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: 0.4598750174045563
+
+f1: 0.8571428571428571
+
+precision: 0.75
+
+recall: 1.0
+
+auc: 0.8781163434903048
+
+accuracy: 0.75

checkpoint-38/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": "4.41.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-38/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f81de18d2363974f2198711d0e06e4f947f86478c4f10c1a05e447224f34f22
+size 498612824

checkpoint-38/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538619ffcbc89151532b77816bc81a76825bf80d390ae08f89f570a495ab05ad
+size 997345530

checkpoint-38/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004ca43bf24123cf116fc7ee9350cd9f7654c0b06c98651da916199fb3cba842
+size 14244

checkpoint-38/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5550347d8f530db7c1e04a6e48fecf22dacbcf84067f2581a5f19409e4f2c595
+size 1064

checkpoint-38/trainer_state.json

@@ -0,0 +1,321 @@
+{
+  "best_metric": 0.4598750174045563,
+  "best_model_checkpoint": "autotrain-tes2/checkpoint-38",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 38,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 8.360681533813477,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.7789,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 3.473684072494507,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.7014,
+      "step": 2
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 4.280536651611328,
+      "learning_rate": 3.9473684210526315e-06,
+      "loss": 0.7496,
+      "step": 3
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 5.139090538024902,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 0.7482,
+      "step": 4
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 7.595941543579102,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 0.7648,
+      "step": 5
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 6.151755332946777,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.6708,
+      "step": 6
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 4.414488792419434,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 0.6814,
+      "step": 7
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.1186416149139404,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.6711,
+      "step": 8
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 5.158999919891357,
+      "learning_rate": 1.1842105263157895e-05,
+      "loss": 0.7188,
+      "step": 9
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 2.7816195487976074,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 0.6272,
+      "step": 10
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 3.866028308868408,
+      "learning_rate": 1.4473684210526317e-05,
+      "loss": 0.6516,
+      "step": 11
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 5.54939079284668,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 0.6311,
+      "step": 12
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 1.7745245695114136,
+      "learning_rate": 1.7105263157894737e-05,
+      "loss": 0.648,
+      "step": 13
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 5.726246356964111,
+      "learning_rate": 1.8421052631578947e-05,
+      "loss": 0.721,
+      "step": 14
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 3.599973678588867,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 0.639,
+      "step": 15
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.8797402381896973,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 0.6811,
+      "step": 16
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 2.823983669281006,
+      "learning_rate": 2.236842105263158e-05,
+      "loss": 0.5753,
+      "step": 17
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 4.9799909591674805,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.5373,
+      "step": 18
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.066366672515869,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4943,
+      "step": 19
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 2.1961863040924072,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 0.6783,
+      "step": 20
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 4.6081390380859375,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.355,
+      "step": 21
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": Infinity,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.5158,
+      "step": 22
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": NaN,
+      "learning_rate": 2.7631578947368426e-05,
+      "loss": 0.5127,
+      "step": 23
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 6.148653984069824,
+      "learning_rate": 2.8947368421052634e-05,
+      "loss": 0.3929,
+      "step": 24
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 7.018494129180908,
+      "learning_rate": 3.0263157894736844e-05,
+      "loss": 0.6157,
+      "step": 25
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 1.8734830617904663,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 0.4951,
+      "step": 26
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 2.3880300521850586,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 0.327,
+      "step": 27
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 1.500815749168396,
+      "learning_rate": 3.421052631578947e-05,
+      "loss": 0.2797,
+      "step": 28
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 3.438194990158081,
+      "learning_rate": 3.5526315789473684e-05,
+      "loss": 0.4684,
+      "step": 29
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 2.816570281982422,
+      "learning_rate": 3.6842105263157895e-05,
+      "loss": 0.3406,
+      "step": 30
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 7.311382293701172,
+      "learning_rate": 3.815789473684211e-05,
+      "loss": 0.5107,
+      "step": 31
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 4.999342918395996,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 0.5008,
+      "step": 32
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 2.1701626777648926,
+      "learning_rate": 4.078947368421053e-05,
+      "loss": 0.0727,
+      "step": 33
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 13.688937187194824,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 0.6574,
+      "step": 34
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 26.409658432006836,
+      "learning_rate": 4.342105263157895e-05,
+      "loss": 1.0675,
+      "step": 35
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 2.801671266555786,
+      "learning_rate": 4.473684210526316e-05,
+      "loss": 0.4416,
+      "step": 36
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 8.945662498474121,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 0.4885,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 17.597484588623047,
+      "learning_rate": 4.736842105263158e-05,
+      "loss": 0.7419,
+      "step": 38
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.75,
+      "eval_auc": 0.8781163434903048,
+      "eval_f1": 0.8571428571428571,
+      "eval_loss": 0.4598750174045563,
+      "eval_precision": 0.75,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.1072,
+      "eval_samples_per_second": 709.107,
+      "eval_steps_per_second": 46.652,
+      "step": 38
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 19930662443520.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-38/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699ae6fe90a677bca5e9c5e9ad34a9ceced4772247506c42c6136f1ff217f3e1
+size 5112

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": "4.41.0",
+  "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 sha256:3f81de18d2363974f2198711d0e06e4f947f86478c4f10c1a05e447224f34f22
+size 498612824

runs/Jul09_20-53-39_bora-HP-Z8-G4/events.out.tfevents.1720583620.bora-HP-Z8-G4.1320251.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bcdc7d033dad417fde5ab1de18f1d30eef0fbe02782f4ef4c5e8ee6a341e0f7
-size 4924
+oid sha256:012cf4020419287f091885ddbea22175dea0e4145a32ad990c3276c40cb51a7a
+size 55962

runs/Jul09_20-53-39_bora-HP-Z8-G4/events.out.tfevents.1720583658.bora-HP-Z8-G4.1320251.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adaab06a3b932f12ec2a6f9517e2743355b97047df52d632aa6d527d46069985
+size 607

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 sha256:699ae6fe90a677bca5e9c5e9ad34a9ceced4772247506c42c6136f1ff217f3e1
+size 5112

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-tes2/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 10,
+    "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-tes2",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "evaluation_strategy": "epoch",
+    "username": "vuk123",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}