upload ipc_level1_F model

config.json

@@ -0,0 +1,69 @@
+{
+  "_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": "15",
+    "5": "16",
+    "6": "17",
+    "7": "21",
+    "8": "22",
+    "9": "23",
+    "10": "24",
+    "11": "25",
+    "12": "26",
+    "13": "27",
+    "14": "28",
+    "15": "41",
+    "16": "42",
+    "17": "99"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "01": 0,
+    "02": 1,
+    "03": 2,
+    "04": 3,
+    "15": 4,
+    "16": 5,
+    "17": 6,
+    "21": 7,
+    "22": 8,
+    "23": 9,
+    "24": 10,
+    "25": 11,
+    "26": 12,
+    "27": 13,
+    "28": 14,
+    "41": 15,
+    "42": 16,
+    "99": 17
+  },
+  "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:d310d7bc7dd5359978436660ff9e735faa514fce78bbd55b73622aa8f2ae41b5
+size 1421676909

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e90f1345986502ffb3f500ea6d1b484187c5f83a6f051ae2d30f98cc82db9a
+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 +1,305 @@
+{
+  "best_metric": 0.8743931388563246,
+  "best_model_checkpoint": "./output//roberta-large_ipc1_F_5_32_5e-6_0.01_0.06_07-08-22_05-58/checkpoint-32000",
+  "epoch": 0.3952569169960474,
+  "global_step": 34000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.87506781368674e-07,
+      "loss": 0.3599,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.18268015170670038,
+      "eval_f1": 0.2879298505097459,
+      "eval_loss": 0.18576645851135254,
+      "eval_roc_auc": 0.5853077432536982,
+      "eval_runtime": 4288.9545,
+      "eval_samples_per_second": 33.197,
+      "eval_steps_per_second": 2.075,
+      "step": 2000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.75013562737348e-07,
+      "loss": 0.1408,
+      "step": 4000
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.6640609636184858,
+      "eval_f1": 0.7541285724569866,
+      "eval_loss": 0.09878645837306976,
+      "eval_roc_auc": 0.8278381936603927,
+      "eval_runtime": 4292.1595,
+      "eval_samples_per_second": 33.172,
+      "eval_steps_per_second": 2.073,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1625203441060218e-06,
+      "loss": 0.0906,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.737512291052114,
+      "eval_f1": 0.8112492470949709,
+      "eval_loss": 0.07406309992074966,
+      "eval_roc_auc": 0.875046712248869,
+      "eval_runtime": 4294.249,
+      "eval_samples_per_second": 33.156,
+      "eval_steps_per_second": 2.072,
+      "step": 6000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.550027125474696e-06,
+      "loss": 0.0713,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.7628459053237814,
+      "eval_f1": 0.8287656289334564,
+      "eval_loss": 0.06319486349821091,
+      "eval_roc_auc": 0.8866137099850818,
+      "eval_runtime": 4295.6601,
+      "eval_samples_per_second": 33.145,
+      "eval_steps_per_second": 2.072,
+      "step": 8000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.93753390684337e-06,
+      "loss": 0.0627,
+      "step": 10000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.7722924568057311,
+      "eval_f1": 0.8382658540559053,
+      "eval_loss": 0.058036886155605316,
+      "eval_roc_auc": 0.8947882381464809,
+      "eval_runtime": 4290.269,
+      "eval_samples_per_second": 33.187,
+      "eval_steps_per_second": 2.074,
+      "step": 10000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.3250406882120437e-06,
+      "loss": 0.0585,
+      "step": 12000
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.7790420002809383,
+      "eval_f1": 0.8449722285551912,
+      "eval_loss": 0.054601434618234634,
+      "eval_roc_auc": 0.900479073554457,
+      "eval_runtime": 4292.2273,
+      "eval_samples_per_second": 33.172,
+      "eval_steps_per_second": 2.073,
+      "step": 12000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.712547469580718e-06,
+      "loss": 0.0542,
+      "step": 14000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.7874280095519034,
+      "eval_f1": 0.8536010998335779,
+      "eval_loss": 0.05090392753481865,
+      "eval_roc_auc": 0.9065922703600303,
+      "eval_runtime": 4293.5118,
+      "eval_samples_per_second": 33.162,
+      "eval_steps_per_second": 2.073,
+      "step": 14000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.100054250949392e-06,
+      "loss": 0.052,
+      "step": 16000
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.7909889029358056,
+      "eval_f1": 0.8566962061823234,
