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: 0.687774658203125
+
+f1: 0.5
+
+precision: 0.5
+
+recall: 0.5
+
+auc: 1.0
+
+accuracy: 0.5

checkpoint-6/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-6/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d68792ca6b6ccefa8247c730ae896fc433470d05c97b8ebd745689aad3a0d6e
+size 498612824

checkpoint-6/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c6bfbfb068f7a6bece1a5a0030527826faa1a9670f09f60ad60222e931474d
+size 997339898

checkpoint-6/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ae460aee1d885b276b898f4f8b9dee77c8b6c7941b7009c1d7d14dd5d118c4
+size 13990

checkpoint-6/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c350a54903a1a9b6f44cb7b3b94efd85379339fffb4d5a43c311252edab041e9
+size 1064

checkpoint-6/trainer_state.json

@@ -0,0 +1,123 @@
+{
+  "best_metric": 0.687774658203125,
+  "best_model_checkpoint": "robertatest/checkpoint-6",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.72326135635376,
+      "learning_rate": 1e-05,
+      "loss": 0.7371,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.217761993408203,
+      "learning_rate": 2e-05,
+      "loss": 0.6233,
+      "step": 2
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.7041667103767395,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.7626,
+      "eval_samples_per_second": 5.245,
+      "eval_steps_per_second": 1.311,
+      "step": 2
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.899262428283691,
+      "learning_rate": 3e-05,
+      "loss": 0.6912,
+      "step": 3
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.985622406005859,
+      "learning_rate": 4e-05,
+      "loss": 0.6854,
+      "step": 4
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 0.75,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6881411671638489,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.6966,
+      "eval_samples_per_second": 5.742,
+      "eval_steps_per_second": 1.435,
+      "step": 4
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 3.8720149993896484,
+      "learning_rate": 5e-05,
+      "loss": 0.6425,
+      "step": 5
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.4388933181762695,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.6463,
+      "step": 6
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5,
+      "eval_auc": 1.0,
+      "eval_f1": 0.5,
+      "eval_loss": 0.687774658203125,
+      "eval_precision": 0.5,
+      "eval_recall": 0.5,
+      "eval_runtime": 0.6946,
+      "eval_samples_per_second": 5.759,
+      "eval_steps_per_second": 1.44,
+      "step": 6
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 25,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3157332664320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88f3b545a9f2fa7c14625b3e89b36a509356ff478b65aff38721c43a2ec0278
+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 sha256:3d68792ca6b6ccefa8247c730ae896fc433470d05c97b8ebd745689aad3a0d6e
+size 498612824

runs/Jan07_10-48-10_r-benoai-roberta-fine-tuned-0vwitbax-9b6ef-g8h07/events.out.tfevents.1736246892.r-benoai-roberta-fine-tuned-0vwitbax-9b6ef-g8h07.125.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04c35ef76ff4e836bc7085b9fa28258fde8ee926ddc75bc9c0fbdda120d9c802
-size 5277
+oid sha256:82fd9e07c114949937c6f476d66de4870837157bdaa5909bf4475c129974015c
+size 12086

runs/Jan07_10-48-10_r-benoai-roberta-fine-tuned-0vwitbax-9b6ef-g8h07/events.out.tfevents.1736246981.r-benoai-roberta-fine-tuned-0vwitbax-9b6ef-g8h07.125.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cd94689977b348d84265868189d48bc6261e14fe3ab0c97ebe679d0cc660d03
+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:d88f3b545a9f2fa7c14625b3e89b36a509356ff478b65aff38721c43a2ec0278
+size 5368

training_params.json

@@ -0,0 +1,30 @@
+{
+    "data_path": "robertatest/autotrain-data",
+    "model": "cardiffnlp/twitter-roberta-base-sentiment",
+    "lr": 5e-05,
+    "epochs": 25,
+    "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": "robertatest",
+    "auto_find_batch_size": false,
+    "mixed_precision": "fp16",
+    "save_total_limit": 1,
+    "push_to_hub": true,
+    "eval_strategy": "epoch",
+    "username": "BenoAI",
+    "log": "tensorboard",
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.01
+}