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-v2
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.36799120903015137
+
+f1: 0.7044155844155844
+
+precision: 0.7251336898395722
+
+recall: 0.6848484848484848
+
+auc: 0.8958072418537535
+
+accuracy: 0.85775

checkpoint-4000/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": "4.35.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8733aaa7e0f3c7a42c1ef7c064bc7094f816fb780ee111cd6c503f424ae6c4
+size 437958648

checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f470bf2998c0e8d633d87230a713e282edd32bcba38282866693dca946c19f6d
+size 876032762

checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b36229509c05afb8ee7115a3b492a86d4b20dc528638ebe2e8cae7ba504c2f4
+size 13990

checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ba1a3d7bc8ea483026b41d861023c364d2eb91784fcc09ebaf96b56346a6e5
+size 1064

checkpoint-4000/trainer_state.json

@@ -0,0 +1,285 @@
+{
+  "best_metric": 0.36799120903015137,
+  "best_model_checkpoint": "/tmp/model/checkpoint-4000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "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": 0.581,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1e-05,
+      "loss": 0.5379,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4945,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2e-05,
+      "loss": 0.4066,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4182,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3e-05,
+      "loss": 0.4407,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.5e-05,
+      "loss": 0.418,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4e-05,
+      "loss": 0.4258,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3885,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 5e-05,
+      "loss": 0.4283,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.4148,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.3951,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.4255,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.3842,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.4461,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.3789,
+      "step": 1600
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.6111111111111115e-05,
+      "loss": 0.3893,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 0.3833,
+      "step": 1800
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3817,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3654,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.84475,
+      "eval_auc": 0.8835736098526796,
+      "eval_f1": 0.689344672336168,
+      "eval_loss": 0.40313366055488586,
+      "eval_precision": 0.6828543111992071,
+      "eval_recall": 0.695959595959596,
+      "eval_runtime": 738.7835,
+      "eval_samples_per_second": 5.414,
+      "eval_steps_per_second": 0.338,
+      "step": 2000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.3236,
+      "step": 2100
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.3882,
+      "step": 2200
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.277777777777778e-05,
+      "loss": 0.3413,
+      "step": 2300
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 0.303,
+      "step": 2400
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.352,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 0.323,
+      "step": 2600
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.055555555555556e-05,
+      "loss": 0.3494,
+      "step": 2700
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4e-05,
+      "loss": 0.3125,
+      "step": 2800
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 3.944444444444445e-05,
+      "loss": 0.314,
+      "step": 2900
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.394,
+      "step": 3000
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.3142,
+      "step": 3100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.3179,
+      "step": 3200
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 3.722222222222222e-05,
+      "loss": 0.2756,
+      "step": 3300
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.3178,
+      "step": 3400
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.3101,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.3615,
+      "step": 3600
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 3.5e-05,
+      "loss": 0.3084,
+      "step": 3700
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 0.308,
+      "step": 3800
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 3.388888888888889e-05,
+      "loss": 0.3686,
+      "step": 3900
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3642,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.85775,
+      "eval_auc": 0.8958072418537535,
+      "eval_f1": 0.7044155844155844,
+      "eval_loss": 0.36799120903015137,
+      "eval_precision": 0.7251336898395722,
+      "eval_recall": 0.6848484848484848,
+      "eval_runtime": 782.6408,
+      "eval_samples_per_second": 5.111,
+      "eval_steps_per_second": 0.319,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2104888442880000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51de84b6cc635b4d4a2683309f35826006d7ae522a97fc7a9c1f92280e58726d
+size 4600

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": "4.35.1",
+  "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:da8733aaa7e0f3c7a42c1ef7c064bc7094f816fb780ee111cd6c503f424ae6c4
+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 sha256:51de84b6cc635b4d4a2683309f35826006d7ae522a97fc7a9c1f92280e58726d
+size 4600

training_params.json

@@ -0,0 +1 @@
+{"data_path": "MatteoWood/autotrain-data-bert-sexism-classifier-v2", "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, "fp16": false, "save_total_limit": 1, "save_strategy": "epoch", "push_to_hub": true, "repo_id": "MatteoWood/bert-sexism-classifier-v2-0", "evaluation_strategy": "epoch", "username": "MatteoWood", "log": "none"}