Upload 10 files

__huggingface_repos__.json

@@ -0,0 +1 @@
+{"repos": [{"repoId": "microsoft/deberta-base", "repoType": "model", "commitHash": "0d1b43ccf21b5acd9f4e5f7b077fa698f05cf195", "filePaths": ["config.json", "vocab.json", "pytorch_model.bin", "merges.txt", "tokenizer_config.json"]}, {"repoId": "microsoft/deberta-base", "repoType": "model", "commitHash": "315ff8e6747aba12a2074c165fcc7e47d2cec9b4", "filePaths": ["model.safetensors"]}]}

best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563fb8cb8595b47b6d1757646255fcaeb2c0d8fea587a82d763804ccd4a7b6ed
+size 556859654

classification_report.txt

@@ -0,0 +1,16 @@
+Microaggression Detection Model - Classification Report
+============================================================
+
+Model: microsoft/deberta-base
+Dataset shape: (48272, 10)
+Training samples: 38617
+Validation samples: 9655
+
+                     precision    recall  f1-score   support
+
+Not Microaggression     0.9996    0.9989    0.9993      4717
+    Microaggression     0.9990    0.9996    0.9993      4938
+
+           accuracy                         0.9993      9655
+          macro avg     0.9993    0.9993    0.9993      9655
+       weighted avg     0.9993    0.9993    0.9993      9655

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e078073bf8b7ffdb7baeae2f655e60c198f6cee61586fea0ec232af1b4b80780
+size 556799560

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "DebertaTokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "gpt2"
+}

training_config.txt

@@ -0,0 +1,13 @@
+Microaggression Detection Model - Training Configuration
+============================================================
+
+Model Name: microsoft/deberta-base
+Max Length: 128
+Batch Size: 16
+Epochs: 5
+Learning Rate: 2e-05
+Patience: 2
+Dataset Shape: (48272, 10)
+Training Samples: 38617
+Validation Samples: 9655
+Model Parameters: 139,193,858