model first version

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/groups/gcc50435/ou/cjkbert/cjkbert-base/epoch-15/",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 2,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 15015
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a786f22e81efbea199a6eb27871240bd6b954d769c7a47bbda370acb461598d1
+size 390429291

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 @@
+{"tokenizer_class": "PreTrainedTokenizerFast"}

train_results.txt

@@ -0,0 +1,5 @@
+epoch = 20.0
+train_loss = 0.4021474394976566
+train_runtime = 51134.1112
+train_samples_per_second = 11365.472
+train_steps_per_second = 44.396

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.999995595043544,
+  "global_step": 2270160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.666798815942489e-05,
+      "loss": 2.7208,
+      "step": 113508
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.3335917585838296e-05,
+      "loss": 2.1526,
+      "step": 227016
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.000384701225171e-05,
+      "loss": 2.0051,
+      "step": 340524
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.667171770565364e-05,
+      "loss": 1.9189,
+      "step": 454032
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 3.3339647132067057e-05,
+      "loss": 1.8591,
+      "step": 567540
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.000757655848046e-05,
+      "loss": 1.8134,
+      "step": 681048
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.6675505984893874e-05,
+      "loss": 1.7768,
+      "step": 794556
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.3343376678295804e-05,
+      "loss": 1.7453,
+      "step": 908064
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 2.001136483772069e-05,
+      "loss": 1.7178,
+      "step": 1021572
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.6679294264134097e-05,
+      "loss": 1.6944,
+      "step": 1135080
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 1.334719432404177e-05,
+      "loss": 1.6729,
+      "step": 1248588
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 1.0015123750455182e-05,
+      "loss": 1.6535,
+      "step": 1362096
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 6.683023810362853e-06,
+      "loss": 1.6363,
+      "step": 1475604
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 3.350953236776263e-06,
+      "loss": 1.6216,
+      "step": 1589112
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 1.8882663189672388e-08,
+      "loss": 1.6102,
+      "step": 1702620
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 1.0015065017443704e-05,
+      "loss": 1.6294,
+      "step": 1816128
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 7.515968037495155e-06,
+      "loss": 1.6191,
+      "step": 1929636
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 5.016915107305212e-06,
+      "loss": 1.6079,
+      "step": 2043144
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 2.517884201994573e-06,
+      "loss": 1.5972,
+      "step": 2156652
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 1.8831271804630513e-08,
+      "loss": 1.5893,
+      "step": 2270160
+    },
+    {
+      "epoch": 20.0,
+      "step": 2270160,
+      "total_flos": 3.805740641757115e+19,
+      "train_loss": 0.4021474394976566,
+      "train_runtime": 51134.1112,
+      "train_samples_per_second": 11365.472,
+      "train_steps_per_second": 44.396
+    }
+  ],
+  "max_steps": 2270160,
+  "num_train_epochs": 20,
+  "total_flos": 3.805740641757115e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01bce61e4e4d2babd6021cf619298cb8992c8b6863fd1035638a1a05d354c73c
+size 3247