Initial commit of my Gradio NLP app

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+import torch
+
+# Load the saved models and tokenizers
+model_roberta = AutoModelForSequenceClassification.from_pretrained("./models/roberta-base-offensive")
+tokenizer_roberta = AutoTokenizer.from_pretrained("./models/roberta-base-offensive")
+
+model_distilbert = AutoModelForSequenceClassification.from_pretrained("./models/distilbert-base-uncased-offensive")
+tokenizer_distilbert = AutoTokenizer.from_pretrained("./models/distilbert-base-uncased-offensive")
+
+model_deberta = AutoModelForSequenceClassification.from_pretrained("./models/deberta-offensive")
+tokenizer_deberta = AutoTokenizer.from_pretrained("./models/deberta-offensive")
+
+model_bert = AutoModelForSequenceClassification.from_pretrained("./models/bert-offensive")
+tokenizer_bert = AutoTokenizer.from_pretrained("./models/bert-offensive")
+
+# Arabic saved Models and tokenizers
+model_arbert = AutoModelForSequenceClassification.from_pretrained("./models/UBC-NLP/ARBERT")
+tokenizer_arbert = AutoTokenizer.from_pretrained("./models/UBC-NLP/ARBERT")
+
+model_marbert = AutoModelForSequenceClassification.from_pretrained("./models/UBC-NLP/MARBERT")
+tokenizer_marbert = AutoTokenizer.from_pretrained("./models/UBC-NLP/MARBERT")
+
+def predict(tweet, model_choice):
+    if model_choice == "RoBERTa":
+        model = model_roberta
+        tokenizer = tokenizer_roberta
+    elif model_choice == "DistilBERT":
+        model = model_distilbert
+        tokenizer = tokenizer_distilbert
+    elif model_choice == "ARBERT":
+        model = model_arbert
+        tokenizer = tokenizer_arbert
+    elif model_choice == "MARBERT":
+        model = model_marbert
+        tokenizer = tokenizer_marbert
+    elif model_choice == "DeBERTa":
+        model = model_deberta
+        tokenizer = tokenizer_deberta
+    elif model_choice == "BERT":
+        model = model_bert
+        tokenizer = tokenizer_bert
+    else:
+        return "Model not selected", "Please select a model."
+    
+    encoded_input = tokenizer.encode(tweet, return_tensors='pt', truncation=True, max_length=512, padding=True)
+    with torch.no_grad():
+        output = model(encoded_input)
+        logits = output.logits
+        probabilities = torch.softmax(logits, dim=-1)
+        prediction_index = probabilities.argmax().item()
+    
+    prediction_map = {0: "Not Offensive", 1: "Offensive"}
+    prediction = prediction_map[prediction_index]
+    confidence = probabilities[0, prediction_index].item()
+    
+    return prediction, f"Confidence: {confidence:.4f}"
+
+def app_interface():
+    with gr.Blocks() as app:
+        gr.Markdown("## Offensive Language Detection")
+        gr.Markdown("### Instructions:")
+        gr.Markdown("1. Select the language of the text.\n2. Choose a model corresponding to the selected language:\n   - For **English**: BERT, DeBERTa, RoBERTa, or DistilBERT\n   - For **Tunisian Arabic**: ARBERT or MARBERT")
+        with gr.Row():
+            language = gr.Radio(["English", "Tunisian Arabic"], label="Choose Language")
+        with gr.Row():
+            model_choice = gr.Dropdown(["RoBERTa", "DistilBERT", "ARBERT", "MARBERT", "DeBERTa", "BERT"], label="Choose Model")
+        with gr.Row():
+            tweet = gr.Textbox(lines=4, placeholder="Enter your text here...", label="Text")
+            submit_btn = gr.Button("Predict")
+        with gr.Row():
+            prediction = gr.Textbox(label="Prediction")
+            confidence = gr.Textbox(label="Confidence")
+
+        submit_btn.click(fn=predict, inputs=[tweet, model_choice], outputs=[prediction, confidence])
+
+    return app
+
+app = app_interface()
+app.launch()

models/UBC-NLP/ARBERT/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "UBC-NLP/ARBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

models/UBC-NLP/ARBERT/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5721a08143fe631ff017403f0a526b5d570444ebab9af55869f50815112efd5
+size 651395072

models/UBC-NLP/ARBERT/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/UBC-NLP/ARBERT/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/UBC-NLP/MARBERT/config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "UBC-NLP/MARBERT",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 100000
+}

models/UBC-NLP/MARBERT/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874e85391a27658550ccfde41216bf0d1bf732472e4461d8ba7876a4dcd1b2c6
+size 651395072

models/UBC-NLP/MARBERT/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/UBC-NLP/MARBERT/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-1000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

