Upload 10 files

config.json

@@ -0,0 +1,24 @@
+{
+  "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": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 2.12218203996621
+perplexity = tensor(8.3493)

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.3"
+}

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_betas": [0.9, 0.999], "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 96, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 70000, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 4e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": null, "model_type": "bert", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 20, "optimizer": "AdamW", "output_dir": "BERT", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 38, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "BERT", "tokenizer_type": null, "train_batch_size": 96, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 40163, "weight_decay": 0.0, "model_class": "LanguageModelingModel", "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "simple", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": true, "mlm_probability": 0.15, "sliding_window": false, "special_tokens": ["[PAD]", "[UNK]", "[CLS]", "[SEP]", "[MASK]"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "vocab_size": 30000, "clean_text": true, "handle_chinese_chars": true, "special_tokens_list": [], "strip_accents": true}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09c29b3512b0e0e1992c52d89d1a1ec9fcd9efc0cf4d5faed96fd6ad5f2daf0
+size 436523179

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 +1,15 @@
+{
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e95d24c96810f016818518693c2672b24e66f1791f53f48b72f71f13eeae7744
+size 3439

training_progress_scores.csv

@@ -0,0 +1,30 @@
+global_step,perplexity,eval_loss,train_loss
+33469,tensor(495.9851),6.20654563341468,5.897248268127441
+66938,tensor(168.4102),5.126402866097105,4.590975284576416
+70000,tensor(80.6666),4.390325209321234,3.7873992919921875
+100407,tensor(21.6076),3.0730473043666247,2.3850345611572266
+133876,tensor(15.5963),2.7470345135873617,2.2173330783843994
+140000,tensor(15.0608),2.7120934600355313,2.068357467651367
+167345,tensor(13.4429),2.598450262515426,2.157835006713867
+200814,tensor(12.2196),2.503041290542594,1.883992314338684
+210000,tensor(11.8532),2.4726015753277033,1.8340803384780884
+234283,tensor(11.3319),2.4276199680327677,1.8948110342025757
+267752,tensor(10.7101),2.3711857266360403,1.6326630115509033
+280000,tensor(10.5675),2.3577842654497396,1.7336448431015015
+301221,tensor(10.3335),2.335391764582615,2.0111379623413086
+334690,tensor(9.9195),2.2945015443270194,1.8034934997558594
+350000,tensor(9.7949),2.2818656015246312,1.4923876523971558
+368159,tensor(9.6421),2.2661435398259218,1.703298807144165
+401628,tensor(9.3831),2.238909857998498,1.773614764213562
+420000,tensor(9.2530),2.224950270643552,1.617546796798706
+435097,tensor(9.1846),2.217525634185423,1.5115395784378052
+468566,tensor(8.9720),2.194107189911353,1.1986712217330933
+490000,tensor(8.8782),2.1836008869576076,1.4819477796554565
+502035,tensor(8.8325),2.1784429578691245,1.4174996614456177
+535504,tensor(8.6801),2.161031563812664,1.6201128959655762
+560000,tensor(8.5960),2.151301508107699,1.6956605911254883
+568973,tensor(8.5537),2.146366256599325,1.7156400680541992
+602442,tensor(8.4695),2.1364745169431476,1.6572712659835815
+630000,tensor(8.4023),2.128499818847858,1.428807258605957
+635911,tensor(8.3994),2.1281595396903357,1.6430681943893433
+669380,tensor(8.3442),2.1215673249634412,1.7592811584472656