Upload best model from trial 4

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/config.json

@@ -0,0 +1,41 @@
+{
+  "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": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed53e877c5c2a4fe303c875708e92351907647ac1597be09fa91e361ef5302d
+size 498622052

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e412d8865e564e8caf438c74231edf8385f5c8a13ecaed797e9bda814fdb877d
+size 997367179

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ab6a44ca7190074a8103d73d2ab111bfc83e764695494ede2e0db3737825f68
+size 14645

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79e90e4fbb7758a21132767c77e1c546d6485070557c764b92aec8cedd1d19d8
+size 1465

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/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
+  }
+}

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/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>"
+}

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/trainer_state.json

@@ -0,0 +1,227 @@
+{
+  "best_global_step": null,
+  "best_metric": 0.8549734244495064,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1648,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.209709167480469,
+      "learning_rate": 4.005012637915311e-05,
+      "loss": 1.2221,
+      "step": 206
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6794229309035688,
+      "eval_f1_macro": 0.6903384635019785,
+      "eval_f1_micro": 0.6794229309035688,
+      "eval_loss": 0.9562283754348755,
+      "eval_precision_macro": 0.6856214964139914,
+      "eval_precision_micro": 0.6794229309035688,
+      "eval_recall_macro": 0.7023407501417045,
+      "eval_recall_micro": 0.6794229309035688,
+      "eval_roc_auc_macro": 0.9142815173195331,
+      "eval_runtime": 20.1781,
+      "eval_samples_per_second": 326.344,
+      "eval_steps_per_second": 10.209,
+      "step": 206
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.155277252197266,
+      "learning_rate": 8.029561922844843e-05,
+      "loss": 0.8574,
+      "step": 412
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7880030372057707,
+      "eval_f1_macro": 0.7945791984207429,
+      "eval_f1_micro": 0.7880030372057707,
+      "eval_loss": 0.755141019821167,
+      "eval_precision_macro": 0.8057505361689319,
+      "eval_precision_micro": 0.7880030372057707,
+      "eval_recall_macro": 0.7890018555398042,
+      "eval_recall_micro": 0.7880030372057707,
+      "eval_roc_auc_macro": 0.9585897323774617,
+      "eval_runtime": 20.0854,
+      "eval_samples_per_second": 327.85,
+      "eval_steps_per_second": 10.256,
+      "step": 412
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 18.14335060119629,
+      "learning_rate": 9.16546156669182e-05,
+      "loss": 0.6984,
+      "step": 618
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8176157934700076,
+      "eval_f1_macro": 0.8230131366176605,
+      "eval_f1_micro": 0.8176157934700076,
+      "eval_loss": 0.7003515958786011,
+      "eval_precision_macro": 0.8298515841583664,
+      "eval_precision_micro": 0.8176157934700076,
+      "eval_recall_macro": 0.8196496420522859,
+      "eval_recall_micro": 0.8176157934700076,
+      "eval_roc_auc_macro": 0.9666945154822795,
+      "eval_runtime": 20.2237,
+      "eval_samples_per_second": 325.609,
+      "eval_steps_per_second": 10.186,
+      "step": 618
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.464390993118286,
+      "learning_rate": 8.992097692704298e-05,
+      "loss": 0.5874,
+      "step": 824
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8065299924069855,
+      "eval_f1_macro": 0.8123017871814888,
+      "eval_f1_micro": 0.8065299924069855,
+      "eval_loss": 0.74701327085495,
+      "eval_precision_macro": 0.8255344076752393,
+      "eval_precision_micro": 0.8065299924069855,
+      "eval_recall_macro": 0.8126038642315582,
+      "eval_recall_micro": 0.8065299924069855,
+      "eval_roc_auc_macro": 0.9644214422301616,
+      "eval_runtime": 20.285,
+      "eval_samples_per_second": 324.623,
+      "eval_steps_per_second": 10.155,
+      "step": 824
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.513798713684082,
+      "learning_rate": 8.680970782526196e-05,
+      "loss": 0.5256,
+      "step": 1030
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8417615793470008,
+      "eval_f1_macro": 0.844078303707352,
+      "eval_f1_micro": 0.8417615793470008,
+      "eval_loss": 0.6605576872825623,
+      "eval_precision_macro": 0.8630138901816512,
+      "eval_precision_micro": 0.8417615793470008,
+      "eval_recall_macro": 0.8320538663423089,
+      "eval_recall_micro": 0.8417615793470008,
+      "eval_roc_auc_macro": 0.974675984316297,
+      "eval_runtime": 20.2936,
+      "eval_samples_per_second": 324.486,
+      "eval_steps_per_second": 10.151,
+      "step": 1030
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.569585084915161,
+      "learning_rate": 8.241841634736791e-05,
+      "loss": 0.4757,
+      "step": 1236
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8482915717539863,
+      "eval_f1_macro": 0.8538860784316519,
+      "eval_f1_micro": 0.8482915717539863,
+      "eval_loss": 0.6944032907485962,
+      "eval_precision_macro": 0.8529922828945118,
+      "eval_precision_micro": 0.8482915717539863,
+      "eval_recall_macro": 0.8565645444042984,
+      "eval_recall_micro": 0.8482915717539863,
+      "eval_roc_auc_macro": 0.9732822144853686,
+      "eval_runtime": 20.0828,
+      "eval_samples_per_second": 327.893,
+      "eval_steps_per_second": 10.258,
+      "step": 1236
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.196255683898926,
+      "learning_rate": 7.688486785603595e-05,
+      "loss": 0.4447,
+      "step": 1442
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8451025056947609,
+      "eval_f1_macro": 0.8500087146399935,
+      "eval_f1_micro": 0.8451025056947609,
+      "eval_loss": 0.726932942867279,
+      "eval_precision_macro": 0.8479685490318113,
+      "eval_precision_micro": 0.8451025056947609,
+      "eval_recall_macro": 0.852480734334885,
+      "eval_recall_micro": 0.8451025056947609,
+      "eval_roc_auc_macro": 0.9672435874676422,
+      "eval_runtime": 20.2051,
+      "eval_samples_per_second": 325.908,
+      "eval_steps_per_second": 10.195,
+      "step": 1442
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.610114097595215,
+      "learning_rate": 7.038266306044823e-05,
+      "loss": 0.4232,
+      "step": 1648
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8549734244495064,
+      "eval_f1_macro": 0.8582909574930282,
+      "eval_f1_micro": 0.8549734244495064,
+      "eval_loss": 0.6973910331726074,
+      "eval_precision_macro": 0.8555984057881977,
+      "eval_precision_micro": 0.8549734244495064,
+      "eval_recall_macro": 0.8620681778852821,
+      "eval_recall_micro": 0.8549734244495064,
+      "eval_roc_auc_macro": 0.9709893949074336,
+      "eval_runtime": 20.2877,
+      "eval_samples_per_second": 324.58,
+      "eval_steps_per_second": 10.154,
+      "step": 1648
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.0
+      },
+      "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": 2.750554836899136e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

HF_FT_Twitter_rob_Preprocess3/trial_4/checkpoint-1648/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69ab58ca4bff302980eee47ec5cff7abe50f26b84c44838c52e3b59e01bbedf8
+size 5777