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-large-sexism-classifier
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.5597109794616699
+
+f1: 0.0
+
+precision: 0.0
+
+recall: 0.0
+
+auc: 0.3925796167656633
+
+accuracy: 0.7525

checkpoint-2000/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-large-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": 1024,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:32a939ba112482a8129e83452a60c42ca929cae94e0b7cb407d2d2acba2a95c8
+size 1340622760

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d804e1d39fee4b58daa08dedf707a1330edad329054a9218fcd3f9fa4a6a8494
+size 2681469421

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8279f59023299a860dc107777f9ab255386203ea2ea8c6c01da6567232b935
+size 13990

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d119c4c5d23cce317bdeb70b767b03f526edd402ce6be035d0fe238cf760b74a
+size 1064

checkpoint-2000/trainer_state.json

@@ -0,0 +1,152 @@
+{
+  "best_metric": 0.5597109794616699,
+  "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": 8.333333333333334e-06,
+      "loss": 0.6258,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.541,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5089,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5764,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.594,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5e-05,
+      "loss": 0.5734,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.5597,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.6287,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.5691,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.5908,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.5939,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5421,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.579,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.5718,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5933,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.5588,
+      "step": 1600
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.5778,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.5536,
+      "step": 1800
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.5748,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.5504,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7525,
+      "eval_auc": 0.3925796167656633,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5597109794616699,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3049.9931,
+      "eval_samples_per_second": 1.311,
+      "eval_steps_per_second": 0.082,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6000,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3727725453312000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f608d1443e276752559b2288c42ab31264db79304459bb8a6a65ae43047283
+size 4600

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-large-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": 1024,
+  "id2label": {
+    "0": "not sexist",
+    "1": "sexist"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "not sexist": 0,
+    "sexist": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:32a939ba112482a8129e83452a60c42ca929cae94e0b7cb407d2d2acba2a95c8
+size 1340622760

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 sha256:40f608d1443e276752559b2288c42ab31264db79304459bb8a6a65ae43047283
+size 4600

training_params.json

@@ -0,0 +1 @@
+{"data_path": "MatteoWood/autotrain-data-bert-large-sexism-classifier", "model": "bert-large-uncased", "lr": 5e-05, "epochs": 3, "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-large-sexism-classifier-0", "evaluation_strategy": "epoch", "username": "MatteoWood", "log": "none"}