upload ipc_level1_B model

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "../models/roberta-large/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ipc1",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "01",
+    "1": "02",
+    "2": "03",
+    "3": "04",
+    "4": "05",
+    "5": "06",
+    "6": "07",
+    "7": "08",
+    "8": "09",
+    "9": "21",
+    "10": "22",
+    "11": "23",
+    "12": "24",
+    "13": "25",
+    "14": "26",
+    "15": "27",
+    "16": "28",
+    "17": "29",
+    "18": "30",
+    "19": "31",
+    "20": "32",
+    "21": "33",
+    "22": "41",
+    "23": "42",
+    "24": "43",
+    "25": "44",
+    "26": "60",
+    "27": "61",
+    "28": "62",
+    "29": "63",
+    "30": "64",
+    "31": "65",
+    "32": "66",
+    "33": "67",
+    "34": "68",
+    "35": "81",
+    "36": "82",
+    "37": "99"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "01": 0,
+    "02": 1,
+    "03": 2,
+    "04": 3,
+    "05": 4,
+    "06": 5,
+    "07": 6,
+    "08": 7,
+    "09": 8,
+    "21": 9,
+    "22": 10,
+    "23": 11,
+    "24": 12,
+    "25": 13,
+    "26": 14,
+    "27": 15,
+    "28": 16,
+    "29": 17,
+    "30": 18,
+    "31": 19,
+    "32": 20,
+    "33": 21,
+    "41": 22,
+    "42": 23,
+    "43": 24,
+    "44": 25,
+    "60": 26,
+    "61": 27,
+    "62": 28,
+    "63": 29,
+    "64": 30,
+    "65": 31,
+    "66": 32,
+    "67": 33,
+    "68": 34,
+    "81": 35,
+    "82": 36,
+    "99": 37
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5808eb38f5ac0aeff73eeb580c6893c4776f5bd0114f0531adcdf219c43f4c
+size 1421758893

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a09352109e9ac36d6d9075a8cad7cf9bdeab4cc85d8c706d0500f2115574986
+size 15523

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "../models/roberta-large/", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.7610864260798164,
+  "best_model_checkpoint": "./output//roberta-large_ipc1_B_5_32_5e-6_0.01_0.06_07-07-22_18-34/checkpoint-20000",
+  "epoch": 0.09819252116662534,
+  "global_step": 20000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.6365272890925457e-07,
+      "loss": 0.4942,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.0,
+      "eval_f1": 3.725980731356789e-05,
+      "eval_loss": 0.242140531539917,
+      "eval_roc_auc": 0.5000018812220105,
+      "eval_runtime": 10105.0715,
+      "eval_samples_per_second": 33.362,
+      "eval_steps_per_second": 2.085,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.2730545781850913e-07,
+      "loss": 0.1998,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.15237019956111908,
+      "eval_roc_auc": 0.5,
+      "eval_runtime": 10093.7625,
+      "eval_samples_per_second": 33.4,
+      "eval_steps_per_second": 2.088,
+      "step": 4000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.909581867277637e-07,
+      "loss": 0.1391,
+      "step": 6000
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.027651218528274128,
+      "eval_f1": 0.051996127342103765,
+      "eval_loss": 0.11342979222536087,
+      "eval_roc_auc": 0.5133426998907926,
+      "eval_runtime": 10096.0276,
+      "eval_samples_per_second": 33.392,
+      "eval_steps_per_second": 2.087,
+      "step": 6000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.546109156370183e-07,
+      "loss": 0.1014,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.378618803540495,
+      "eval_f1": 0.5170973118634858,
+      "eval_loss": 0.08398378640413284,
+      "eval_roc_auc": 0.6863826768837573,
+      "eval_runtime": 10090.8157,
+      "eval_samples_per_second": 33.409,
+      "eval_steps_per_second": 2.088,
+      "step": 8000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.182636445462728e-07,
+      "loss": 0.0776,
+      "step": 10000
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.5363778742792056,
+      "eval_f1": 0.6512947171889306,
+      "eval_loss": 0.06587187945842743,
+      "eval_roc_auc": 0.764578950366969,
+      "eval_runtime": 10097.484,
+      "eval_samples_per_second": 33.387,
+      "eval_steps_per_second": 2.087,
+      "step": 10000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.819163734555274e-07,
+      "loss": 0.0634,
+      "step": 12000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.6100976483709452,
+      "eval_f1": 0.7042497089763607,
+      "eval_loss": 0.05614431947469711,
+      "eval_roc_auc": 0.8049277667745456,
+      "eval_runtime": 10099.2828,
+      "eval_samples_per_second": 33.381,
+      "eval_steps_per_second": 2.086,
+      "step": 12000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.145569102364782e-06,
+      "loss": 0.055,
+      "step": 14000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.6416227664269951,
+      "eval_f1": 0.7269993152493521,
+      "eval_loss": 0.05014372989535332,
+      "eval_roc_auc": 0.8223509407753063,
+      "eval_runtime": 10095.4543,
+      "eval_samples_per_second": 33.394,
+      "eval_steps_per_second": 2.087,
+      "step": 14000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3092218312740365e-06,
+      "loss": 0.0502,
+      "step": 16000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.6483650126954748,
+      "eval_f1": 0.7361196439111947,
+      "eval_loss": 0.04603615403175354,
+      "eval_roc_auc": 0.8236568822502442,
+      "eval_runtime": 10103.5894,
+      "eval_samples_per_second": 33.367,
+      "eval_steps_per_second": 2.085,
+      "step": 16000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.472874560183291e-06,
+      "loss": 0.0464,
+      "step": 18000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.6700867326356754,
+      "eval_f1": 0.7512896154078634,
+      "eval_loss": 0.043166279792785645,
+      "eval_roc_auc": 0.8373107879447877,
+      "eval_runtime": 10097.7203,
+      "eval_samples_per_second": 33.387,
+      "eval_steps_per_second": 2.087,
+      "step": 18000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6365272890925457e-06,
+      "loss": 0.0441,
+      "step": 20000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.6828178021404333,
+      "eval_f1": 0.7610864260798164,
+      "eval_loss": 0.0410546213388443,
+      "eval_roc_auc": 0.8459980425262335,
+      "eval_runtime": 10102.9844,
+      "eval_samples_per_second": 33.369,
+      "eval_steps_per_second": 2.086,
+      "step": 20000
+    }
+  ],
+  "max_steps": 1018405,
+  "num_train_epochs": 5,
+  "total_flos": 5.9650862088192e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78d41f00a28720c117b2e2c2e257914d9398ad8582ef388ea96f41fc0ecf6a3
+size 2735