metacognitive_cls

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+base_model: microsoft/deberta-v3-large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+- precision
+- recall
+model-index:
+- name: metacognitive-cls
+  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. -->
+
+# metacognitive-cls
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1544
+- Accuracy: 0.9477
+- F1: 0.8277
+- Precision: 0.8781
+- Recall: 0.7827
+
+## 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: 9.946303722432942e-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 12
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
+| 0.692         | 1.0   | 61   | 0.6603          | 0.6342   | 0.2154 | 0.1642    | 0.3131 |
+| 0.5269        | 2.0   | 122  | 0.3794          | 0.8719   | 0.5059 | 0.6632    | 0.4089 |
+| 0.3652        | 3.0   | 183  | 0.3409          | 0.8770   | 0.4737 | 0.7552    | 0.3450 |
+| 0.3282        | 4.0   | 244  | 0.3081          | 0.8940   | 0.5586 | 0.8397    | 0.4185 |
+| 0.2936        | 5.0   | 305  | 0.2756          | 0.9022   | 0.5892 | 0.9013    | 0.4377 |
+| 0.2529        | 6.0   | 366  | 0.2550          | 0.9129   | 0.6805 | 0.8265    | 0.5783 |
+| 0.2141        | 7.0   | 427  | 0.2388          | 0.9221   | 0.7361 | 0.8061    | 0.6773 |
+| 0.1802        | 8.0   | 488  | 0.2059          | 0.9278   | 0.7413 | 0.8707    | 0.6454 |
+| 0.1494        | 9.0   | 549  | 0.2064          | 0.9221   | 0.7532 | 0.7657    | 0.7412 |
+| 0.1179        | 10.0  | 610  | 0.1786          | 0.9401   | 0.8098 | 0.8245    | 0.7955 |
+| 0.0941        | 11.0  | 671  | 0.1589          | 0.9457   | 0.8227 | 0.8632    | 0.7859 |
+| 0.0816        | 12.0  | 732  | 0.1544          | 0.9477   | 0.8277 | 0.8781    | 0.7827 |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Rewrite",
+    "1": "Highlight",
+    "2": "Summarize",
+    "3": "Quizzing",
+    "4": "Examples",
+    "5": "Comparisons",
+    "6": "Explain",
+    "7": "MA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Comparisons": 5,
+    "Examples": 4,
+    "Explain": 6,
+    "Highlight": 1,
+    "MA": 7,
+    "Quizzing": 3,
+    "Rewrite": 0,
+    "Summarize": 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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "multi_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3f17fcca4ae846c00dec3e0ac779afd01f451abc2cd76ed4a58471bfc6d6e3
+size 1740329048

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 2056,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e217f4e297dfb519e3c206b7733d029f44b52ed101fc5ab95e8a72e8312c951
+size 5048