Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+---
+library_name: transformers
+tags:
+- autotrain
+- text-classification
+base_model: dost-asti/BERT-ceb-cased
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.04441085457801819
+
+f1: 0.9523809523809523
+
+precision: 0.9090909090909091
+
+recall: 1.0
+
+auc: 1.0
+
+accuracy: 0.95

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 30002,
+  "[MASK]": 30003,
+  "[PAD]": 30001,
+  "[SEP]": 30000,
+  "[UNK]": 30004
+}

checkpoint-30/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dost-asti/BERT-ceb-cased",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "fake",
+    "1": "true"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fake": 0,
+    "true": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30004
+}

checkpoint-30/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a85b3cce30965c3f41d199a33f5166870d4156203cc55a282e84ec7547b283
+size 436367944

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70b6ea10ea9a5ae8e3b8dddbcaedf8a0eb40842f72a4b2d73641b68502fd8eb
+size 872850170

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d254b3238eaab1fc1b3fbb985be43e82a6a761a33a80eff5987e91823eef0b
+size 13990

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1acf7518eaa83a30405413555139e93a2eb8b9085597afc9a51f69cd1ccf771
+size 1064

checkpoint-30/trainer_state.json

@@ -0,0 +1,291 @@
+{
+  "best_metric": 0.04441085457801819,
+  "best_model_checkpoint": "trainCMDBERT-sample/checkpoint-30",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 7.945383071899414,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6922,
+      "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.711484909057617,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6868,
+      "step": 2
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.974453926086426,
+      "learning_rate": 5e-05,
+      "loss": 0.6604,
+      "step": 3
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.878942966461182,
+      "learning_rate": 4.814814814814815e-05,
+      "loss": 0.7292,
+      "step": 4
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.609418869018555,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.6536,
+      "step": 5
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.901663303375244,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6743,
+      "step": 6
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.790696620941162,
+      "learning_rate": 4.259259259259259e-05,
+      "loss": 0.595,
+      "step": 7
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.129704475402832,
+      "learning_rate": 4.074074074074074e-05,
+      "loss": 0.5059,
+      "step": 8
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 13.14133358001709,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.7147,
+      "step": 9
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.443601608276367,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.4751,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.3918549418449402,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.5522,
+      "eval_samples_per_second": 12.885,
+      "eval_steps_per_second": 1.289,
+      "step": 10
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 5.978346824645996,
+      "learning_rate": 3.518518518518519e-05,
+      "loss": 0.4208,
+      "step": 11
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 10.853551864624023,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.5508,
+      "step": 12
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 3.4875123500823975,
+      "learning_rate": 3.148148148148148e-05,
+      "loss": 0.2284,
+      "step": 13
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 5.512720108032227,
+      "learning_rate": 2.962962962962963e-05,
+      "loss": 0.3199,
+      "step": 14
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 8.866156578063965,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.2572,
+      "step": 15
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 13.71770191192627,
+      "learning_rate": 2.5925925925925925e-05,
+      "loss": 0.3133,
+      "step": 16
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 2.18959379196167,
+      "learning_rate": 2.4074074074074074e-05,
+      "loss": 0.1026,
+      "step": 17
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 2.2819249629974365,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.063,
+      "step": 18
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.038083553314209,
+      "learning_rate": 2.037037037037037e-05,
+      "loss": 0.1096,
+      "step": 19
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.494248867034912,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.0653,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.95,
+      "eval_auc": 1.0,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.19424112141132355,
+      "eval_precision": 0.9090909090909091,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.5099,
+      "eval_samples_per_second": 13.246,
+      "eval_steps_per_second": 1.325,
+      "step": 20
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.483051061630249,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0604,
+      "step": 21
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.8026891350746155,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.026,
+      "step": 22
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.3247548341751099,
+      "learning_rate": 1.2962962962962962e-05,
+      "loss": 0.0319,
+      "step": 23
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4032141864299774,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.0164,
+      "step": 24
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0784159898757935,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.0222,
+      "step": 25
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.32401901483535767,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 0.0132,
+      "step": 26
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 8.892071723937988,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.0401,
+      "step": 27
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.20014284551143646,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 0.009,
+      "step": 28
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.24240027368068695,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 0.0093,
+      "step": 29
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1646367609500885,
+      "learning_rate": 0.0,
+      "loss": 0.0074,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.95,
+      "eval_auc": 1.0,
+      "eval_f1": 0.9523809523809523,
+      "eval_loss": 0.04441085457801819,
+      "eval_precision": 0.9090909090909091,
+      "eval_recall": 1.0,
+      "eval_runtime": 1.4953,
+      "eval_samples_per_second": 13.375,
+      "eval_steps_per_second": 1.337,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 30,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 15786663321600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7faf0fa4cb37d6877095efc7e3e4603e8e7d983ba8ebd45c0b43a0f8b30a8903
+size 5368

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "dost-asti/BERT-ceb-cased",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "fake",
+    "1": "true"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "fake": 0,
+    "true": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30004
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a85b3cce30965c3f41d199a33f5166870d4156203cc55a282e84ec7547b283
+size 436367944

runs/Nov22_16-49-42_r-roncc13-trainedcmdbert-sample-9zmi99tm-c7bf0-bshfz/events.out.tfevents.1763830184.r-roncc13-trainedcmdbert-sample-9zmi99tm-c7bf0-bshfz.94.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44cdb36bcad8dca88a437aa49f32ac39e80088cfca473824c02e0336bb718869
-size 5250
+oid sha256:6297fc6ec80c85909107184bd70a4e89e0d8019eaf0ae2039a165c806ae970b1
+size 13335

runs/Nov22_16-49-42_r-roncc13-trainedcmdbert-sample-9zmi99tm-c7bf0-bshfz/events.out.tfevents.1763830268.r-roncc13-trainedcmdbert-sample-9zmi99tm-c7bf0-bshfz.94.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f337c0e7dc3a50fc02efb64a4e9637c739eb72fcea7d2d6be201c6fc501d7f37
+size 597

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,79 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30000": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30003": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30004": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7faf0fa4cb37d6877095efc7e3e4603e8e7d983ba8ebd45c0b43a0f8b30a8903
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "trainCMDBERT-sample/autotrain-data",
+    "model": "dost-asti/BERT-ceb-cased",
+    "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": "trainCMDBERT-sample",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "roncc13",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}