upload fos model

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "../models/roberta-large/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "nace",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "Art",
+    "1": "Biology",
+    "2": "Business",
+    "3": "Chemistry",
+    "4": "Computer Science",
+    "5": "Economics",
+    "6": "Engineering",
+    "7": "Environmental Science",
+    "8": "Geography",
+    "9": "Geology",
+    "10": "History",
+    "11": "Materials Science",
+    "12": "Mathematics",
+    "13": "Medicine",
+    "14": "Philosophy",
+    "15": "Physics",
+    "16": "Political Science",
+    "17": "Psychology",
+    "18": "Sociology"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "Art": 0,
+    "Biology": 1,
+    "Business": 2,
+    "Chemistry": 3,
+    "Computer Science": 4,
+    "Economics": 5,
+    "Engineering": 6,
+    "Environmental Science": 7,
+    "Geography": 8,
+    "Geology": 9,
+    "History": 10,
+    "Materials Science": 11,
+    "Mathematics": 12,
+    "Medicine": 13,
+    "Philosophy": 14,
+    "Physics": 15,
+    "Political Science": 16,
+    "Psychology": 17,
+    "Sociology": 18
+  },
+  "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",
+  "transformers_version": "4.6.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d47c27a923a6cda14c5ed153c6601c3e1918d3b6ec50683e4240d04f256768
+size 2843262493

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904c4b71bbf089ea7864757c877c2950671ae6cc75d2f95e2f48e00a8586a91a
+size 1421681005

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e90f1345986502ffb3f500ea6d1b484187c5f83a6f051ae2d30f98cc82db9a
+size 15523

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396a57403ef857fb5d322349ea51b7f10b639efd5e0c529a85f3324f2ac9c15b
+size 623

