Add model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 1.283639632165432
+perplexity = tensor(3.6098)

model_args.json

@@ -0,0 +1 @@
+{"adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 1, "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": 32, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 20, "evaluate_during_training_verbose": false, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "roberta-large", "model_type": "roberta", "multiprocessing_chunksize": 500, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 25, "output_dir": "outputs/", "overwrite_output_dir": true, "process_count": 70, "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_recent_only": true, "save_steps": 2000, "silent": false, "tensorboard_dir": null, "thread_count": null, "train_batch_size": 16, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": false, "use_multiprocessing": false, "wandb_kwargs": {"name": "roberta-large"}, "wandb_project": "lm", "warmup_ratio": 0.06, "warmup_steps": 224, "weight_decay": 0, "skip_special_tokens": true, "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": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "tokenizer_name": "roberta-large", "vocab_size": null, "clean_text": true, "handle_chinese_chars": true, "strip_accents": true, "use_hf_datasets": false, "optimizer": "AdamW", "adam_betas": [0.9, 0.999], "scheduler": "linear_schedule_with_warmup"}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7f7e87584ea11bd47198778a4c8b9997be18b9298926a274fa5f4b64d492e2
+size 2843625659

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db16634c829ecbdaee4f14991bfea9919e8b50424f82b9560e2b6847ddd53a6d
+size 1421815481

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b5810e25b504d7a05b03b2995a3077a31b3f1f5d28e2412b62a52a963756f35
+size 627

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "cache_dir/e16a2590deb9e6d73711d6e05bf27d832fa8c1162d807222e043ca650a556964.fc9576039592f026ad76a1c231b89aee8668488c671dfbe6616bab2ed298d730", "name_or_path": "roberta-large", "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0788536d16567f9020e517515a70c520bfbdef1c71905eaf65e40be4d82282cb
+size 3003