Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: google-bert/bert-base-uncased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.4558769166469574
+
+f1: 0.8207547169811321
+
+precision: 0.7837837837837838
+
+recall: 0.8613861386138614
+
+auc: 0.884088408840884
+
+accuracy: 0.81

checkpoint-100/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 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": "4.43.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbf7e7fe25bd434025d06d11a7e2e86ef65d03b60d99d811b4a2e048fd34a30
+size 437958648

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f07e5e7e2007dd33ebec8074d52afc944ffdd9e1885c2dfd1acc3ea706d36b
+size 876032762

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18960c194b39c1c762e07eaeaf2c6bd3d4e437ef57953721af826bd8bfce0b40
+size 13990

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d035e61f1c66cd4befda09e39359b5d11abe5b64d7c41726de679803569f208e
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": 0.4558769166469574,
+  "best_model_checkpoint": "autotrain-hajarhammadi/checkpoint-100",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 10.27597713470459,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.8126,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.333163261413574,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6527,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.110249996185303,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7055,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.72261381149292,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7058,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.8690927028656006,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6694,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.992794990539551,
+      "learning_rate": 5e-05,
+      "loss": 0.683,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 8.307418823242188,
+      "learning_rate": 4.9074074074074075e-05,
+      "loss": 0.6078,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 14.761510848999023,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.6806,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 17.669111251831055,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.495,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 21.18276023864746,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.5911,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 10.731266975402832,
+      "learning_rate": 4.5370370370370374e-05,
+      "loss": 0.4819,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 21.16441535949707,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.4505,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 20.13530921936035,
+      "learning_rate": 4.351851851851852e-05,
+      "loss": 0.4387,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 13.650543212890625,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.5372,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 8.348587036132812,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5308,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.786101341247559,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.4489,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 16.651531219482422,
+      "learning_rate": 3.981481481481482e-05,
+      "loss": 0.4135,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 34.40428924560547,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.3764,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 24.429424285888672,
+      "learning_rate": 3.7962962962962964e-05,
+      "loss": 0.7231,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.558081865310669,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.4568,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.81,
+      "eval_auc": 0.884088408840884,
+      "eval_f1": 0.8207547169811321,
+      "eval_loss": 0.4558769166469574,
+      "eval_precision": 0.7837837837837838,
+      "eval_recall": 0.8613861386138614,
+      "eval_runtime": 33.1066,
+      "eval_samples_per_second": 6.041,
+      "eval_steps_per_second": 0.393,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 52622211072000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9abf1353f501f559f5a995f19c388060b52db6e50f13aea2a94d0957fce035
+size 5240

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "google-bert/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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 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": "4.43.1",
+  "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 sha256:1bbf7e7fe25bd434025d06d11a7e2e86ef65d03b60d99d811b4a2e048fd34a30
+size 437958648

runs/Aug02_12-51-14_r-hajarhammadi-autotrain2-j6vlscc7-35c1e-sajz4/events.out.tfevents.1722603075.r-hajarhammadi-autotrain2-j6vlscc7-35c1e-sajz4.133.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:183cf9f0efa949f77e8f72f47216a795420532c759453ac86d2ccb7a7124e28b
-size 15939
+oid sha256:114eed6128b675f6093c155f1908a533c2a21ad4ea9238c94d29167cfab84437
+size 19555

runs/Aug02_12-51-14_r-hajarhammadi-autotrain2-j6vlscc7-35c1e-sajz4/events.out.tfevents.1722604697.r-hajarhammadi-autotrain2-j6vlscc7-35c1e-sajz4.133.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27960b588895c3020e7ed07fb460fdeb1623162b97887589f856009237b866b9
+size 607

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 sha256:4e9abf1353f501f559f5a995f19c388060b52db6e50f13aea2a94d0957fce035
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-hajarhammadi/autotrain-data",
+    "model": "google-bert/bert-base-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": "autotrain-hajarhammadi",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "Hajarhammadi",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}