model upload

added_tokens.json

@@ -0,0 +1 @@
+{"[S]": 50265, "[E]": 50266}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "/hdd1/mujeen/retrieval_prf/output/labeler_multi.train.v4.1_nq.dev.v4.1_rlmulti_title",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50267
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4535eed2130cc31c889a01b22e83815a9c7d97fd86dd252c9a63fb476bf77972
+size 1421619501

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": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": "/mnt/hdd-nfs/jungsoo/DensePhrases/resources/ckpts/roberta-large-multi-lr_2e-5/special_tokens_map.json", "name_or_path": "/hdd1/mujeen/retrieval_prf/output/labeler_multi.train.v4.1_nq.dev.v4.1_rlmulti_title", "tokenizer_class": "RobertaTokenizer"}

trainer_state.json

@@ -0,0 +1,340 @@
+{
+  "best_metric": 0.8577586206896551,
+  "best_model_checkpoint": "/hdd1/mujeen/retrieval_prf/output/labeler_multi.train.v4.1_nq.dev.v4.1_rlmulti_title_trec/checkpoint-420",
+  "epoch": 0.9994979079497908,
+  "global_step": 1493,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9075686537173478e-05,
+      "loss": 0.3211,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.8103448275862069,
+      "eval_loss": 0.4440845847129822,
+      "eval_runtime": 1.5296,
+      "eval_samples_per_second": 151.678,
+      "eval_steps_per_second": 18.96,
+      "step": 70
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.8137977227059614e-05,
+      "loss": 0.3188,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.8232758620689655,
+      "eval_loss": 0.4316616654396057,
+      "eval_runtime": 1.6492,
+      "eval_samples_per_second": 140.671,
+      "eval_steps_per_second": 17.584,
+      "step": 140
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.7200267916945747e-05,
+      "loss": 0.2842,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.7758620689655172,
+      "eval_loss": 0.5898870825767517,
+      "eval_runtime": 1.5155,
+      "eval_samples_per_second": 153.087,
+      "eval_steps_per_second": 19.136,
+      "step": 210
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.6262558606831884e-05,
+      "loss": 0.2794,
+      "step": 280
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.8448275862068966,
+      "eval_loss": 0.5094500184059143,
+      "eval_runtime": 1.6915,
+      "eval_samples_per_second": 137.154,
+      "eval_steps_per_second": 17.144,
+      "step": 280
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.533824514400536e-05,
+      "loss": 0.2598,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "eval_accuracy": 0.8405172413793104,
+      "eval_loss": 0.48097702860832214,
+      "eval_runtime": 1.4778,
+      "eval_samples_per_second": 156.993,
+      "eval_steps_per_second": 19.624,
+      "step": 350
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.4400535833891497e-05,
+      "loss": 0.2461,
+      "step": 420
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.8577586206896551,
+      "eval_loss": 0.47814619541168213,
+      "eval_runtime": 1.4344,
+      "eval_samples_per_second": 161.736,
+      "eval_steps_per_second": 20.217,
+      "step": 420
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.3476222371064971e-05,
+      "loss": 0.2338,
+      "step": 490
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.8577586206896551,
+      "eval_loss": 0.4246264100074768,
+      "eval_runtime": 1.7409,
+      "eval_samples_per_second": 133.263,
+      "eval_steps_per_second": 16.658,
+      "step": 490
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.2538513060951106e-05,
+      "loss": 0.2323,
+      "step": 560
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.8405172413793104,
+      "eval_loss": 0.4822118878364563,
+      "eval_runtime": 1.5407,
+      "eval_samples_per_second": 150.581,
+      "eval_steps_per_second": 18.823,
+      "step": 560
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.1600803750837242e-05,
+      "loss": 0.1967,
+      "step": 630
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.8060344827586207,
+      "eval_loss": 0.5343669652938843,
+      "eval_runtime": 1.5896,
+      "eval_samples_per_second": 145.95,
+      "eval_steps_per_second": 18.244,
+      "step": 630
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0663094440723377e-05,
+      "loss": 0.1964,
+      "step": 700
+    },
+    {
+      "epoch": 0.47,
+      "eval_accuracy": 0.8362068965517241,
+      "eval_loss": 0.4444664716720581,
+      "eval_runtime": 1.6432,
