Initial Commit

README.md

@@ -0,0 +1,88 @@
+---
+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-PO-CDF-CL-D2_data-cl-cardiff_cl_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-CL-D2_data-cl-cardiff_cl_only66
+
+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: 31.7416
+- Accuracy: 0.4560
+- F1: 0.4541
+
+## 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        | 1.09  | 250  | 19.9794         | 0.4306   | 0.4241 |
+| 22.4123       | 2.17  | 500  | 21.3481         | 0.4336   | 0.4260 |
+| 22.4123       | 3.26  | 750  | 24.4238         | 0.4560   | 0.4561 |
+| 12.6859       | 4.35  | 1000 | 25.0953         | 0.4352   | 0.4316 |
+| 12.6859       | 5.43  | 1250 | 27.9114         | 0.4360   | 0.4335 |
+| 6.8096        | 6.52  | 1500 | 29.7395         | 0.4321   | 0.4237 |
+| 6.8096        | 7.61  | 1750 | 29.6224         | 0.4360   | 0.4305 |
+| 4.5159        | 8.7   | 2000 | 31.3276         | 0.4390   | 0.4333 |
+| 4.5159        | 9.78  | 2250 | 32.6593         | 0.4398   | 0.4354 |
+| 3.2964        | 10.87 | 2500 | 33.0071         | 0.4352   | 0.4235 |
+| 3.2964        | 11.96 | 2750 | 34.0500         | 0.4352   | 0.4265 |
+| 2.4206        | 13.04 | 3000 | 33.9132         | 0.4344   | 0.4289 |
+| 2.4206        | 14.13 | 3250 | 31.9401         | 0.4576   | 0.4554 |
+| 1.78          | 15.22 | 3500 | 33.3465         | 0.4491   | 0.4410 |
+| 1.78          | 16.3  | 3750 | 33.5318         | 0.4259   | 0.4209 |
+| 1.3706        | 17.39 | 4000 | 34.5140         | 0.4583   | 0.4564 |
+| 1.3706        | 18.48 | 4250 | 32.4824         | 0.4483   | 0.4475 |
+| 1.1506        | 19.57 | 4500 | 33.5403         | 0.4460   | 0.4435 |
+| 1.1506        | 20.65 | 4750 | 33.4105         | 0.4352   | 0.4321 |
+| 0.9541        | 21.74 | 5000 | 32.5699         | 0.4468   | 0.4467 |
+| 0.9541        | 22.83 | 5250 | 32.0965         | 0.4390   | 0.4375 |
+| 0.7436        | 23.91 | 5500 | 33.0832         | 0.4290   | 0.4200 |
+| 0.7436        | 25.0  | 5750 | 31.5703         | 0.4367   | 0.4327 |
+| 0.6718        | 26.09 | 6000 | 33.3243         | 0.4313   | 0.4274 |
+| 0.6718        | 27.17 | 6250 | 32.8775         | 0.4375   | 0.4328 |
+| 0.5245        | 28.26 | 6500 | 32.0762         | 0.4437   | 0.4418 |
+| 0.5245        | 29.35 | 6750 | 31.7416         | 0.4560   | 0.4541 |
+
+
+### 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": 0.5487636664855445, "accuracy": 0.5528735632183908, "confusion_matrix": [[138, 72, 80], [73, 141, 76], [26, 62, 202]]}, "english": {"f1": 0.6081898842970522, "accuracy": 0.6195402298850575, "confusion_matrix": [[216, 28, 46], [109, 114, 67], [39, 42, 209]]}, "french": {"f1": 0.4506655910432762, "accuracy": 0.4632183908045977, "confusion_matrix": [[95, 132, 63], [23, 208, 59], [27, 163, 100]]}, "german": {"f1": 0.6451204514921933, "accuracy": 0.6494252873563219, "confusion_matrix": [[160, 35, 95], [49, 163, 78], [27, 21, 242]]}, "hindi": {"f1": 0.42293421121909186, "accuracy": 0.4413793103448276, "confusion_matrix": [[97, 41, 152], [61, 80, 149], [39, 44, 207]]}, "italian": {"f1": 0.6123113412900704, "accuracy": 0.6137931034482759, "confusion_matrix": [[154, 40, 96], [35, 161, 94], [31, 40, 219]]}, "portuguese": {"f1": 0.48163998236246214, "accuracy": 0.4942528735632184, "confusion_matrix": [[103, 71, 116], [61, 116, 113], [27, 52, 211]]}, "spanish": {"f1": 0.5250823061394478, "accuracy": 0.539080459770115, "confusion_matrix": [[170, 61, 59], [83, 90, 117], [43, 38, 209]]}, "all": {"f1": 0.5355126575777598, "accuracy": 0.5395114942528736, "confusion_matrix": [[1098, 487, 735], [476, 1068, 776], [256, 475, 1589]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ed82b8d8d76745ffd06030f49daa039c711871307eadbf35536cfa984c148f
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ca527e3c526fe996bf2124c9f19a71533761b9afcfa76fc47f429569334397
+size 4600