Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+
+---
+tags:
+- autotrain
+- text-classification
+base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
+widget:
+- text: "I love AutoTrain"
+---
+
+# Model Trained Using AutoTrain
+
+- Problem type: Text Classification
+
+## Validation Metrics
+loss: 0.17190960049629211
+
+f1_macro: 0.9521367521367522
+
+f1_micro: 0.9375
+
+f1_weighted: 0.9378205128205128
+
+precision_macro: 0.9523809523809524
+
+precision_micro: 0.9375
+
+precision_weighted: 0.9464285714285714
+
+recall_macro: 0.9583333333333334
+
+recall_micro: 0.9375
+
+recall_weighted: 0.9375
+
+accuracy: 0.9375

checkpoint-24/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "_num_labels": 3,
+  "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": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 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": "4.46.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-24/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccf5c0910813c2faa4f1e81cfcfdfd4eef906615c1ccf118bdc72367dd0e4c4
+size 498615900

checkpoint-24/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad347cd27fd17d5ee90ec22316594341f7dd8fcffb0ea955d50baf9c67fa1e8b
+size 997346042

checkpoint-24/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146d7c867acb15d0f5e9ccada703d4ab48e0a2c1b775236873b3b46f650a470b
+size 13990

checkpoint-24/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4125a99ce223336389179846164efbb632a48ee9f07ff7b83fd310857676db47
+size 1064

checkpoint-24/trainer_state.json

@@ -0,0 +1,264 @@
+{
+  "best_metric": 0.17190960049629211,
+  "best_model_checkpoint": "firstparagraph/checkpoint-24",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 24,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.125,
+      "grad_norm": 25.121994018554688,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6721,
+      "step": 1
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 18.93373680114746,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8281,
+      "step": 2
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 38.99924087524414,
+      "learning_rate": 5e-05,
+      "loss": 1.0106,
+      "step": 3
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 16.744102478027344,
+      "learning_rate": 4.761904761904762e-05,
+      "loss": 0.6273,
+      "step": 4
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 38.71282196044922,
+      "learning_rate": 4.523809523809524e-05,
+      "loss": 1.035,
+      "step": 5
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 27.912067413330078,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 1.2093,
+      "step": 6
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 10.65064811706543,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.8038,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.035674571990967,
+      "learning_rate": 3.809523809523809e-05,
+      "loss": 0.3203,
+      "step": 8
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.625,
+      "eval_f1_macro": 0.5904761904761905,
+      "eval_f1_micro": 0.625,
+      "eval_f1_weighted": 0.6214285714285714,
+      "eval_loss": 0.6885449886322021,
+      "eval_precision_macro": 0.5857142857142857,
+      "eval_precision_micro": 0.625,
+      "eval_precision_weighted": 0.6660714285714286,
+      "eval_recall_macro": 0.6944444444444443,
+      "eval_recall_micro": 0.625,
+      "eval_recall_weighted": 0.625,
+      "eval_runtime": 4.7789,
+      "eval_samples_per_second": 3.348,
+      "eval_steps_per_second": 0.209,
+      "step": 8
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 14.902674674987793,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.5841,
+      "step": 9
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 11.219338417053223,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3689,
+      "step": 10
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 14.7273588180542,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.4076,
+      "step": 11
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 20.348325729370117,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.4607,
+      "step": 12
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 7.504858493804932,
+      "learning_rate": 2.6190476190476192e-05,
+      "loss": 0.2815,
+      "step": 13
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 11.642386436462402,
+      "learning_rate": 2.380952380952381e-05,
+      "loss": 0.2483,
+      "step": 14
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 9.98347282409668,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.1843,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.617571830749512,
+      "learning_rate": 1.9047619047619046e-05,
+      "loss": 0.3504,
+      "step": 16
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.875,
+      "eval_f1_macro": 0.9047619047619048,
+      "eval_f1_micro": 0.875,
+      "eval_f1_weighted": 0.875,
+      "eval_loss": 0.2879645526409149,
+      "eval_precision_macro": 0.9166666666666666,
+      "eval_precision_micro": 0.875,
+      "eval_precision_weighted": 0.90625,
+      "eval_recall_macro": 0.9166666666666666,
+      "eval_recall_micro": 0.875,
+      "eval_recall_weighted": 0.875,
+      "eval_runtime": 4.6651,
+      "eval_samples_per_second": 3.43,
+      "eval_steps_per_second": 0.214,
+      "step": 16
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 8.915639877319336,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.1485,
+      "step": 17
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 3.445385217666626,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.0882,
+      "step": 18
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 4.290743350982666,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.0859,
+      "step": 19
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 5.496181011199951,
+      "learning_rate": 9.523809523809523e-06,
+      "loss": 0.1354,
+      "step": 20
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 13.18715763092041,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.1897,
+      "step": 21
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 28.582820892333984,
+      "learning_rate": 4.7619047619047615e-06,
+      "loss": 0.2239,
+      "step": 22
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 3.829745292663574,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.0806,
+      "step": 23
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.7107293605804443,
+      "learning_rate": 0.0,
+      "loss": 0.0605,
+      "step": 24
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9375,
+      "eval_f1_macro": 0.9521367521367522,
+      "eval_f1_micro": 0.9375,
+      "eval_f1_weighted": 0.9378205128205128,
+      "eval_loss": 0.17190960049629211,
+      "eval_precision_macro": 0.9523809523809524,
+      "eval_precision_micro": 0.9375,
+      "eval_precision_weighted": 0.9464285714285714,
+      "eval_recall_macro": 0.9583333333333334,
+      "eval_recall_micro": 0.9375,
+      "eval_recall_weighted": 0.9375,
+      "eval_runtime": 3.7456,
+      "eval_samples_per_second": 4.272,
+      "eval_steps_per_second": 0.267,
+      "step": 24
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 24,
+  "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": 12432108987648.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-24/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde3bf9d822488987d48561d658e1b795fc84643a4cfd674b23803d9f78f8d56
+size 5304

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "_num_labels": 3,
+  "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": "0",
+    "1": "1",
+    "2": "2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 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": "4.46.2",
+  "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:cccf5c0910813c2faa4f1e81cfcfdfd4eef906615c1ccf118bdc72367dd0e4c4
+size 498615900

runs/Nov21_20-09-02_r-zkava01-headlinesonly-c0e0w45t-ed2c4-eenl1/events.out.tfevents.1732219746.r-zkava01-headlinesonly-c0e0w45t-ed2c4-eenl1.136.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0aa7497cdeaf26f8e2358c3287e770d832760283d9157a3dc08420f7c4c100
-size 5315
+oid sha256:21f9b74ca35ed5d8d9bd01fbf6278dee101873df63d590d58e4cae2d0ad2b4a7
+size 13085

runs/Nov21_20-09-02_r-zkava01-headlinesonly-c0e0w45t-ed2c4-eenl1/events.out.tfevents.1732219967.r-zkava01-headlinesonly-c0e0w45t-ed2c4-eenl1.136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae49b3ce840c9af7b9a1165ae1ad4a9ad07d5a79916b1d2d6c25e132aa8f350
+size 906

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": false,
+  "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:bde3bf9d822488987d48561d658e1b795fc84643a4cfd674b23803d9f78f8d56
+size 5304

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "firstparagraph/autotrain-data",
+    "model": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+    "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": "firstparagraph",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "zkava01",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}