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_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-PR-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: 1.3348
+- Accuracy: 0.4846
+- F1: 0.4848
+
+## 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  | 1.3126          | 0.4718   | 0.4615 |
+| No log        | 3.45  | 200  | 1.3334          | 0.4638   | 0.4466 |
+| No log        | 5.17  | 300  | 1.3417          | 0.4810   | 0.4818 |
+| No log        | 6.9   | 400  | 1.3541          | 0.4766   | 0.4702 |
+| 1.1194        | 8.62  | 500  | 1.3613          | 0.4916   | 0.4913 |
+| 1.1194        | 10.34 | 600  | 1.3438          | 0.4797   | 0.4784 |
+| 1.1194        | 12.07 | 700  | 1.3501          | 0.4713   | 0.4713 |
+| 1.1194        | 13.79 | 800  | 1.3617          | 0.4687   | 0.4683 |
+| 1.1194        | 15.52 | 900  | 1.3527          | 0.4819   | 0.4812 |
+| 0.9567        | 17.24 | 1000 | 1.3561          | 0.4824   | 0.4777 |
+| 0.9567        | 18.97 | 1100 | 1.3531          | 0.4749   | 0.4732 |
+| 0.9567        | 20.69 | 1200 | 1.3379          | 0.4960   | 0.4965 |
+| 0.9567        | 22.41 | 1300 | 1.3384          | 0.4797   | 0.4793 |
+| 0.9567        | 24.14 | 1400 | 1.3404          | 0.4824   | 0.4807 |
+| 0.9355        | 25.86 | 1500 | 1.3475          | 0.4753   | 0.4755 |
+| 0.9355        | 27.59 | 1600 | 1.3409          | 0.4780   | 0.4776 |
+| 0.9355        | 29.31 | 1700 | 1.3348          | 0.4846   | 0.4848 |
+
+
+### 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": 0.5012031147151351, "accuracy": 0.5, "confusion_matrix": [[154, 88, 48], [88, 139, 63], [54, 94, 142]]}, "english": {"f1": 0.6063988927258209, "accuracy": 0.6103448275862069, "confusion_matrix": [[233, 44, 13], [117, 141, 32], [47, 86, 157]]}, "french": {"f1": 0.4786685597491703, "accuracy": 0.4850574712643678, "confusion_matrix": [[129, 115, 46], [46, 188, 56], [69, 116, 105]]}, "german": {"f1": 0.547019763815062, "accuracy": 0.5471264367816092, "confusion_matrix": [[137, 99, 54], [46, 177, 67], [39, 89, 162]]}, "hindi": {"f1": 0.473165101241564, "accuracy": 0.4747126436781609, "confusion_matrix": [[119, 60, 111], [70, 133, 87], [58, 71, 161]]}, "italian": {"f1": 0.5373080148791206, "accuracy": 0.535632183908046, "confusion_matrix": [[152, 67, 71], [32, 152, 106], [56, 72, 162]]}, "portuguese": {"f1": 0.43264816647123655, "accuracy": 0.4425287356321839, "confusion_matrix": [[77, 139, 74], [58, 173, 59], [34, 121, 135]]}, "spanish": {"f1": 0.5031761744905152, "accuracy": 0.5206896551724138, "confusion_matrix": [[186, 54, 50], [142, 74, 74], [64, 33, 193]]}, "all": {"f1": 0.5123973462914827, "accuracy": 0.5117816091954023, "confusion_matrix": [[1210, 655, 455], [605, 1135, 580], [424, 679, 1217]]}}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54bc4d3a4a52fb9fcbc036556faa6da3959e5b650a5b8debca10edc36800c2d
+size 946740394

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3064ad9337fc94fb85b568e755739455b617f2d11d54bd012b77768dd13b67b9
+size 4600