+      "eval_samples_per_second": 141.185,
+      "eval_steps_per_second": 17.648,
+      "step": 700
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.725385130609512e-06,
+      "loss": 0.1877,
+      "step": 770
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.8146551724137931,
+      "eval_loss": 0.5718417167663574,
+      "eval_runtime": 1.4594,
+      "eval_samples_per_second": 158.967,
+      "eval_steps_per_second": 19.871,
+      "step": 770
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.787675820495646e-06,
+      "loss": 0.1644,
+      "step": 840
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.8362068965517241,
+      "eval_loss": 0.5547271370887756,
+      "eval_runtime": 1.5651,
+      "eval_samples_per_second": 148.231,
+      "eval_steps_per_second": 18.529,
+      "step": 840
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.849966510381782e-06,
+      "loss": 0.1696,
+      "step": 910
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.8318965517241379,
+      "eval_loss": 0.6141758561134338,
+      "eval_runtime": 1.5041,
+      "eval_samples_per_second": 154.243,
+      "eval_steps_per_second": 19.28,
+      "step": 910
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.912257200267918e-06,
+      "loss": 0.1686,
+      "step": 980
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.8362068965517241,
+      "eval_loss": 0.5542225241661072,
+      "eval_runtime": 1.514,
+      "eval_samples_per_second": 153.237,
+      "eval_steps_per_second": 19.155,
+      "step": 980
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 5.974547890154053e-06,
+      "loss": 0.1494,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.8060344827586207,
+      "eval_loss": 0.67829829454422,
+      "eval_runtime": 1.5337,
+      "eval_samples_per_second": 151.268,
+      "eval_steps_per_second": 18.909,
+      "step": 1050
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 5.036838580040188e-06,
+      "loss": 0.1405,
+      "step": 1120
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.8017241379310345,
+      "eval_loss": 0.7149924635887146,
+      "eval_runtime": 1.4909,
+      "eval_samples_per_second": 155.615,
+      "eval_steps_per_second": 19.452,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.099129269926323e-06,
+      "loss": 0.1389,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.8060344827586207,
+      "eval_loss": 0.6625778079032898,
+      "eval_runtime": 1.5744,
+      "eval_samples_per_second": 147.356,
+      "eval_steps_per_second": 18.419,
+      "step": 1190
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.1614199598124583e-06,
+      "loss": 0.1456,
+      "step": 1260
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.8060344827586207,
+      "eval_loss": 0.619906485080719,
+      "eval_runtime": 1.5518,
+      "eval_samples_per_second": 149.504,
+      "eval_steps_per_second": 18.688,
+      "step": 1260
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 2.2237106496985938e-06,
+      "loss": 0.1236,
+      "step": 1330
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.8103448275862069,
+      "eval_loss": 0.6299593448638916,
+      "eval_runtime": 1.479,
+      "eval_samples_per_second": 156.858,
+      "eval_steps_per_second": 19.607,
+      "step": 1330
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.2860013395847288e-06,
+      "loss": 0.1105,
+      "step": 1400
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.8103448275862069,
+      "eval_loss": 0.6908773183822632,
+      "eval_runtime": 1.4889,
+      "eval_samples_per_second": 155.816,
+      "eval_steps_per_second": 19.477,
+      "step": 1400
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.482920294708641e-07,
+      "loss": 0.1128,
+      "step": 1470
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.8146551724137931,
+      "eval_loss": 0.6748644113540649,
+      "eval_runtime": 1.5998,
+      "eval_samples_per_second": 145.02,
+      "eval_steps_per_second": 18.127,
+      "step": 1470
+    },
+    {
+      "epoch": 1.0,
+      "step": 1493,
+      "total_flos": 1.4158017763099392e+16,
+      "train_loss": 0.19774836465486806,
+      "train_runtime": 1383.9705,
+      "train_samples_per_second": 34.538,
+      "train_steps_per_second": 1.079
+    }
+  ],
+  "max_steps": 1493,
+  "num_train_epochs": 1,
+  "total_flos": 1.4158017763099392e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8559804e7f3df1000800810d123596e37948a4dcbdce83afdc5bc4f62b207b50
+size 3055