upload ipc_level1_H model

config.json

@@ -0,0 +1,45 @@
+{
+  "_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": "99"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "01": 0,
+    "02": 1,
+    "03": 2,
+    "04": 3,
+    "05": 4,
+    "99": 5
+  },
+  "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 sha256:1d549fa5163630decdb3cca84499b6f6d5c21870499eb50a69d6f0a1c07e215a
+size 1421627693

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": 0.9076670631807177,
+  "best_model_checkpoint": "./output//roberta-large_ipc1_H_5_32_5e-6_0.01_0.06_07-08-22_06-40/checkpoint-28000",
+  "epoch": 0.2084682793177131,
+  "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": 2.481759070829404e-07,
+      "loss": 0.4329,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.5884747561984958,
+      "eval_f1": 0.6872181807983729,
+      "eval_loss": 0.2462294101715088,
+      "eval_roc_auc": 0.7804816717606253,
+      "eval_runtime": 6569.6147,
+      "eval_samples_per_second": 33.839,
+      "eval_steps_per_second": 2.115,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.963518141658809e-07,
+      "loss": 0.1951,
+      "step": 4000
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.7922514304221094,
+      "eval_f1": 0.8496544620977544,
+      "eval_loss": 0.14517635107040405,
+      "eval_roc_auc": 0.895243709044785,
+      "eval_runtime": 6569.3584,
+      "eval_samples_per_second": 33.841,
+      "eval_steps_per_second": 2.115,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.445277212488212e-07,
+      "loss": 0.1382,
+      "step": 6000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.8181744575191623,
+      "eval_f1": 0.8705377939577977,
+      "eval_loss": 0.12493952363729477,
+      "eval_roc_auc": 0.9109245202637991,
+      "eval_runtime": 6567.6398,
+      "eval_samples_per_second": 33.85,
+      "eval_steps_per_second": 2.116,
+      "step": 6000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.927036283317617e-07,
+      "loss": 0.1226,
+      "step": 8000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.8257044154161719,
+      "eval_f1": 0.8795041743265541,
+      "eval_loss": 0.11273977905511856,
+      "eval_roc_auc": 0.9185852786225337,
+      "eval_runtime": 6573.4579,
+      "eval_samples_per_second": 33.82,
+      "eval_steps_per_second": 2.114,
+      "step": 8000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.240879535414702e-06,
+      "loss": 0.1121,
+      "step": 10000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.8326721004714096,
+      "eval_f1": 0.8861235840391877,
+      "eval_loss": 0.10739490389823914,
+      "eval_roc_auc": 0.9245890326912541,
+      "eval_runtime": 6572.6062,
+      "eval_samples_per_second": 33.824,
+      "eval_steps_per_second": 2.114,
+      "step": 10000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4890554424976424e-06,
+      "loss": 0.1059,
+      "step": 12000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.8378045269711036,
+      "eval_f1": 0.8920632767595246,
+      "eval_loss": 0.1017272025346756,
+      "eval_roc_auc": 0.929144259699995,
+      "eval_runtime": 6575.5269,
+      "eval_samples_per_second": 33.809,
+      "eval_steps_per_second": 2.113,
+      "step": 12000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.7372313495805828e-06,
+      "loss": 0.1024,
+      "step": 14000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.8408677894130772,
+      "eval_f1": 0.893626255792282,
+      "eval_loss": 0.09984249621629715,
+      "eval_roc_auc": 0.928852296252917,
+      "eval_runtime": 6574.5786,
+      "eval_samples_per_second": 33.814,
+      "eval_steps_per_second": 2.113,
+      "step": 14000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9854072566635234e-06,
+      "loss": 0.0974,
+      "step": 16000
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.8442549210119112,
+      "eval_f1": 0.898560228806424,
+      "eval_loss": 0.09467251598834991,
+      "eval_roc_auc": 0.9336472029116307,
+      "eval_runtime": 6575.3988,
+      "eval_samples_per_second": 33.81,
+      "eval_steps_per_second": 2.113,
+      "step": 16000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.2335831637464636e-06,
+      "loss": 0.0964,
+      "step": 18000
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.8498776494296304,
+      "eval_f1": 0.9009191664807081,
+      "eval_loss": 0.09292563796043396,
+      "eval_roc_auc": 0.9335645456901214,
+      "eval_runtime": 6575.3606,
+      "eval_samples_per_second": 33.81,
+      "eval_steps_per_second": 2.113,
+      "step": 18000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.481759070829404e-06,
+      "loss": 0.0954,
+      "step": 20000
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.8467199251502393,
+      "eval_f1": 0.8968800725980649,
+      "eval_loss": 0.09573328495025635,
+      "eval_roc_auc": 0.9303951610003275,
+      "eval_runtime": 6576.7864,
+      "eval_samples_per_second": 33.803,
+      "eval_steps_per_second": 2.113,
+      "step": 20000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.7299349779123447e-06,
+      "loss": 0.0926,
+      "step": 22000
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.8511686278743388,
+      "eval_f1": 0.9032656201127709,
+      "eval_loss": 0.09094775468111038,
+      "eval_roc_auc": 0.9367924962877248,
+      "eval_runtime": 6579.9338,
+      "eval_samples_per_second": 33.786,
+      "eval_steps_per_second": 2.112,
+      "step": 22000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.978110884995285e-06,
+      "loss": 0.0916,
+      "step": 24000
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.8545737522041096,
+      "eval_f1": 0.9044808139596631,
+      "eval_loss": 0.08910883218050003,
+      "eval_roc_auc": 0.9358689602259472,
+      "eval_runtime": 6577.1239,
+      "eval_samples_per_second": 33.801,
+      "eval_steps_per_second": 2.113,
+      "step": 24000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.2262867920782255e-06,
+      "loss": 0.0907,
+      "step": 26000
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.8548076577062866,
+      "eval_f1": 0.9047564303992575,
+      "eval_loss": 0.08734705299139023,
+      "eval_roc_auc": 0.9352966950206927,
+      "eval_runtime": 6579.4149,
+      "eval_samples_per_second": 33.789,
+      "eval_steps_per_second": 2.112,
+      "step": 26000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.4744626991611656e-06,
+      "loss": 0.09,
+      "step": 28000
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.8557117924358559,
+      "eval_f1": 0.9076670631807177,
+      "eval_loss": 0.08580958843231201,
+      "eval_roc_auc": 0.9401102386424043,
+      "eval_runtime": 6641.2181,
+      "eval_samples_per_second": 33.475,
+      "eval_steps_per_second": 2.092,
+      "step": 28000
+    }
+  ],
+  "max_steps": 671565,
+  "num_train_epochs": 5,
+  "total_flos": 8.35021786841088e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1257f22ca922923c53551e8989f6950a4d60387f9706ea4bc926ee079d2a65
+size 2735