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_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-PO-CDF-CL-D2_data-cl-cardiff_cl_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: 35.0455
+- Accuracy: 0.4421
+- F1: 0.4372
+
+## 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        | 1.09  | 250  | 22.7040         | 0.4236   | 0.4110 |
+| 23.1676       | 2.17  | 500  | 21.6418         | 0.4336   | 0.4116 |
+| 23.1676       | 3.26  | 750  | 24.6174         | 0.4267   | 0.4155 |
+| 12.9705       | 4.35  | 1000 | 27.2959         | 0.4460   | 0.4447 |
+| 12.9705       | 5.43  | 1250 | 28.1257         | 0.4375   | 0.4315 |
+| 7.1171        | 6.52  | 1500 | 27.9161         | 0.4360   | 0.4279 |
+| 7.1171        | 7.61  | 1750 | 29.9352         | 0.4383   | 0.4361 |
+| 4.3718        | 8.7   | 2000 | 34.5593         | 0.4298   | 0.4191 |
+| 4.3718        | 9.78  | 2250 | 34.0346         | 0.4421   | 0.4373 |
+| 3.4048        | 10.87 | 2500 | 33.3230         | 0.4390   | 0.4351 |
+| 3.4048        | 11.96 | 2750 | 35.1604         | 0.4367   | 0.4313 |
+| 2.4739        | 13.04 | 3000 | 33.4441         | 0.4228   | 0.4170 |
+| 2.4739        | 14.13 | 3250 | 32.9534         | 0.4367   | 0.4308 |
+| 2.0055        | 15.22 | 3500 | 34.2647         | 0.4429   | 0.4414 |
+| 2.0055        | 16.3  | 3750 | 33.4915         | 0.4460   | 0.4450 |
+| 1.4812        | 17.39 | 4000 | 35.4776         | 0.4298   | 0.4249 |
+| 1.4812        | 18.48 | 4250 | 35.4540         | 0.4375   | 0.4366 |
+| 1.299         | 19.57 | 4500 | 34.2270         | 0.4468   | 0.4467 |
+| 1.299         | 20.65 | 4750 | 34.7234         | 0.4460   | 0.4441 |
+| 0.98          | 21.74 | 5000 | 34.8872         | 0.4352   | 0.4294 |
+| 0.98          | 22.83 | 5250 | 34.8777         | 0.4383   | 0.4370 |
+| 0.7847        | 23.91 | 5500 | 35.0968         | 0.4522   | 0.4518 |
+| 0.7847        | 25.0  | 5750 | 34.3877         | 0.4329   | 0.4285 |
+| 0.6835        | 26.09 | 6000 | 35.0458         | 0.4390   | 0.4365 |
+| 0.6835        | 27.17 | 6250 | 35.2727         | 0.4360   | 0.4326 |
+| 0.5378        | 28.26 | 6500 | 33.4029         | 0.4390   | 0.4353 |
+| 0.5378        | 29.35 | 6750 | 35.0455         | 0.4421   | 0.4372 |
+
+
+### 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": 0.5197240620720346, "accuracy": 0.5287356321839081, "confusion_matrix": [[101, 93, 96], [47, 166, 77], [27, 70, 193]]}, "english": {"f1": 0.5937565896018729, "accuracy": 0.603448275862069, "confusion_matrix": [[232, 37, 21], [121, 115, 54], [56, 56, 178]]}, "french": {"f1": 0.4108960245918663, "accuracy": 0.4482758620689655, "confusion_matrix": [[104, 166, 20], [28, 239, 23], [33, 210, 47]]}, "german": {"f1": 0.6767599584491766, "accuracy": 0.6781609195402298, "confusion_matrix": [[176, 55, 59], [48, 194, 48], [31, 39, 220]]}, "hindi": {"f1": 0.4440536817957769, "accuracy": 0.4494252873563218, "confusion_matrix": [[144, 57, 89], [98, 92, 100], [75, 60, 155]]}, "italian": {"f1": 0.5894634016561572, "accuracy": 0.593103448275862, "confusion_matrix": [[128, 77, 85], [20, 194, 76], [25, 71, 194]]}, "portuguese": {"f1": 0.4806079340381193, "accuracy": 0.4862068965517241, "confusion_matrix": [[102, 97, 91], [58, 146, 86], [39, 76, 175]]}, "spanish": {"f1": 0.5642141374018236, "accuracy": 0.5689655172413793, "confusion_matrix": [[174, 69, 47], [75, 123, 92], [44, 48, 198]]}, "all": {"f1": 0.546620031340669, "accuracy": 0.5468390804597701, "confusion_matrix": [[1151, 659, 510], [502, 1294, 524], [354, 605, 1361]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31d6635517dee265ed18f720d73b86e693087b4546b974ceb929203dcf1eb22
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3543cf0fb0144607cb9d7bda3d2d51d300adce71d78a109a467cf8e5df07b4b3
+size 4600