add

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "D:\\Users\\jiji\\Desktop\\nlp\\transformers\\examples\\pytorch\\language-modeling\\model\\checkpoint-2000",
+  "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": "4.21.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a242b7480b2363f8cf2518649ec9736224d8c1945b1357d4832c9824089310b
+size 818439513

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de49fe8b6a1ec3f83bb101a9577dc17dfe07cc2962ec6878efaf5fbdd75e498
+size 409232875

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2a591482d56f037f662d1ba0edecb4f0efd44d84cbde8ce433f4fe980ca7be
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd1310f0dba61f4c91a54dc53b3db4a53ac88089564e345dd61af19bb4e7bfeb
+size 623

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "D:\\Users\\jiji\\Desktop\\nlp\\transformers\\examples\\pytorch\\language-modeling\\model\\checkpoint-2000",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04552924495167396,
+  "global_step": 10500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9963865678609785e-05,
+      "loss": 1.9206,
+      "step": 500
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.992773135721956e-05,
+      "loss": 1.6087,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.989159703582935e-05,
+      "loss": 1.6003,
+      "step": 1500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9855462714439135e-05,
+      "loss": 1.6624,
+      "step": 2000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.981932839304891e-05,
+      "loss": 1.6501,
+      "step": 2500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9783194071658694e-05,
+      "loss": 1.648,
+      "step": 3000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9747059750268484e-05,
+      "loss": 1.6296,
+      "step": 3500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.971092542887826e-05,
+      "loss": 1.6759,
+      "step": 4000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9674791107488043e-05,
+      "loss": 1.6815,
+      "step": 4500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9638656786097827e-05,
+      "loss": 1.6881,
+      "step": 5000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.960252246470761e-05,
+      "loss": 1.6932,
+      "step": 5500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.956638814331739e-05,
+      "loss": 1.6802,
+      "step": 6000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9530253821927176e-05,
+      "loss": 1.6612,
+      "step": 6500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.949411950053696e-05,
+      "loss": 1.7148,
+      "step": 7000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.945798517914674e-05,
+      "loss": 1.7202,
+      "step": 7500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9421850857756525e-05,
+      "loss": 1.7063,
+      "step": 8000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.938571653636631e-05,
+      "loss": 1.7157,
+      "step": 8500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9349582214976085e-05,
+      "loss": 1.715,
+      "step": 9000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9313447893585874e-05,
+      "loss": 1.7405,
+      "step": 9500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.927731357219566e-05,
+      "loss": 1.7382,
+      "step": 10000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9241179250805434e-05,
+      "loss": 1.7077,
+      "step": 10500
+    }
+  ],
+  "max_steps": 691863,
+  "num_train_epochs": 3,
+  "total_flos": 2136390435903936.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730966aadaf025597fe2ec0df36a6c86fa7d52afd926b744a3c2264332bc52ec
+size 3247