+      "eval_loss": 0.05001804977655411,
+      "eval_roc_auc": 0.9095118884122836,
+      "eval_runtime": 4295.395,
+      "eval_samples_per_second": 33.147,
+      "eval_steps_per_second": 2.072,
+      "step": 16000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.487561032318066e-06,
+      "loss": 0.0505,
+      "step": 18000
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.7934822306503723,
+      "eval_f1": 0.8588736803762056,
+      "eval_loss": 0.0483463890850544,
+      "eval_roc_auc": 0.9101339626012807,
+      "eval_runtime": 4294.2134,
+      "eval_samples_per_second": 33.156,
+      "eval_steps_per_second": 2.072,
+      "step": 18000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.87506781368674e-06,
+      "loss": 0.0496,
+      "step": 20000
+    },
+    {
+      "epoch": 0.23,
+      "eval_accuracy": 0.7956946200309032,
+      "eval_f1": 0.8605352183127327,
+      "eval_loss": 0.04739997163414955,
+      "eval_roc_auc": 0.9099304679611407,
+      "eval_runtime": 4298.5202,
+      "eval_samples_per_second": 33.123,
+      "eval_steps_per_second": 2.07,
+      "step": 20000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.262574595055414e-06,
+      "loss": 0.0489,
+      "step": 22000
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.7958912768647282,
+      "eval_f1": 0.8615685152480835,
+      "eval_loss": 0.04697679355740547,
+      "eval_roc_auc": 0.9107013229700466,
+      "eval_runtime": 4299.3608,
+      "eval_samples_per_second": 33.117,
+      "eval_steps_per_second": 2.07,
+      "step": 22000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.650081376424087e-06,
+      "loss": 0.047,
+      "step": 24000
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.7968815844922039,
+      "eval_f1": 0.8662429018314002,
+      "eval_loss": 0.045747920870780945,
+      "eval_roc_auc": 0.9202107490921341,
+      "eval_runtime": 4298.6579,
+      "eval_samples_per_second": 33.122,
+      "eval_steps_per_second": 2.07,
+      "step": 24000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.997600755885568e-06,
+      "loss": 0.0469,
+      "step": 26000
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.8009551903357213,
+      "eval_f1": 0.8666653592720427,
+      "eval_loss": 0.04524701461195946,
+      "eval_roc_auc": 0.915663430411922,
+      "eval_runtime": 4298.4038,
+      "eval_samples_per_second": 33.124,
+      "eval_steps_per_second": 2.07,
+      "step": 26000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.972866280479058e-06,
+      "loss": 0.0458,
+      "step": 28000
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.801559207753898,
+      "eval_f1": 0.869541226037224,
+      "eval_loss": 0.043748680502176285,
+      "eval_roc_auc": 0.919819594006768,
+      "eval_runtime": 4302.7264,
+      "eval_samples_per_second": 33.091,
+      "eval_steps_per_second": 2.068,
+      "step": 28000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.948131805072547e-06,
+      "loss": 0.045,
+      "step": 30000
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.8011167298777918,
+      "eval_f1": 0.8685897435897435,
+      "eval_loss": 0.04380137473344803,
+      "eval_roc_auc": 0.9187617147650531,
+      "eval_runtime": 4304.499,
+      "eval_samples_per_second": 33.077,
+      "eval_steps_per_second": 2.067,
+      "step": 30000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.923397329666036e-06,
+      "loss": 0.044,
+      "step": 32000
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.8065528866413822,
+      "eval_f1": 0.8743931388563246,
+      "eval_loss": 0.042223840951919556,
+      "eval_roc_auc": 0.9221526483236073,
+      "eval_runtime": 4303.0647,
+      "eval_samples_per_second": 33.088,
+      "eval_steps_per_second": 2.068,
+      "step": 32000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.8986628542595245e-06,
+      "loss": 0.0435,
+      "step": 34000
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.8098117713161961,
+      "eval_f1": 0.8743206079011508,
+      "eval_loss": 0.042016852647066116,
+      "eval_roc_auc": 0.9207942735325755,
+      "eval_runtime": 4360.5908,
+      "eval_samples_per_second": 32.652,
+      "eval_steps_per_second": 2.041,
+      "step": 34000
+    }
+  ],
+  "max_steps": 430100,
+  "num_train_epochs": 5,
+  "total_flos": 1.013996137611264e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaf5488385767f5528ab77b13ee423a9a311a2700f88b57c84255addc6bd079
+size 2735