upload ipc_level1_A model

config.json

@@ -0,0 +1,65 @@
+{
+  "_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": "21",
+    "2": "22",
+    "3": "23",
+    "4": "24",
+    "5": "41",
+    "6": "42",
+    "7": "43",
+    "8": "44",
+    "9": "45",
+    "10": "46",
+    "11": "47",
+    "12": "61",
+    "13": "62",
+    "14": "63",
+    "15": "99"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "01": 0,
+    "21": 1,
+    "22": 2,
+    "23": 3,
+    "24": 4,
+    "41": 5,
+    "42": 6,
+    "43": 7,
+    "44": 8,
+    "45": 9,
+    "46": 10,
+    "47": 11,
+    "61": 12,
+    "62": 13,
+    "63": 14,
+    "99": 15
+  },
+  "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 sha256:38b922152043be2d9c8c0cdd6123a06fb3e3d564f2c455337d652e3dd761ca5a
+size 1421668653

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c8a6f313617d39fb13ca970de19c598085e0ec817ebac9d7a6b7c418de6c51
+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 +1,254 @@
+{
+  "best_metric": 0.9262784238149737,
+  "best_model_checkpoint": "./output//roberta-large_ipc1_A_5_32_5e-6_0.01_0.06_07-07-22_18-28/checkpoint-28000",
+  "epoch": 0.20382165605095542,
+  "global_step": 28000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4264188484216146e-07,
+      "loss": 0.4036,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.29802271068070474,
+      "eval_f1": 0.4513093341029148,
+      "eval_loss": 0.18722428381443024,
+      "eval_roc_auc": 0.6489909583092993,
+      "eval_runtime": 6738.4514,
+      "eval_samples_per_second": 33.744,
+      "eval_steps_per_second": 2.109,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.852837696843229e-07,
+      "loss": 0.139,
+      "step": 4000
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.7495184315381165,
+      "eval_f1": 0.8233456807060868,
+      "eval_loss": 0.09316979348659515,
+      "eval_roc_auc": 0.8729328968232468,
+      "eval_runtime": 6731.1126,
+      "eval_samples_per_second": 33.781,
+      "eval_steps_per_second": 2.111,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.279256545264844e-07,
+      "loss": 0.0833,
+      "step": 6000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.8257777660500831,
+      "eval_f1": 0.8730237370770162,
+      "eval_loss": 0.06400171667337418,
+      "eval_roc_auc": 0.9127664928657763,
+      "eval_runtime": 6737.696,
+      "eval_samples_per_second": 33.748,
+      "eval_steps_per_second": 2.109,
+      "step": 6000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.705675393686458e-07,
+      "loss": 0.0609,
+      "step": 8000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.8517252904803371,
+      "eval_f1": 0.8936563937601606,
+      "eval_loss": 0.04994160309433937,
+      "eval_roc_auc": 0.9287281571162814,
+      "eval_runtime": 6739.6994,
+      "eval_samples_per_second": 33.738,
+      "eval_steps_per_second": 2.109,
+      "step": 8000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2132094242108074e-06,
+      "loss": 0.0486,
+      "step": 10000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.8612335189241013,
+      "eval_f1": 0.9012467044040513,
+      "eval_loss": 0.042878150939941406,
+      "eval_roc_auc": 0.9363720666329317,
+      "eval_runtime": 6737.7132,
+      "eval_samples_per_second": 33.748,
+      "eval_steps_per_second": 2.109,
+      "step": 10000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4558513090529688e-06,
+      "loss": 0.0428,
+      "step": 12000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.8677643788866313,
+      "eval_f1": 0.9071863695310901,
+      "eval_loss": 0.03869173675775528,
+      "eval_roc_auc": 0.9411312512824218,
+      "eval_runtime": 6738.7732,
+      "eval_samples_per_second": 33.742,
+      "eval_steps_per_second": 2.109,
+      "step": 12000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.6984931938951305e-06,
+      "loss": 0.0381,
+      "step": 14000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.8750956540095522,
+      "eval_f1": 0.9134744162179311,
+      "eval_loss": 0.035005878657102585,
+      "eval_roc_auc": 0.9451390338347415,
+      "eval_runtime": 6740.1138,
+      "eval_samples_per_second": 33.736,
+      "eval_steps_per_second": 2.109,
+      "step": 14000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9411350787372917e-06,
+      "loss": 0.035,
+      "step": 16000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.8797310253230247,
+      "eval_f1": 0.916496962291688,
+      "eval_loss": 0.03334926813840866,
+      "eval_roc_auc": 0.9482613871646639,
+      "eval_runtime": 6745.7206,
+      "eval_samples_per_second": 33.708,
+      "eval_steps_per_second": 2.107,
+      "step": 16000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.1837769635794533e-06,
+      "loss": 0.0339,
+      "step": 18000
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.8754386890782911,
+      "eval_f1": 0.9137814990877805,
+      "eval_loss": 0.03394022211432457,
+      "eval_roc_auc": 0.9477629191629577,
+      "eval_runtime": 6743.1748,
+      "eval_samples_per_second": 33.72,
+      "eval_steps_per_second": 2.108,
+      "step": 18000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.426418848421615e-06,
+      "loss": 0.033,
+      "step": 20000
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.8812702852468534,
+      "eval_f1": 0.9188712895614195,
+      "eval_loss": 0.03143986314535141,
+      "eval_roc_auc": 0.9501313707572241,
+      "eval_runtime": 6746.8218,
+      "eval_samples_per_second": 33.702,
+      "eval_steps_per_second": 2.106,
+      "step": 20000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.6690607332637764e-06,
+      "loss": 0.0315,
+      "step": 22000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.8836671328425293,
+      "eval_f1": 0.9219864147882801,
+      "eval_loss": 0.02986242063343525,
+      "eval_roc_auc": 0.952957229106777,
+      "eval_runtime": 6747.8476,
+      "eval_samples_per_second": 33.697,
+      "eval_steps_per_second": 2.106,
+      "step": 22000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 2.9117026181059375e-06,
+      "loss": 0.0306,
+      "step": 24000
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.8826424255218092,
+      "eval_f1": 0.9214287520120004,
+      "eval_loss": 0.03005838766694069,
+      "eval_roc_auc": 0.9537168355560653,
+      "eval_runtime": 6748.6977,
+      "eval_samples_per_second": 33.693,
+      "eval_steps_per_second": 2.106,
+      "step": 24000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.154344502948099e-06,
+      "loss": 0.03,
+      "step": 26000
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.8873129799192548,
+      "eval_f1": 0.924658794955391,
+      "eval_loss": 0.028916172683238983,
+      "eval_roc_auc": 0.9536678452333417,
+      "eval_runtime": 6745.8355,
+      "eval_samples_per_second": 33.707,
+      "eval_steps_per_second": 2.107,
+      "step": 26000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.396986387790261e-06,
+      "loss": 0.0294,
+      "step": 28000
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.8904354786218786,
+      "eval_f1": 0.9262784238149737,
+      "eval_loss": 0.028293747454881668,
+      "eval_roc_auc": 0.954565095074253,
+      "eval_runtime": 6746.7818,
+      "eval_samples_per_second": 33.702,
+      "eval_steps_per_second": 2.106,
+      "step": 28000
+    }
+  ],
+  "max_steps": 686875,
+  "num_train_epochs": 5,
+  "total_flos": 8.35050000089088e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d7fbce1bd319d6108183732e817fe542839a983283ece3b1f04d38f988a086
+size 2735