new model

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/groups/0/gcc50435/ou/cjkbert/cjkbert-small-5epoch/checkpoint-454034/",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 2,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "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:f5794941042239687cc44b674a3c56a1cf23c00308498efbc69014bb0590656b
+size 100182532

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 = 5.0
+train_loss = 1.4089593235308369
+train_runtime = 87255.1901
+train_samples_per_second = 1665.125
+train_steps_per_second = 13.009

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1135085,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.000405255994045e-05,
+      "loss": 3.0415,
+      "step": 227017
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.000801702075175e-05,
+      "loss": 2.5231,
+      "step": 454034
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.0011805283304773e-05,
+      "loss": 2.4052,
+      "step": 681051
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.001612214063264e-05,
+      "loss": 2.3395,
+      "step": 908068
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.052709708964527e-08,
+      "loss": 2.3001,
+      "step": 1135085
+    },
+    {
+      "epoch": 5.0,
+      "step": 1135085,
+      "total_flos": 1.9066978434981486e+18,
+      "train_loss": 1.4089593235308369,
+      "train_runtime": 87255.1901,
+      "train_samples_per_second": 1665.125,
+      "train_steps_per_second": 13.009
+    }
+  ],
+  "max_steps": 1135085,
+  "num_train_epochs": 5,
+  "total_flos": 1.9066978434981486e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8997bd28ac59f142bd358ec47ffd54a94605b667e513112c2f2aa29cb429963b
+size 3119