Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+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: 0.5335766077041626
+
+f1_macro: 0.8027609455799637
+
+f1_micro: 0.8
+
+f1_weighted: 0.798510908659599
+
+precision_macro: 0.8034159941442764
+
+precision_micro: 0.8
+
+precision_weighted: 0.8030223296082353
+
+recall_macro: 0.8077239632795189
+
+recall_micro: 0.8
+
+recall_weighted: 0.8
+
+accuracy: 0.8

checkpoint-100/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9391be07ea135e09e1ff19cdd1bf3f20014e6edfd1853f6268d1f16454609c3
+size 498615900

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c6d70b403df93d69db7afc50103dad0bd7e9e80592dd980b27a85a0694c4d31
+size 997346042

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9d42cd090cb622748a5c0f5d5ada95da9f80c87048c5533fdb977a5b236f70
+size 13990

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388d25972bb1e5c37bd606304b2b7f03e402ddc476d98d532c28ffa8e9b3a17e
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,428 @@
+{
+  "best_metric": 0.5335766077041626,
+  "best_model_checkpoint": "autotrain-roberta-sentiment/checkpoint-100",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "grad_norm": 3.4940836429595947,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1535,
+      "step": 2
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.262470245361328,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.1256,
+      "step": 4
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.512415647506714,
+      "learning_rate": 1.2e-05,
+      "loss": 1.0537,
+      "step": 6
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9540835022926331,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.1332,
+      "step": 8
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.4703962802886963,
+      "learning_rate": 2e-05,
+      "loss": 1.0453,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.3024346828460693,
+      "learning_rate": 2.4e-05,
+      "loss": 1.0759,
+      "step": 12
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.083477973937988,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.0091,
+      "step": 14
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.6913983821868896,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.0225,
+      "step": 16
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 2.0365138053894043,
+      "learning_rate": 3.6e-05,
+      "loss": 1.0758,
+      "step": 18
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.462596893310547,
+      "learning_rate": 4e-05,
+      "loss": 1.0949,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 2.2764413356781006,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.1325,
+      "step": 22
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.8556883335113525,
+      "learning_rate": 4.8e-05,
+      "loss": 1.0637,
+      "step": 24
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.2826690673828125,
+      "learning_rate": 4.977777777777778e-05,
+      "loss": 1.1215,
+      "step": 26
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.986983299255371,
+      "learning_rate": 4.933333333333334e-05,
+      "loss": 1.1464,
+      "step": 28
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 3.0181400775909424,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 1.0994,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.1268210411071777,
+      "learning_rate": 4.844444444444445e-05,
+      "loss": 1.0626,
+      "step": 32
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.155054807662964,
+      "learning_rate": 4.8e-05,
+      "loss": 1.1088,
+      "step": 34
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.4121484756469727,
+      "learning_rate": 4.755555555555556e-05,
+      "loss": 1.0775,
+      "step": 36
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.4863100051879883,
+      "learning_rate": 4.711111111111111e-05,
+      "loss": 1.0617,
+      "step": 38
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.520081043243408,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 1.0156,
+      "step": 40
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 7.486565589904785,
+      "learning_rate": 4.6222222222222224e-05,
+      "loss": 0.8929,
+      "step": 42
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 18.066055297851562,
+      "learning_rate": 4.577777777777778e-05,
+      "loss": 1.2286,
+      "step": 44
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 10.362664222717285,
+      "learning_rate": 4.5333333333333335e-05,
+      "loss": 0.9297,
+      "step": 46
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 6.666133403778076,
+      "learning_rate": 4.4888888888888894e-05,
+      "loss": 0.9551,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 8.330809593200684,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.972,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.465,
+      "eval_f1_macro": 0.3169122948031185,
+      "eval_f1_micro": 0.465,
+      "eval_f1_weighted": 0.3513784524105401,
+      "eval_loss": 0.9785851240158081,
+      "eval_precision_macro": 0.8102836879432624,
+      "eval_precision_micro": 0.465,
+      "eval_precision_weighted": 0.7694946808510639,
+      "eval_recall_macro": 0.398005698005698,
+      "eval_recall_micro": 0.465,
+      "eval_recall_weighted": 0.465,
+      "eval_runtime": 38.6621,
+      "eval_samples_per_second": 5.173,
+      "eval_steps_per_second": 0.181,
+      "step": 50
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 8.873079299926758,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 1.0789,
+      "step": 52
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 12.436768531799316,
+      "learning_rate": 4.355555555555556e-05,
+      "loss": 0.9067,
+      "step": 54
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 19.907135009765625,
+      "learning_rate": 4.311111111111111e-05,
+      "loss": 0.7823,
+      "step": 56
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 39.21774673461914,
+      "learning_rate": 4.266666666666667e-05,
+      "loss": 1.3983,
+      "step": 58
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 27.241775512695312,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 1.1425,
+      "step": 60
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 50.450050354003906,
+      "learning_rate": 4.177777777777778e-05,
+      "loss": 1.0617,
+      "step": 62
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 19.874343872070312,
+      "learning_rate": 4.133333333333333e-05,
+      "loss": 1.1376,
+      "step": 64
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 15.969518661499023,
+      "learning_rate": 4.088888888888889e-05,
+      "loss": 1.042,
+      "step": 66
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 12.018631935119629,
+      "learning_rate": 4.0444444444444444e-05,
+      "loss": 0.7554,
+      "step": 68
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 9.8690767288208,
+      "learning_rate": 4e-05,
+      "loss": 0.9531,
+      "step": 70
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 7.842430114746094,
+      "learning_rate": 3.9555555555555556e-05,
+      "loss": 0.8799,
+      "step": 72
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 8.438117027282715,
+      "learning_rate": 3.9111111111111115e-05,
+      "loss": 0.7729,
+      "step": 74
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 6.847545623779297,
+      "learning_rate": 3.866666666666667e-05,
+      "loss": 0.792,
+      "step": 76
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 7.344234943389893,
+      "learning_rate": 3.8222222222222226e-05,
+      "loss": 0.7008,
+      "step": 78
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 19.439647674560547,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.6895,
+      "step": 80
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 8.48671817779541,
+      "learning_rate": 3.733333333333334e-05,
+      "loss": 0.5814,
+      "step": 82
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 12.682677268981934,
+      "learning_rate": 3.688888888888889e-05,
+      "loss": 0.6957,
+      "step": 84
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 21.3659610748291,
+      "learning_rate": 3.644444444444445e-05,
+      "loss": 0.539,
+      "step": 86
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 26.52878189086914,
+      "learning_rate": 3.6e-05,
+      "loss": 1.0977,
+      "step": 88
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 17.535959243774414,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.5173,
+      "step": 90
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 15.361188888549805,
+      "learning_rate": 3.511111111111111e-05,
+      "loss": 0.5678,
+      "step": 92
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 17.405290603637695,
+      "learning_rate": 3.466666666666667e-05,
+      "loss": 0.7743,
+      "step": 94
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 20.69967269897461,
+      "learning_rate": 3.4222222222222224e-05,
+      "loss": 0.7244,
+      "step": 96
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 15.444042205810547,
+      "learning_rate": 3.377777777777778e-05,
+      "loss": 0.6662,
+      "step": 98
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 17.32610511779785,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6937,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8,
+      "eval_f1_macro": 0.8027609455799637,
+      "eval_f1_micro": 0.8,
+      "eval_f1_weighted": 0.798510908659599,
+      "eval_loss": 0.5335766077041626,
+      "eval_precision_macro": 0.8034159941442764,
+      "eval_precision_micro": 0.8,
+      "eval_precision_weighted": 0.8030223296082353,
+      "eval_recall_macro": 0.8077239632795189,
+      "eval_recall_micro": 0.8,
+      "eval_recall_weighted": 0.8,
+      "eval_runtime": 35.6379,
+      "eval_samples_per_second": 5.612,
+      "eval_steps_per_second": 0.196,
+      "step": 100
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 250,
+  "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": 105113810382336.0,
+  "train_batch_size": 16,
+  "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:cdeb21fb5dbd6d010b51d25402cc7e4acbf851d9f905b2569ce3802ffe67c04e
+size 5240

