Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: FacebookAI/roberta-base
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.3766980469226837
+
+f1: 0.8717948717948718
+
+precision: 0.8095238095238095
+
+recall: 0.9444444444444444
+
+auc: 0.9248366013071895
+
+accuracy: 0.8571428571428571

checkpoint-54/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_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": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "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": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-54/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7973a3204c7773cd10cc2ca41558b6fbfc0911023afc2a14893225203b2942fa
+size 498612824

checkpoint-54/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874787dc545dc12c0542de0c77dd67d1ae2276b78e672cf285f91d250b378b7b
+size 997339898

checkpoint-54/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26edbf4f48fbaac42c4ee4e2665df323f332c00976e108a49ad4ff80146c01e8
+size 13990

checkpoint-54/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae95f6829da5ddd39caae8c0bb77e2dfb385b5a632b831421569d9e4300d1b17
+size 1064

checkpoint-54/trainer_state.json

@@ -0,0 +1,459 @@
+{
+  "best_metric": 0.3766980469226837,
+  "best_model_checkpoint": "d-roberta-exai-01/checkpoint-54",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 54,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05555555555555555,
+      "grad_norm": 1.1439120769500732,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6799,
+      "step": 1
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 1.8278450965881348,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6989,
+      "step": 2
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.1776649951934814,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7057,
+      "step": 3
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.2689857482910156,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6973,
+      "step": 4
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 2.244907855987549,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6857,
+      "step": 5
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 2.460754871368408,
+      "learning_rate": 5e-05,
+      "loss": 0.6646,
+      "step": 6
+    },
+    {
+      "epoch": 0.3888888888888889,
+      "grad_norm": 4.120091438293457,
+      "learning_rate": 4.8958333333333335e-05,
+      "loss": 0.7275,
+      "step": 7
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 5.090549468994141,
+      "learning_rate": 4.791666666666667e-05,
+      "loss": 0.7605,
+      "step": 8
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.4805407524108887,
+      "learning_rate": 4.6875e-05,
+      "loss": 0.6976,
+      "step": 9
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 4.3824872970581055,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 0.6799,
+      "step": 10
+    },
+    {
+      "epoch": 0.6111111111111112,
+      "grad_norm": 3.8339335918426514,
+      "learning_rate": 4.4791666666666673e-05,
+      "loss": 0.7532,
+      "step": 11
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.0908315181732178,
+      "learning_rate": 4.375e-05,
+      "loss": 0.6979,
+      "step": 12
+    },
+    {
+      "epoch": 0.7222222222222222,
+      "grad_norm": 1.9701024293899536,
+      "learning_rate": 4.270833333333333e-05,
+      "loss": 0.7122,
+      "step": 13
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 3.0795094966888428,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.6867,
+      "step": 14
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 2.4303715229034424,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 0.693,
+      "step": 15
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.7773878574371338,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 0.6741,
+      "step": 16
+    },
+    {
+      "epoch": 0.9444444444444444,
+      "grad_norm": 5.024258613586426,
+      "learning_rate": 3.854166666666667e-05,
+      "loss": 0.694,
+      "step": 17
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4120217561721802,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.6736,
+      "step": 18
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5428571428571428,
+      "eval_auc": 0.9281045751633986,
+      "eval_f1": 0.6923076923076923,
+      "eval_loss": 0.6742954850196838,
+      "eval_precision": 0.5294117647058824,
+      "eval_recall": 1.0,
+      "eval_runtime": 30.0824,
+      "eval_samples_per_second": 1.163,
+      "eval_steps_per_second": 0.1,
+      "step": 18
+    },
+    {
+      "epoch": 1.0555555555555556,
+      "grad_norm": 4.765969276428223,
+      "learning_rate": 3.6458333333333336e-05,
+      "loss": 0.6705,
+      "step": 19
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.414098858833313,
+      "learning_rate": 3.541666666666667e-05,
+      "loss": 0.6782,
+      "step": 20
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 1.3146916627883911,
+      "learning_rate": 3.4375e-05,
+      "loss": 0.6824,
+      "step": 21
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 3.936519145965576,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.7143,
+      "step": 22
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 2.058326482772827,
+      "learning_rate": 3.229166666666667e-05,
+      "loss": 0.6797,
+      "step": 23
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 2.090275764465332,
+      "learning_rate": 3.125e-05,
+      "loss": 0.691,
+      "step": 24
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 6.395630359649658,
+      "learning_rate": 3.0208333333333334e-05,
+      "loss": 0.755,
+      "step": 25
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 1.6730719804763794,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.6576,
+      "step": 26
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 2.8280136585235596,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 0.7343,
+      "step": 27
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.9934184551239014,
+      "learning_rate": 2.7083333333333332e-05,
+      "loss": 0.627,
+      "step": 28
+    },
+    {
+      "epoch": 1.6111111111111112,
+      "grad_norm": 4.483340263366699,
+      "learning_rate": 2.604166666666667e-05,
+      "loss": 0.6001,
+      "step": 29
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 2.275224208831787,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5915,
+      "step": 30
+    },
+    {
+      "epoch": 1.7222222222222223,
+      "grad_norm": 5.251317977905273,
+      "learning_rate": 2.3958333333333334e-05,
+      "loss": 0.651,
+      "step": 31
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 3.7001290321350098,
+      "learning_rate": 2.2916666666666667e-05,
+      "loss": 0.5814,
+      "step": 32
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 2.8710334300994873,
+      "learning_rate": 2.1875e-05,
+      "loss": 0.5595,
+      "step": 33
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 5.27128791809082,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 0.6996,
+      "step": 34
+    },
+    {
+      "epoch": 1.9444444444444444,
+      "grad_norm": 4.378724575042725,
+      "learning_rate": 1.9791666666666665e-05,
+      "loss": 0.4621,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.3865132331848145,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 0.4726,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8857142857142857,
+      "eval_auc": 0.9215686274509803,
+      "eval_f1": 0.8823529411764706,
+      "eval_loss": 0.44821038842201233,
+      "eval_precision": 0.9375,
+      "eval_recall": 0.8333333333333334,
+      "eval_runtime": 29.785,
+      "eval_samples_per_second": 1.175,
+      "eval_steps_per_second": 0.101,
+      "step": 36
+    },
+    {
+      "epoch": 2.0555555555555554,
+      "grad_norm": 10.086033821105957,
+      "learning_rate": 1.7708333333333335e-05,
+      "loss": 0.3497,
+      "step": 37
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 4.620193004608154,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4411,
+      "step": 38
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 6.217515468597412,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.5982,
+      "step": 39
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 7.31005859375,
+      "learning_rate": 1.4583333333333335e-05,
+      "loss": 0.3145,
+      "step": 40
+    },
+    {
+      "epoch": 2.2777777777777777,
+      "grad_norm": 7.373918533325195,
+      "learning_rate": 1.3541666666666666e-05,
+      "loss": 0.7014,
+      "step": 41
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 47.0409049987793,
+      "learning_rate": 1.25e-05,
+      "loss": 0.5427,
+      "step": 42
+    },
+    {
+      "epoch": 2.388888888888889,
+      "grad_norm": 21.664775848388672,
+      "learning_rate": 1.1458333333333333e-05,
+      "loss": 0.8382,
+      "step": 43
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 56.60698318481445,
+      "learning_rate": 1.0416666666666668e-05,
+      "loss": 0.5747,
+      "step": 44
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 18.434154510498047,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 0.6116,
+      "step": 45
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 6.595049858093262,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6499,
+      "step": 46
+    },
+    {
+      "epoch": 2.611111111111111,
+      "grad_norm": 19.58675193786621,
+      "learning_rate": 7.2916666666666674e-06,
+      "loss": 0.6439,
+      "step": 47
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 7.169925212860107,
+      "learning_rate": 6.25e-06,
+      "loss": 0.4054,
+      "step": 48
+    },
+    {
+      "epoch": 2.7222222222222223,
+      "grad_norm": 6.507111549377441,
+      "learning_rate": 5.208333333333334e-06,
+      "loss": 0.2461,
+      "step": 49
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 10.119100570678711,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.4848,
+      "step": 50
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 26.183744430541992,
+      "learning_rate": 3.125e-06,
+      "loss": 1.01,
+      "step": 51
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 18.847240447998047,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.3273,
+      "step": 52
+    },
+    {
+      "epoch": 2.9444444444444446,
+      "grad_norm": 15.944683074951172,
+      "learning_rate": 1.0416666666666667e-06,
+      "loss": 0.9338,
+      "step": 53
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.516860008239746,
+      "learning_rate": 0.0,
+      "loss": 0.4842,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_auc": 0.9248366013071895,
+      "eval_f1": 0.8717948717948718,
+      "eval_loss": 0.3766980469226837,
+      "eval_precision": 0.8095238095238095,
+      "eval_recall": 0.9444444444444444,
+      "eval_runtime": 27.1832,
+      "eval_samples_per_second": 1.288,
+      "eval_steps_per_second": 0.11,
+      "step": 54
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 54,
+  "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": 110506643251200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-54/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5672e0fba442016e53c4ba494b371e6e8ec6c0eb9ca69ca91a754d41a624e83a
+size 5240

