added model

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "distilbert-base-cased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.0.dev0",
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71445761097e707dddcbc105d01c55f84fa4a2a4fc366ae878dec7192911ad2a
+size 526327977

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28dd79ecb0adf125e697b21e5e83837251bd08054fc295d80e6b920b0eee3d0
+size 263174287

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1b379e3f479f666b3735554652330d68800c321c8235592ba6750ea30a479a
+size 14649

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a30656fcdfc4d0c89d1f2b76eff1eaadef807c69e180832bb3fe2adea1df336
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilbert-base-cased", "tokenizer_class": "DistilBertTokenizer"}

trainer_state.json

@@ -0,0 +1,82 @@
+{
+  "best_metric": 0.7565779291131405,
+  "best_model_checkpoint": "output-no-git/EN-OUTPUT/distilbert-base-cased/FalseTrue-0/2/checkpoint-520",
+  "epoch": 5.0,
+  "global_step": 520,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7446351647377014,
+      "eval_f1": 0.7378445712448767,
+      "eval_f1_binary": 0.7800369685767097,
+      "eval_f1_weighted": 0.7470798170127886,
+      "eval_loss": 0.7295559048652649,
+      "eval_runtime": 0.9453,
+      "eval_samples_per_second": 492.97,
+      "eval_steps_per_second": 62.415,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7424892783164978,
+      "eval_f1": 0.7401728463897408,
+      "eval_f1_binary": 0.7647058823529411,
+      "eval_f1_weighted": 0.7455427383816858,
+      "eval_loss": 0.9534124732017517,
+      "eval_runtime": 0.7364,
+      "eval_samples_per_second": 632.823,
+      "eval_steps_per_second": 80.121,
+      "step": 208
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7618025541305542,
+      "eval_f1": 0.7543816329922364,
+      "eval_f1_binary": 0.7970749542961609,
+      "eval_f1_weighted": 0.7637265230630523,
+      "eval_loss": 1.0867007970809937,
+      "eval_runtime": 0.736,
+      "eval_samples_per_second": 633.169,
+      "eval_steps_per_second": 80.165,
+      "step": 312
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7532188892364502,
+      "eval_f1": 0.7470105321795617,
+      "eval_f1_binary": 0.7866419294990724,
+      "eval_f1_weighted": 0.7556852157130167,
+      "eval_loss": 1.2413438558578491,
+      "eval_runtime": 0.7367,
+      "eval_samples_per_second": 632.508,
+      "eval_steps_per_second": 80.082,
+      "step": 416
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 9.316239316239318e-06,
+      "loss": 0.1347,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7682403326034546,
+      "eval_f1": 0.7565779291131405,
+      "eval_f1_binary": 0.8098591549295775,
+      "eval_f1_weighted": 0.7682403433476395,
+      "eval_loss": 1.2424249649047852,
+      "eval_runtime": 0.7359,
+      "eval_samples_per_second": 633.202,
+      "eval_steps_per_second": 80.169,
+      "step": 520
+    }
+  ],
+  "max_steps": 936,
+  "num_train_epochs": 9,
+  "total_flos": 550898794160640.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32828f31b46ce6b06ec54c7895e01003dafbca56a8af9b867f2b06c70908f98
+size 2735