models/bert-offensive/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd658ae002182ad99ffbb9982d5d85515c0c49949eac2d6d4eb86c479d67955b
+size 437958648

models/bert-offensive/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c5eb3685348006d842a33f8c23a222816e6efa7e3dbf1212516a44add594c0
+size 876038394

models/bert-offensive/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ed3ecad87f77a0ed60753e4ffd969dbef607419cab5d7c3471fc6b16360766
+size 14244

models/bert-offensive/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cdc454fd78e2054130f997d6bf748bc81368c748607a351ea7de15a408d26e6
+size 1064

models/bert-offensive/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-1000/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6711409395973155,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.309788227081299,
+      "learning_rate": 4.440715883668904e-05,
+      "loss": 0.5291,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 8.38113784790039,
+      "learning_rate": 3.881431767337807e-05,
+      "loss": 0.4834,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4470,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 423493688042880.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

models/bert-offensive/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff52faf0d3a27635d14f511f07bc80871b57c3a7826358862dda78696619e8f5
+size 4856

models/bert-offensive/checkpoint-1500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

models/bert-offensive/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13c8461e29b1c84d3992da1258c4e67c9df1faa1b7d2a6d3866c8b4ab31264e
+size 437958648

models/bert-offensive/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a5c46aedd4909a23c89b0d3396dc7938f781b6289de190c8bb1fa275715998e
+size 876038394

models/bert-offensive/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a5e93a639b18c5080b3206380db8bdf3c9bf762e376ba68470d9bd63251d88
+size 14244

models/bert-offensive/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bd70d973811a00199980200e5162073c3f4bfdfc513c94464ee46ef32af9473
+size 1064

models/bert-offensive/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-1500/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0067114093959733,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.309788227081299,
+      "learning_rate": 4.440715883668904e-05,
+      "loss": 0.5291,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 8.38113784790039,
+      "learning_rate": 3.881431767337807e-05,
+      "loss": 0.4834,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8244186046511628,
+      "eval_f1": 0.700990099009901,
+      "eval_loss": 0.40849873423576355,
+      "eval_precision": 0.6679245283018868,
+      "eval_recall": 0.7375,
+      "eval_runtime": 1.415,
+      "eval_samples_per_second": 607.771,
+      "eval_steps_per_second": 76.325,
+      "step": 1490
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 4.857753753662109,
+      "learning_rate": 3.3221476510067115e-05,
+      "loss": 0.4743,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4470,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 635261087615520.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

models/bert-offensive/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff52faf0d3a27635d14f511f07bc80871b57c3a7826358862dda78696619e8f5
+size 4856

models/bert-offensive/checkpoint-2000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

models/bert-offensive/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d84caca90c708c6d9b08f796f62f3fe3770d1ebbe5dc4708d787c870652e882a
+size 437958648

models/bert-offensive/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f977dfb26bf16852ccff9864f65c99dfca153be14bcd7280af5f7a05a0d808
+size 876038394

models/bert-offensive/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57db07813490de347f6b29da476f84f897496ba4cc251212c6d017a619dce80
+size 14244

models/bert-offensive/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd68bf4dff9924c9178e7ecdd91ec247aec55edc72b3ca0231603fd33cef86d3
+size 1064

models/bert-offensive/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

models/bert-offensive/checkpoint-2000/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.342281879194631,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "grad_norm": 3.309788227081299,
+      "learning_rate": 4.440715883668904e-05,
+      "loss": 0.5291,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 8.38113784790039,
+      "learning_rate": 3.881431767337807e-05,
+      "loss": 0.4834,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8244186046511628,
+      "eval_f1": 0.700990099009901,
+      "eval_loss": 0.40849873423576355,
+      "eval_precision": 0.6679245283018868,
+      "eval_recall": 0.7375,
+      "eval_runtime": 1.415,
+      "eval_samples_per_second": 607.771,
+      "eval_steps_per_second": 76.325,
+      "step": 1490
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 4.857753753662109,
+      "learning_rate": 3.3221476510067115e-05,
+      "loss": 0.4743,
+      "step": 1500
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 20.212223052978516,
+      "learning_rate": 2.7628635346756153e-05,
+      "loss": 0.3753,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4470,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 846855820558080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

models/bert-offensive/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff52faf0d3a27635d14f511f07bc80871b57c3a7826358862dda78696619e8f5
+size 4856

models/bert-offensive/checkpoint-2500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

models/bert-offensive/checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58457eeb8339abe1f0ee26937443a95a8a25aae3c4fe5f569327ab3fd87f48c
+size 437958648

models/bert-offensive/checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77406637943250708e3999e599a8b10ef39a486f27cfa07a01bbff9f9a76e71b
+size 876038394

models/bert-offensive/checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccff0626d2d12f751c557becd9d0ba8acfabed972b2c6065108c51d3e8d4d12
+size 14244