Initial commit

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ckpt_mlm/bert-base-multilingual-cased/checkpoint-12000/",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "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": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764a233c2fea23964b489c86974663b2fdef953e34466739a536f11670157a35
+size 711969707

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.38807321648017595,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.973158269193455e-05,
+      "loss": 1.1361,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9462087402712206e-05,
+      "loss": 1.0853,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.919259211348986e-05,
+      "loss": 1.0513,
+      "step": 1500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.892309682426751e-05,
+      "loss": 1.0224,
+      "step": 2000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.8654140525623614e-05,
+      "loss": 1.0188,
+      "step": 2500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.838464523640127e-05,
+      "loss": 0.9882,
+      "step": 3000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.811514994717893e-05,
+      "loss": 0.9726,
+      "step": 3500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.784565465795658e-05,
+      "loss": 0.9692,
+      "step": 4000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.757615936873423e-05,
+      "loss": 0.9499,
+      "step": 4500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.730666407951189e-05,
+      "loss": 0.9558,
+      "step": 5000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.703770778086799e-05,
+      "loss": 0.9387,
+      "step": 5500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.676821249164565e-05,
+      "loss": 0.924,
+      "step": 6000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.6498717202423306e-05,
+      "loss": 0.9163,
+      "step": 6500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.622922191320096e-05,
+      "loss": 0.9206,
+      "step": 7000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.5959726623978616e-05,
+      "loss": 0.9196,
+      "step": 7500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.5690231334756274e-05,
+      "loss": 0.9009,
+      "step": 8000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.5420736045533925e-05,
+      "loss": 0.9045,
+      "step": 8500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.5151240756311583e-05,
+      "loss": 0.9058,
+      "step": 9000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.488282344824612e-05,
+      "loss": 0.8905,
+      "step": 9500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.461332815902378e-05,
+      "loss": 0.8932,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.434383286980144e-05,
+      "loss": 0.8844,
+      "step": 10500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.4074337580579096e-05,
+      "loss": 0.8951,
+      "step": 11000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.3804842291356755e-05,
+      "loss": 0.8806,
+      "step": 11500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.35353470021344e-05,
+      "loss": 0.8887,
+      "step": 12000
+    }
+  ],
+  "max_steps": 92766,
+  "num_train_epochs": 3,
+  "total_flos": 3.31877922352704e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8058a53d7363d5f2861dc8fb13391f6aeb92735da2a0ab882780080bfd828c
+size 3567