upload nace2_level1_42 model

config.json

@@ -0,0 +1,36 @@
+{
+  "_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": "2",
+    "1": "9"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "2": 0,
+    "9": 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": "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 sha256:634b318884f8b6934c3d16a4cf1acf2a30ee32b661341b59be729365ca780d45
+size 1421611309

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb44788eff298d21db432d051268b574a890e91981721c0b768b7d181e79a2d
+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 +1,112 @@
+{
+  "best_metric": 0.981159271079996,
+  "best_model_checkpoint": "./output//42_roberta-large_nace_5__5e-6_0.01_0.06_07-21-22_10-40/checkpoint-12000",
+  "epoch": 4.418262150220913,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.74,
+      "learning_rate": 4.535840188014101e-06,
+      "loss": 0.1726,
+      "step": 2000
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.9712155725823152,
+      "eval_f1": 0.9751469526657729,
+      "eval_loss": 0.08084136247634888,
+      "eval_roc_auc": 0.9750559610355007,
+      "eval_runtime": 143.2301,
+      "eval_samples_per_second": 33.715,
+      "step": 2000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.7524481002741874e-06,
+      "loss": 0.0668,
+      "step": 4000
+    },
+    {
+      "epoch": 1.47,
+      "eval_accuracy": 0.9726651480637813,
+      "eval_f1": 0.9771228359439407,
+      "eval_loss": 0.08218056708574295,
+      "eval_roc_auc": 0.9770191055094254,
+      "eval_runtime": 143.2878,
+      "eval_samples_per_second": 33.701,
+      "step": 4000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 2.969056012534274e-06,
+      "loss": 0.0501,
+      "step": 6000
+    },
+    {
+      "epoch": 2.21,
+      "eval_accuracy": 0.9749430523917996,
+      "eval_f1": 0.9794069192751236,
+      "eval_loss": 0.07129524648189545,
+      "eval_roc_auc": 0.9792922833616305,
+      "eval_runtime": 143.1874,
+      "eval_samples_per_second": 33.725,
+      "step": 6000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 2.18566392479436e-06,
+      "loss": 0.0377,
+      "step": 8000
+    },
+    {
+      "epoch": 2.95,
+      "eval_accuracy": 0.9757713812383516,
+      "eval_f1": 0.9797813080255828,
+      "eval_loss": 0.08654613047838211,
+      "eval_roc_auc": 0.9797172685997191,
+      "eval_runtime": 143.3834,
+      "eval_samples_per_second": 33.679,
+      "step": 8000
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.4022718370544457e-06,
+      "loss": 0.0254,
+      "step": 10000
+    },
+    {
+      "epoch": 3.68,
+      "eval_accuracy": 0.9743218057568854,
+      "eval_f1": 0.9794111591517397,
+      "eval_loss": 0.09397488832473755,
+      "eval_roc_auc": 0.979291082596074,
+      "eval_runtime": 143.2996,
+      "eval_samples_per_second": 33.699,
+      "step": 10000
+    },
+    {
+      "epoch": 4.42,
+      "learning_rate": 6.18879749314532e-07,
+      "loss": 0.0196,
+      "step": 12000
+    },
+    {
+      "epoch": 4.42,
+      "eval_accuracy": 0.9763926278732656,
+      "eval_f1": 0.981159271079996,
+      "eval_loss": 0.09825791418552399,
+      "eval_roc_auc": 0.981051940958186,
+      "eval_runtime": 143.2702,
+      "eval_samples_per_second": 33.706,
+      "step": 12000
+    }
+  ],
+  "max_steps": 13580,
+  "num_train_epochs": 5,
+  "total_flos": 6.9866971594752e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e29be6c16f421407d80ba77f94e95f9e2710e715b9e56f70d2f57544f489847
+size 2479