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/"}

trainer_state.json

@@ -0,0 +1,288 @@
+{
+  "best_metric": 0.6985175177661591,
+  "best_model_checkpoint": "./output//roberta-large_nace_5__5e-5_0.01_0.06_07-21-22_16-22/checkpoint-26000",
+  "epoch": 0.10478545947653499,
+  "global_step": 34000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.0273057878408088e-06,
+      "loss": 0.3175,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.2783648835349153,
+      "eval_f1": 0.46687230297082155,
+      "eval_loss": 0.1457696259021759,
+      "eval_roc_auc": 0.6606907669432402,
+      "eval_runtime": 2510.5482,
+      "eval_samples_per_second": 32.867,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.0546115756816175e-06,
+      "loss": 0.1255,
+      "step": 4000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.459812880238505,
+      "eval_f1": 0.6263968944830018,
+      "eval_loss": 0.10650500655174255,
+      "eval_roc_auc": 0.7560059946779483,
+      "eval_runtime": 2508.5898,
+      "eval_samples_per_second": 32.893,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.0819173635224263e-06,
+      "loss": 0.1042,
+      "step": 6000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.5097801585185544,
+      "eval_f1": 0.6604502012072435,
+      "eval_loss": 0.0960676446557045,
+      "eval_roc_auc": 0.780487395930802,
+      "eval_runtime": 2510.7767,
+      "eval_samples_per_second": 32.864,
+      "step": 6000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.109223151363235e-06,
+      "loss": 0.0962,
+      "step": 8000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.5427684998909276,
+      "eval_f1": 0.6739507307713664,
+      "eval_loss": 0.09160555154085159,
+      "eval_roc_auc": 0.7915836904940926,
+      "eval_runtime": 2512.9385,
+      "eval_samples_per_second": 32.836,
+      "step": 8000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.136528939204044e-06,
+      "loss": 0.0926,
+      "step": 10000
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.5522093220544393,
+      "eval_f1": 0.6834786765291677,
+      "eval_loss": 0.08829274028539658,
+      "eval_roc_auc": 0.7978195145032272,
+      "eval_runtime": 2516.7533,
+      "eval_samples_per_second": 32.786,
+      "step": 10000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.1638347270448526e-06,
+      "loss": 0.0905,
+      "step": 12000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.5546452723174249,
+      "eval_f1": 0.6794668300903938,
+      "eval_loss": 0.08848168700933456,
+      "eval_roc_auc": 0.7959266090899211,
+      "eval_runtime": 2514.7748,
+      "eval_samples_per_second": 32.812,
+      "step": 12000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.191140514885661e-06,
+      "loss": 0.089,
+      "step": 14000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.557250890757932,
+      "eval_f1": 0.687455713685222,
+      "eval_loss": 0.08794952929019928,
+      "eval_roc_auc": 0.8052103848950731,
+      "eval_runtime": 2514.8342,
+      "eval_samples_per_second": 32.811,
+      "step": 14000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.21844630272647e-06,
+      "loss": 0.088,
+      "step": 16000
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.5636498048815959,
+      "eval_f1": 0.6874285817931185,
+      "eval_loss": 0.08668860048055649,
+      "eval_roc_auc": 0.8033362882753715,
+      "eval_runtime": 2516.4721,
+      "eval_samples_per_second": 32.79,
+      "step": 16000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.24575209056728e-06,
+      "loss": 0.0871,
+      "step": 18000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.5651525801682139,
+      "eval_f1": 0.6958583698677593,
+      "eval_loss": 0.08520551770925522,
+      "eval_roc_auc": 0.8107390175102938,
+      "eval_runtime": 2518.4918,
+      "eval_samples_per_second": 32.763,
+      "step": 18000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0273057878408088e-05,
+      "loss": 0.087,
+      "step": 20000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.573066388734033,
+      "eval_f1": 0.6973633931983186,
+      "eval_loss": 0.08506815880537033,
+      "eval_roc_auc": 0.8115768508510465,
+      "eval_runtime": 2519.3256,
+      "eval_samples_per_second": 32.752,
+      "step": 20000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1300363666248896e-05,
+      "loss": 0.0861,
+      "step": 22000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.5722059286908888,
+      "eval_f1": 0.6942218473218051,
+      "eval_loss": 0.0845654234290123,
+      "eval_roc_auc": 0.8075303988101568,
+      "eval_runtime": 2516.7809,
+      "eval_samples_per_second": 32.786,
+      "step": 22000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.2327669454089705e-05,
+      "loss": 0.0859,
+      "step": 24000
+    },
+    {
+      "epoch": 0.07,
+      "eval_accuracy": 0.5684974670964927,
+      "eval_f1": 0.6959252561784207,
+      "eval_loss": 0.08408927917480469,
+      "eval_roc_auc": 0.8082295703584903,
+      "eval_runtime": 2517.9216,
+      "eval_samples_per_second": 32.771,
+      "step": 24000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3354975241930514e-05,
+      "loss": 0.0852,
+      "step": 26000
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.5729209588675861,
+      "eval_f1": 0.6985175177661591,
+      "eval_loss": 0.08367094397544861,
+      "eval_roc_auc": 0.8080635277752549,
+      "eval_runtime": 2517.5004,
+      "eval_samples_per_second": 32.776,
+      "step": 26000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4382281029771322e-05,
+      "loss": 0.0852,
+      "step": 28000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.5761082967738808,
+      "eval_f1": 0.6972306734063196,
+      "eval_loss": 0.08429088443517685,
+      "eval_roc_auc": 0.8106490105342776,
+      "eval_runtime": 2518.0349,
+      "eval_samples_per_second": 32.769,
+      "step": 28000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5409586817612133e-05,
+      "loss": 0.0849,
+      "step": 30000
+    },
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.566861381098965,
+      "eval_f1": 0.6942268289743281,
+      "eval_loss": 0.08503852039575577,
+      "eval_roc_auc": 0.807482831888307,
+      "eval_runtime": 2516.78,
+      "eval_samples_per_second": 32.786,
+      "step": 30000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.643689260545294e-05,
+      "loss": 0.0848,
+      "step": 32000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.5588627384443852,
+      "eval_f1": 0.6923745410036719,
+      "eval_loss": 0.08319058269262314,
+      "eval_roc_auc": 0.8023797746651582,
+      "eval_runtime": 2516.0951,
+      "eval_samples_per_second": 32.794,
+      "step": 32000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.7464198393293748e-05,
+      "loss": 0.0849,
+      "step": 34000
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.5693700462951742,
+      "eval_f1": 0.6952779925325279,
+      "eval_loss": 0.08376839756965637,
+      "eval_roc_auc": 0.8095160304055978,
+      "eval_runtime": 2518.8664,
+      "eval_samples_per_second": 32.758,
+      "step": 34000
+    }
+  ],
+  "max_steps": 1622360,
+  "num_train_epochs": 5,
+  "total_flos": 6.9870397489152e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c977e870cd84212a10faad154616e0c5af4e2ac825e4f21da3ab262904d3c624
+size 2479