Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+tags:
+- autotrain
+- text-classification
+widget:
+- text: "I love AutoTrain"
+datasets:
+- MatteoWood/autotrain-data-bert-sexism-classifier-aug200
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.35955047607421875
+
+f1: 0.5477528089887641
+
+precision: 0.8986175115207373
+
+recall: 0.3939393939393939
+
+auc: 0.8849468102956475
+
+accuracy: 0.839

checkpoint-2025/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "_num_labels": 2,
+  "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,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2025/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0deda1e447dd37b2cfeb1b51598faf855c7f51af3d44dc0cca2ccd038885e9fa
+size 437958648

checkpoint-2025/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9dbe71af26ddfcbfba35d99ca3b28515d50850946d3903a13e1dac0b0c0f5f
+size 876032762

checkpoint-2025/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b842d13cc9d220a7a880f8336af28bb480aef0aeaff25bd82e2cad00d6f791
+size 13990

checkpoint-2025/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:724aae5e4cb898cea91e1d8aa056fca105b950d3665a6fe7ced03b700ab32db8
+size 1064

checkpoint-2025/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.35955047607421875,
+  "best_model_checkpoint": "/tmp/model/checkpoint-2025",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2025,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.93583415597236e-06,
+      "loss": 0.5941,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.87166831194472e-06,
+      "loss": 0.5625,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.4807502467917079e-05,
+      "loss": 0.5233,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.974333662388944e-05,
+      "loss": 0.443,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.46791707798618e-05,
+      "loss": 0.4222,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.9615004935834158e-05,
+      "loss": 0.4242,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.455083909180652e-05,
+      "loss": 0.4401,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.948667324777888e-05,
+      "loss": 0.3815,
+      "step": 800
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.4422507403751234e-05,
+      "loss": 0.3833,
+      "step": 900
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.93583415597236e-05,
+      "loss": 0.3968,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.952260755048288e-05,
+      "loss": 0.4156,
+      "step": 1100
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.8973880597014924e-05,
+      "loss": 0.4019,
+      "step": 1200
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.842515364354697e-05,
+      "loss": 0.3999,
+      "step": 1300
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.7876426690079015e-05,
+      "loss": 0.4215,
+      "step": 1400
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.7327699736611064e-05,
+      "loss": 0.3855,
+      "step": 1500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 4.677897278314311e-05,
+      "loss": 0.3786,
+      "step": 1600
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.6230245829675155e-05,
+      "loss": 0.415,
+      "step": 1700
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.5681518876207204e-05,
+      "loss": 0.4079,
+      "step": 1800
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5132791922739246e-05,
+      "loss": 0.4044,
+      "step": 1900
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.4584064969271295e-05,
+      "loss": 0.3671,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.839,
+      "eval_auc": 0.8849468102956475,
+      "eval_f1": 0.5477528089887641,
+      "eval_loss": 0.35955047607421875,
+      "eval_precision": 0.8986175115207373,
+      "eval_recall": 0.3939393939393939,
+      "eval_runtime": 897.0094,
+      "eval_samples_per_second": 4.459,
+      "eval_steps_per_second": 0.279,
+      "step": 2025
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10125,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1065599774208000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2025/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c5011c96c6221d3601f14e2029d12a6e12557326ba91f587068a352aac16f6
+size 4728

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "_num_labels": 2,
+  "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,
+  "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,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "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 sha256:0deda1e447dd37b2cfeb1b51598faf855c7f51af3d44dc0cca2ccd038885e9fa
+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 +1,55 @@
+{
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06c5011c96c6221d3601f14e2029d12a6e12557326ba91f587068a352aac16f6
+size 4728

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "MatteoWood/autotrain-data-bert-sexism-classifier-aug200",
+    "model": "bert-base-uncased",
+    "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,
+    "mixed_precision": null,
+    "save_total_limit": 1,
+    "save_strategy": "epoch",
+    "push_to_hub": true,
+    "repo_id": "MatteoWood/bert-sexism-classifier-aug200-0",
+    "evaluation_strategy": "epoch",
+    "username": "MatteoWood",
+    "log": "none"
+}