Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- MatteoWood/autotrain-data-hatebert-sexism-classifier
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.3898809254169464
+
+f1: 0.7137662337662338
+
+precision: 0.73475935828877
+
+recall: 0.693939393939394
+
+auc: 0.8955589113728649
+
+accuracy: 0.86225

checkpoint-2000/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "GroNLP/hateBERT",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfc68ade2a57582899e85852a82e32218e50c18e852c5d945b50a32147e3d74
+size 437958648

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb798d8df7e8cd12ffa1d129e698c3b78db99c37ce40390d45a315dba2552cc6
+size 876032762

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3455de9519cb2af9764292422f4bdb76186276849e12e0620a1920380b40bfd0
+size 13990

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e03df1c7dbec372c494fe8e69c69d1b862d9c4cfe90f66f78b5e436c89b27e5
+size 1064

checkpoint-2000/trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": 0.3898809254169464,
+  "best_model_checkpoint": "/tmp/model/checkpoint-2000",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 5e-06,
+      "loss": 0.7412,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1e-05,
+      "loss": 0.5394,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4858,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2e-05,
+      "loss": 0.4178,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.5e-05,
+      "loss": 0.3928,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3e-05,
+      "loss": 0.4125,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.5e-05,
+      "loss": 0.3896,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4e-05,
+      "loss": 0.3878,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3794,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5e-05,
+      "loss": 0.4038,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.399,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.393,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.4145,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.3391,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.4212,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.3693,
+      "step": 1600
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.6111111111111115e-05,
+      "loss": 0.3795,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 0.368,
+      "step": 1800
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3376,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3751,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.86225,
+      "eval_auc": 0.8955589113728649,
+      "eval_f1": 0.7137662337662338,
+      "eval_loss": 0.3898809254169464,
+      "eval_precision": 0.73475935828877,
+      "eval_recall": 0.693939393939394,
+      "eval_runtime": 640.7343,
+      "eval_samples_per_second": 6.243,
+      "eval_steps_per_second": 0.39,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1052444221440000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f8942a5e206856a430ea8cefa9ac99f9fd1491cf95d0fb7f4ee500f420c50e
+size 4600

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "GroNLP/hateBERT",
+  "_num_labels": 2,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfc68ade2a57582899e85852a82e32218e50c18e852c5d945b50a32147e3d74
+size 437958648

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6f8942a5e206856a430ea8cefa9ac99f9fd1491cf95d0fb7f4ee500f420c50e
+size 4600

training_params.json

@@ -0,0 +1 @@
+{"data_path": "MatteoWood/autotrain-data-hatebert-sexism-classifier", "model": "GroNLP/hateBERT", "lr": 5e-05, "epochs": 5, "max_seq_length": 128, "batch_size": 8, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "train_split": "train", "valid_split": "validation", "text_column": "autotrain_text", "target_column": "autotrain_label", "logging_steps": -1, "project_name": "/tmp/model", "auto_find_batch_size": false, "fp16": false, "save_total_limit": 1, "save_strategy": "epoch", "push_to_hub": true, "repo_id": "MatteoWood/hatebert-sexism-classifier-0", "evaluation_strategy": "epoch", "username": "MatteoWood", "log": "none"}