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_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": "0",
+    "1": "1"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "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": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7973a3204c7773cd10cc2ca41558b6fbfc0911023afc2a14893225203b2942fa
+size 498612824

runs/Aug09_11-04-45_r-ivanterzic-bert-deception-detection-finetuned-2w8h5-d1fc6-cku/events.out.tfevents.1723201487.r-ivanterzic-bert-deception-detection-finetuned-2w8h5-d1fc6-cku.104.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189ded122cff5961996c3f33a1233a87e545307e43f11aa6aa5ba5146655f6ba
-size 15408
+oid sha256:9886879a825e2a4300bb698a66a12adfaa10072eedb81f829260346d10ab9957
+size 18128

runs/Aug09_11-04-45_r-ivanterzic-bert-deception-detection-finetuned-2w8h5-d1fc6-cku/events.out.tfevents.1723202979.r-ivanterzic-bert-deception-detection-finetuned-2w8h5-d1fc6-cku.104.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a979074f6a72adb8535cc26812d052424bdcbff276f167b04418e1f0e9112a1
+size 597

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "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
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "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 sha256:5672e0fba442016e53c4ba494b371e6e8ec6c0eb9ca69ca91a754d41a624e83a
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "d-roberta-exai-01/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 3,
+    "max_seq_length": 512,
+    "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": "d-roberta-exai-01",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "ivanterzic",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}