Upload 12 files

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "../model/iter2/roberta-base/",
+  "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": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b550c872366848a71104d4ffcb9ce38c4b320178a1b07a695d59da7f9adc1978
+size 498640508

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e561880c5a3770db4668b5180db4562be7595aa6290f0c2d5c284c8978412ba
+size 997401227

readme.md

@@ -0,0 +1,3 @@
+Base model for error identification.
+
+Please cite our paper when using it.

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8fc2dac8c511a2d1d138defc5c36988a11a1d9ae89d102f39752f91ea9cd25
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd870779a2d1f19d526db5eefef955e95050292e6e80cc53c5bd74c19f50dd6
+size 1465

trainer_state.json

@@ -0,0 +1,41 @@
+{
+  "best_metric": 0.7021276595744681,
+  "best_model_checkpoint": "../model/iter3/roberta-base/checkpoint-216",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.311070919036865,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.1212,
+      "step": 216
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6692307692307692,
+      "eval_loss": 0.1722601354122162,
+      "eval_macro_f1": 0.5433354082106209,
+      "eval_micro_f1": 0.7021276595744681,
+      "eval_precision": 0.7279411764705882,
+      "eval_recall": 0.678082191780822,
+      "eval_runtime": 0.9143,
+      "eval_samples_per_second": 142.181,
+      "eval_steps_per_second": 9.843,
+      "step": 216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 907806492518400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239272dff4db0695404f8dfa5a4260d488ece61a2c2be8f5469fd7de5953cfc2
+size 5393