Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: cardiffnlp/twitter-roberta-base-sentiment
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.4823857545852661
+
+f1: 0.7666666666666667
+
+precision: 0.92
+
+recall: 0.6571428571428571
+
+auc: 0.8741854636591478
+
+accuracy: 0.79

checkpoint-200/config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NONTOXIC",
+    "1": "TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NONTOXIC": 0,
+    "TOXIC": 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": "4.45.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e7b2515677556c3b0b67bcdecd5aec156095c76879421510efbc1c0636c821
+size 498612824

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57dc1065ee1b9cbd79bf7d2daedafd4661f386bdf6768fb770e7670c3bc6e484
+size 997339898

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca27102ed7b9af45002d578b9e983b9865821cee3cd5b539f9e5e209ba7eed74
+size 13990

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7665b28e8c41ee6373fc3b9189263cf3dc093da1e219a5f029ddbd95ebe35e02
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": 0.4823857545852661,
+  "best_model_checkpoint": "ft-roberta-toxicity/checkpoint-200",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 3.1541271209716797,
+      "learning_rate": 5e-06,
+      "loss": 0.7051,
+      "step": 5
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.209589958190918,
+      "learning_rate": 1e-05,
+      "loss": 0.6954,
+      "step": 10
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.086088180541992,
+      "learning_rate": 1.5e-05,
+      "loss": 0.719,
+      "step": 15
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.385767936706543,
+      "learning_rate": 2e-05,
+      "loss": 0.6785,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.3053433895111084,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6874,
+      "step": 25
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.8885927200317383,
+      "learning_rate": 3e-05,
+      "loss": 0.6988,
+      "step": 30
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.523589611053467,
+      "learning_rate": 3.5e-05,
+      "loss": 0.7674,
+      "step": 35
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.986541748046875,
+      "learning_rate": 4e-05,
+      "loss": 0.6891,
+      "step": 40
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 6.452502727508545,
+      "learning_rate": 4.5e-05,
+      "loss": 0.8348,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.318837642669678,
+      "learning_rate": 5e-05,
+      "loss": 0.7019,
+      "step": 50
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.7034225463867188,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.65,
+      "step": 55
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.1009528636932373,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.6593,
+      "step": 60
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 7.615400791168213,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.6755,
+      "step": 65
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.228475332260132,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.6034,
+      "step": 70
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.151826858520508,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.7218,
+      "step": 75
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 11.06347370147705,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.7539,
+      "step": 80
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 24.23040771484375,
+      "learning_rate": 4.6111111111111115e-05,
+      "loss": 0.6296,
+      "step": 85
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 6.828371047973633,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 0.559,
+      "step": 90
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 7.590404510498047,
+      "learning_rate": 4.5e-05,
+      "loss": 0.4996,
+      "step": 95
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 51.719970703125,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.6665,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.715,
+      "eval_auc": 0.795187969924812,
+      "eval_f1": 0.7219512195121951,
+      "eval_loss": 0.5786986351013184,
+      "eval_precision": 0.74,
+      "eval_recall": 0.7047619047619048,
+      "eval_runtime": 32.3877,
+      "eval_samples_per_second": 6.175,
+      "eval_steps_per_second": 0.401,
+      "step": 100
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 13.197641372680664,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.6974,
+      "step": 105
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.645239353179932,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.4852,
+      "step": 110
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 4.36188268661499,
+      "learning_rate": 4.277777777777778e-05,
+      "loss": 0.7566,
+      "step": 115
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 6.4677300453186035,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 0.4989,
+      "step": 120
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 6.412233829498291,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5496,
+      "step": 125
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 12.167023658752441,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 0.5181,
+      "step": 130
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 4.28169584274292,
+      "learning_rate": 4.055555555555556e-05,
+      "loss": 0.4636,
+      "step": 135
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 20.04325294494629,
+      "learning_rate": 4e-05,
+      "loss": 0.4278,
+      "step": 140
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 18.524545669555664,
+      "learning_rate": 3.944444444444445e-05,
+      "loss": 0.574,
+      "step": 145
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 12.304378509521484,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.4926,
+      "step": 150
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 16.889781951904297,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.2429,
+      "step": 155
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 18.878406524658203,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.4433,
+      "step": 160
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 21.254526138305664,
+      "learning_rate": 3.722222222222222e-05,
+      "loss": 0.644,
+      "step": 165
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 21.575471878051758,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.6373,
+      "step": 170
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 8.538455963134766,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.5708,
+      "step": 175
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 7.5060577392578125,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.7443,
+      "step": 180
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 7.51224946975708,
+      "learning_rate": 3.5e-05,
+      "loss": 0.4896,
+      "step": 185
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 5.721360683441162,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 0.544,
+      "step": 190
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 6.373270511627197,
+      "learning_rate": 3.388888888888889e-05,
+      "loss": 0.4813,
+      "step": 195
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.219586372375488,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3724,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.79,
+      "eval_auc": 0.8741854636591478,
+      "eval_f1": 0.7666666666666667,
+      "eval_loss": 0.4823857545852661,
+      "eval_precision": 0.92,
+      "eval_recall": 0.6571428571428571,
+      "eval_runtime": 32.4699,
+      "eval_samples_per_second": 6.16,
+      "eval_steps_per_second": 0.4,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 105244422144000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13b2e7a26fd4167d96c783d7e8d167a265cee625cae53843427363df4363159
+size 5240

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment",
+  "_num_labels": 2,
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "NONTOXIC",
+    "1": "TOXIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NONTOXIC": 0,
+    "TOXIC": 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": "4.45.0",
+  "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 sha256:82e7b2515677556c3b0b67bcdecd5aec156095c76879421510efbc1c0636c821
+size 498612824

runs/Nov02_01-51-31_r-bgonzalezbustamante-autotrain-kh5afcbo-97d26-43px8/events.out.tfevents.1730512293.r-bgonzalezbustamante-autotrain-kh5afcbo-97d26-43px8.146.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ca8b98d6ac7926c234ce75e9c78ee38d80f8513a15dc24c867a82a5ab841c1
-size 26144
+oid sha256:625c91cddcad7722e74ff1fdd46abe7a2c189e33057b429438523eb7d69cd6bd
+size 29127

runs/Nov02_01-51-31_r-bgonzalezbustamante-autotrain-kh5afcbo-97d26-43px8/events.out.tfevents.1730515098.r-bgonzalezbustamante-autotrain-kh5afcbo-97d26-43px8.146.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487a690392a39d2b894e1c1938eea00d2222af4e0fc4183eea7eacf86a1109a3
+size 607

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "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": "</s>",
+    "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 +1,57 @@
+{
+  "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": 1000000000000000019884624838656,
+  "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:a13b2e7a26fd4167d96c783d7e8d167a265cee625cae53843427363df4363159
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "ft-roberta-toxicity/autotrain-data",
+    "model": "cardiffnlp/twitter-roberta-base-sentiment",
+    "lr": 5e-05,
+    "epochs": 5,
+    "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": "ft-roberta-toxicity",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "bgonzalezbustamante",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}