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "FacebookAI/roberta-base",
+  "_num_labels": 3,
+  "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": "negative",
+    "1": "neutral",
+    "2": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "neutral": 1,
+    "positive": 2
+  },
+  "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:b9391be07ea135e09e1ff19cdd1bf3f20014e6edfd1853f6268d1f16454609c3
+size 498615900

runs/Aug11_23-28-48_r-daljeetsingh-autotrain-advanced-rfi43y38-98aba-8p7xj/events.out.tfevents.1723418930.r-daljeetsingh-autotrain-advanced-rfi43y38-98aba-8p7xj.111.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:828f2489220aa342b9672a44e029199f11b89cbbd922141f5b5b6090c5a87f9f
-size 32900
+oid sha256:d3fb2c601f3c46c21d96deb095eb154b3a860df54e805afc75392dd9794575d7
+size 35775

runs/Aug11_23-28-48_r-daljeetsingh-autotrain-advanced-rfi43y38-98aba-8p7xj/events.out.tfevents.1723421606.r-daljeetsingh-autotrain-advanced-rfi43y38-98aba-8p7xj.111.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5d1abd85b0288d1d79490ec7922e87e85b585c6b4177be40fb26916e54261f
+size 921

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:cdeb21fb5dbd6d010b51d25402cc7e4acbf851d9f905b2569ce3802ffe67c04e
+size 5240

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "autotrain-roberta-sentiment/autotrain-data",
+    "model": "FacebookAI/roberta-base",
+    "lr": 5e-05,
+    "epochs": 5,
+    "max_seq_length": 128,
+    "batch_size": 16,
+    "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-roberta-sentiment",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "daljeetsingh",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}