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-aug1000
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.40127208828926086
+
+f1: 0.6585251291686237
+
+precision: 0.6154521510096576
+
+recall: 0.7080808080808081
+
+auc: 0.8725866639820129
+
+accuracy: 0.81825

checkpoint-2125/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-2125/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57426b4e39038e7c7cd53e0f234d11f3df865d431e798f040dbec54883582c10
+size 437958648

checkpoint-2125/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47a68a3c6d654512cf2c4782992279bd20006c086635ce0abb7423799639d1f
+size 876032762

checkpoint-2125/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea80c828fda242274420c31869cb79ef9697d9a196c824561751c1bf181c217f
+size 13990

checkpoint-2125/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a141b17ab5b122bc9546e16075353f781c23e23a8e5a1d6643d35f05d6a7b510
+size 1064

checkpoint-2125/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.40127208828926086,
+  "best_model_checkpoint": "/tmp/model/checkpoint-2125",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2125,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.703668861712135e-06,
+      "loss": 0.6976,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.40733772342427e-06,
+      "loss": 0.5756,
+      "step": 200
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.4111006585136408e-05,
+      "loss": 0.5905,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.881467544684854e-05,
+      "loss": 0.5445,
+      "step": 400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2.3518344308560677e-05,
+      "loss": 0.5061,
+      "step": 500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.8222013170272817e-05,
+      "loss": 0.4163,
+      "step": 600
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.292568203198495e-05,
+      "loss": 0.4063,
+      "step": 700
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.762935089369708e-05,
+      "loss": 0.4095,
+      "step": 800
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.233301975540922e-05,
+      "loss": 0.4238,
+      "step": 900
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.7036688617121355e-05,
+      "loss": 0.431,
+      "step": 1000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.9806525831416025e-05,
+      "loss": 0.437,
+      "step": 1100
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.9283622673080946e-05,
+      "loss": 0.4363,
+      "step": 1200
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.8760719514745873e-05,
+      "loss": 0.4071,
+      "step": 1300
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 4.8237816356410795e-05,
+      "loss": 0.4217,
+      "step": 1400
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.7714913198075716e-05,
+      "loss": 0.4258,
+      "step": 1500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.7192010039740643e-05,
+      "loss": 0.3626,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.6669106881405564e-05,
+      "loss": 0.402,
+      "step": 1700
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 4.614620372307049e-05,
+      "loss": 0.4052,
+      "step": 1800
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 4.562330056473541e-05,
+      "loss": 0.4162,
+      "step": 1900
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5100397406400334e-05,
+      "loss": 0.4147,
+      "step": 2000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.457749424806526e-05,
+      "loss": 0.4177,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.81825,
+      "eval_auc": 0.8725866639820129,
+      "eval_f1": 0.6585251291686237,
+      "eval_loss": 0.40127208828926086,
+      "eval_precision": 0.6154521510096576,
+      "eval_recall": 0.7080808080808081,
+      "eval_runtime": 648.355,
+      "eval_samples_per_second": 6.169,
+      "eval_steps_per_second": 0.386,
+      "step": 2125
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1118221985280000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2125/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f258d7d3e60c8146d7b80339d8138fe24bd0e2cb0dd36624df653df34e0f46a
+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 sha256:57426b4e39038e7c7cd53e0f234d11f3df865d431e798f040dbec54883582c10
+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 sha256:1f258d7d3e60c8146d7b80339d8138fe24bd0e2cb0dd36624df653df34e0f46a
+size 4728

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "MatteoWood/autotrain-data-bert-sexism-classifier-aug1000",
+    "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-aug1000-0",
+    "evaluation_strategy": "epoch",
+    "username": "MatteoWood",
+    "log": "none"
+}