, 25], [98, 134, 58], [28, 71, 191]]}, "french": {"f1": 0.4083166599973322, "accuracy": 0.41954022988505746, "confusion_matrix": [[94, 155, 41], [46, 185, 59], [50, 154, 86]]}, "german": {"f1": 0.4917687806454329, "accuracy": 0.49885057471264366, "confusion_matrix": [[93, 131, 66], [40, 175, 75], [23, 101, 166]]}, "hindi": {"f1": 0.4242699551628113, "accuracy": 0.43333333333333335, "confusion_matrix": [[78, 142, 70], [42, 166, 82], [48, 109, 133]]}, "italian": {"f1": 0.4698857189645693, "accuracy": 0.47586206896551725, "confusion_matrix": [[93, 121, 76], [23, 178, 89], [28, 119, 143]]}, "portuguese": {"f1": 0.3775497809602761, "accuracy": 0.4114942528735632, "confusion_matrix": [[36, 164, 90], [27, 184, 79], [13, 139, 138]]}, "spanish": {"f1": 0.4896033849277321, "accuracy": 0.4954022988505747, "confusion_matrix": [[110, 118, 62], [64, 128, 98], [38, 59, 193]]}, "all": {"f1": 0.4764533146388188, "accuracy": 0.4783045977011494, "confusion_matrix": [[865, 1019, 436], [424, 1357, 539], [301, 912, 1107]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139a9dc4fbf83cf59459b848207d16fa84753cfec6cf448c9382f7c69759dc7e
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00776aecec59e74e2fa04f4ec0789b019d131db54845f838f5732f7d2502abb1
+size 4600