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: 0.21242013573646545
+
+f1: 1.0
+
+precision: 1.0
+
+recall: 1.0
+
+auc: 1.0
+
+accuracy: 1.0

checkpoint-3/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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 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": "4.47.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

checkpoint-3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f6226caa60e536f1f70752161a160ccf93ac944c2c0fbec3e5ebb9ae820ea5
+size 498612824

checkpoint-3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c182646316497b96a09daf6f8e825aa0baa63421fa0434c477111beec96d71
+size 997339898

checkpoint-3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59cd6ddfdf11005bacb3a4367e0d8e63aa031f1629a834b4c3297e0b6ae8a47
+size 13990

checkpoint-3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a41b254d981983d12a5d0bed17f4768863ab9648e2daeb9b71c409365e3b73
+size 1064

checkpoint-3/trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.21242013573646545,
+  "best_model_checkpoint": "Roberta/checkpoint-3",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.709331035614014,
+      "learning_rate": 5e-05,
+      "loss": 0.5731,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.6056622862815857,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.4235,
+      "eval_samples_per_second": 4.722,
+      "eval_steps_per_second": 2.361,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.63822078704834,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5393,
+      "step": 2
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.30428773164749146,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.4369,
+      "eval_samples_per_second": 4.577,
+      "eval_steps_per_second": 2.289,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.563619136810303,
+      "learning_rate": 0.0,
+      "loss": 0.2507,
+      "step": 3
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 1.0,
+      "eval_auc": 1.0,
+      "eval_f1": 1.0,
+      "eval_loss": 0.21242013573646545,
+      "eval_precision": 1.0,
+      "eval_recall": 1.0,
+      "eval_runtime": 0.4293,
+      "eval_samples_per_second": 4.659,
+      "eval_steps_per_second": 2.33,
+      "step": 3
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 3,
+  "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": 986666457600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b005353208822978fac66b37c87cfd5551f84e01c1bfe9d8b6efb180f782db
+size 5368

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": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negative": 0,
+    "positive": 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": "4.47.1",
+  "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 sha256:49f6226caa60e536f1f70752161a160ccf93ac944c2c0fbec3e5ebb9ae820ea5
+size 498612824

runs/Jan07_10-56-04_r-philprz-robertafinetuning-zi88cip8-5abb0-u796e/events.out.tfevents.1736247365.r-philprz-robertafinetuning-zi88cip8-5abb0-u796e.105.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0c1323ff762f563087a7f0e255b12504ed97ca1236b32ba696f9fd8082d58a
-size 5264
+oid sha256:1d1ab432bc3d0a5db30ad363194189b4befc8631c8c03b492261e85a8bdf9a5c
+size 7760

runs/Jan07_10-56-04_r-philprz-robertafinetuning-zi88cip8-5abb0-u796e/events.out.tfevents.1736247389.r-philprz-robertafinetuning-zi88cip8-5abb0-u796e.105.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3c6ce9f53c9b4d9d4b44ef1e34e8e954aa47dc650edaafceaa297be7a50194
+size 597

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 +1,58 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "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 sha256:89b005353208822978fac66b37c87cfd5551f84e01c1bfe9d8b6efb180f782db
+size 5368

training_params.json

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