upload nace2_level1_28 model

config.json

@@ -0,0 +1,42 @@
+{
+  "_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": "1",
+    "1": "2",
+    "2": "3",
+    "3": "4",
+    "4": "9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "1": 0,
+    "2": 1,
+    "3": 2,
+    "4": 3,
+    "9": 4
+  },
+  "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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24ad3e647c4645dbe97f2cbac3c58cf9c3555828581ff9ee4620d0a9916f614b
+size 1421623597

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9d0add05500e427d7ed5e950ba488ee4ff92ba1bb784bc84bd405999491ff2
+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/"}

trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_metric": 0.8505891563864203,
+  "best_model_checkpoint": "./output//28_roberta-large_nace_5__5e-6_0.01_0.06_07-21-22_10-40/checkpoint-16000",
+  "epoch": 0.06421396091777803,
+  "global_step": 16000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.3377747454883547e-07,
+      "loss": 0.5803,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "eval_accuracy": 0.002219141961875006,
+      "eval_f1": 0.004815820909835742,
+      "eval_loss": 0.4762592911720276,
+      "eval_roc_auc": 0.4995028806565217,
+      "eval_runtime": 13327.9977,
+      "eval_samples_per_second": 33.236,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.6755494909767094e-07,
+      "loss": 0.3811,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.6265994527772009,
+      "eval_f1": 0.7223735823190928,
+      "eval_loss": 0.28443753719329834,
+      "eval_roc_auc": 0.8082289013358491,
+      "eval_runtime": 13329.5463,
+      "eval_samples_per_second": 33.232,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.013324236465065e-07,
+      "loss": 0.2627,
+      "step": 6000
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.7253907766771115,
+      "eval_f1": 0.7919750914486393,
+      "eval_loss": 0.22472703456878662,
+      "eval_roc_auc": 0.8576420537998708,
+      "eval_runtime": 13320.5922,
+      "eval_samples_per_second": 33.254,
+      "step": 6000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.351098981953419e-07,
+      "loss": 0.2193,
+      "step": 8000
+    },
+    {
+      "epoch": 0.03,
+      "eval_accuracy": 0.7562691324802918,
+      "eval_f1": 0.8144825798742746,
+      "eval_loss": 0.20236817002296448,
+      "eval_roc_auc": 0.8730890185004464,
+      "eval_runtime": 13323.985,
+      "eval_samples_per_second": 33.246,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.688873727441773e-07,
+      "loss": 0.1991,
+      "step": 10000
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.7722049647375407,
+      "eval_f1": 0.8289314788242148,
+      "eval_loss": 0.18846644461154938,
+      "eval_roc_auc": 0.8831482505191296,
+      "eval_runtime": 13322.5542,
+      "eval_samples_per_second": 33.249,
+      "step": 10000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.02664847293013e-07,
+      "loss": 0.1878,
+      "step": 12000
+    },
+    {
+      "epoch": 0.05,
+      "eval_accuracy": 0.7822215800832574,
+      "eval_f1": 0.837804383735982,
+      "eval_loss": 0.17950177192687988,
+      "eval_roc_auc": 0.8893622425676875,
+      "eval_runtime": 13327.9426,
+      "eval_samples_per_second": 33.236,
+      "step": 12000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.364423218418484e-07,
+      "loss": 0.1806,
+      "step": 14000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.7860525911812246,
+      "eval_f1": 0.8418071128806041,
+      "eval_loss": 0.17355895042419434,
+      "eval_roc_auc": 0.8909973044567995,
+      "eval_runtime": 13332.0958,
+      "eval_samples_per_second": 33.225,
+      "step": 14000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0702197963906837e-06,
+      "loss": 0.171,
+      "step": 16000
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.796651646634941,
+      "eval_f1": 0.8505891563864203,
+      "eval_loss": 0.16524717211723328,
+      "eval_roc_auc": 0.8974221260411068,
+      "eval_runtime": 13333.5968,
+      "eval_samples_per_second": 33.222,
+      "step": 16000
+    }
+  ],
+  "max_steps": 1245835,
+  "num_train_epochs": 5,
+  "total_flos": 6.9867576164352e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb701c89f56d62eb53b8302216875aba9c0ac0651cd8d2451b6673ab54f3706
+size 2479