Upload 11 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 261
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 128,
+  "n_head": 8,
+  "n_inner": null,
+  "n_layer": 8,
+  "n_positions": 1024,
+  "output_dir": "./",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "show_running_loss": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 262
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 0.36027592917283374
+perplexity = tensor(1.4337)

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.35.0"
+}

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a25c1f0862644bee2f59218ef808e956e61c97bc7edb181200faf138f38c42b
+size 7013872

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": {"n_head": 8, "n_layer": 8, "n_embd": 128}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": true, "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": 2, "encoding": null, "eval_batch_size": 1, "evaluate_during_training": false, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 2000, "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": "gpt2", "multiprocessing_chunksize": -1, "n_gpu": 1, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 500, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 1, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": false, "save_optimizer_and_scheduler": false, "save_steps": 3000, "scheduler": "linear_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "outputs/", "tokenizer_type": null, "train_batch_size": 1, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": true, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": null, "warmup_ratio": 0.06, "warmup_steps": 180, "weight_decay": 0.0, "model_class": "LanguageModelingModel", "block_size": 128, "config_name": null, "dataset_class": null, "dataset_type": "text", "discriminator_config": {}, "discriminator_loss_weight": 50.0, "generator_config": {}, "max_steps": -1, "min_frequency": 2, "mlm": false, "mlm_probability": 0.15, "sliding_window": false, "special_tokens": ["<s>", "<pad>", "</s>", "<unk>", "<mask>"], "stride": 0.8, "tie_generator_and_discriminator_embeddings": true, "vocab_size": 50, "clean_text": true, "handle_chinese_chars": true, "special_tokens_list": [], "strip_accents": true}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "261": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4974f3e28e7aa000ca36ab6908a880068cfd9118ccd479dad39b2b1c5abdec
+size 3896

vocab.json

@@ -0,0 +1,263 @@
+{
+  "!": 5,
+  "\"": 6,
+  "#": 7,
+  "$": 8,
+  "%": 9,
+  "&": 10,
+  "'": 11,
+  "(": 12,
+  ")": 13,
+  "*": 14,
+  "+": 15,
+  ",": 16,
+  "-": 17,
+  ".": 18,
+  "/": 19,
+  "0": 20,
+  "1": 21,
+  "2": 22,
+  "3": 23,
+  "4": 24,
+  "5": 25,
+  "6": 26,
+  "7": 27,
+  "8": 28,
+  "9": 29,
+  ":": 30,
+  ";": 31,
+  "<": 32,
+  "</s>": 2,
+  "<mask>": 4,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3,
+  "=": 33,
+  ">": 34,
+  "?": 35,
+  "@": 36,
+  "A": 37,
+  "B": 38,
+  "C": 39,
+  "D": 40,
+  "E": 41,
+  "F": 42,
+  "G": 43,
+  "H": 44,
+  "I": 45,
+  "J": 46,
+  "K": 47,
+  "L": 48,
+  "M": 49,
+  "N": 50,
+  "O": 51,
+  "P": 52,
+  "Q": 53,
+  "R": 54,
+  "S": 55,
+  "T": 56,
+  "U": 57,
+  "V": 58,
+  "W": 59,
+  "X": 60,
+  "Y": 61,
+  "Z": 62,
+  "[": 63,
+  "\\": 64,
+  "]": 65,
+  "^": 66,
+  "_": 67,
+  "`": 68,
+  "a": 69,
+  "b": 70,
+  "c": 71,
+  "d": 72,
+  "e": 73,
+  "f": 74,
+  "g": 75,
+  "h": 76,
+  "i": 77,
+  "j": 78,
+  "k": 79,
+  "l": 80,
+  "m": 81,
+  "n": 82,
+  "o": 83,
+  "p": 84,
+  "q": 85,
+  "r": 86,
+  "s": 87,
+  "t": 88,
+  "u": 89,
+  "v": 90,
+  "w": 91,
+  "x": 92,
+  "y": 93,
+  "z": 94,
+  "{": 95,
+  "|": 96,
+  "}": 97,
+  "~": 98,
+  "¡": 99,
+  "¢": 100,
+  "£": 101,
+  "¤": 102,
+  "¥": 103,
+  "¦": 104,
+  "§": 105,
+  "¨": 106,
+  "©": 107,
+  "ª": 108,
+  "«": 109,
+  "¬": 110,
+  "®": 111,
+  "¯": 112,
+  "°": 113,
+  "±": 114,
+  "²": 115,
+  "³": 116,
+  "´": 117,
+  "µ": 118,
+  "¶": 119,
+  "·": 120,
+  "¸": 121,
+  "¹": 122,
+  "º": 123,
+  "»": 124,
+  "¼": 125,
+  "½": 126,
+  "¾": 127,
+  "¿": 128,
+  "À": 129,
+  "Á": 130,
+  "Â": 131,
+  "Ã": 132,
+  "Ä": 133,
+  "Å": 134,
+  "Æ": 135,
+  "Ç": 136,
+  "È": 137,
+  "É": 138,
+  "Ê": 139,
+  "Ë": 140,
+  "Ì": 141,
+  "Í": 142,
+  "Î": 143,
+  "Ï": 144,
+  "Ð": 145,
+  "Ñ": 146,
+  "Ò": 147,
+  "Ó": 148,
+  "Ô": 149,
+  "Õ": 150,
+  "Ö": 151,
+  "×": 152,
+  "Ø": 153,
+  "Ù": 154,
+  "Ú": 155,
+  "Û": 156,
+  "Ü": 157,
+  "Ý": 158,
+  "Þ": 159,
+  "ß": 160,
+  "à": 161,
+  "á": 162,
+  "â": 163,
+  "ã": 164,
+  "ä": 165,
+  "å": 166,
+  "æ": 167,
+  "ç": 168,
+  "è": 169,
+  "é": 170,
+  "ê": 171,
+  "ë": 172,
+  "ì": 173,
+  "í": 174,
+  "î": 175,
+  "ï": 176,
+  "ð": 177,
+  "ñ": 178,
+  "ò": 179,
+  "ó": 180,
+  "ô": 181,
+  "õ": 182,
+  "ö": 183,
+  "÷": 184,
+  "ø": 185,
+  "ù": 186,
+  "ú": 187,
+  "û": 188,
+  "ü": 189,
+  "ý": 190,
+  "þ": 191,
+  "ÿ": 192,
+  "Ā": 193,
+  "ā": 194,
+  "Ă": 195,
+  "ă": 196,
+  "Ą": 197,
+  "ą": 198,
+  "Ć": 199,
+  "ć": 200,
+  "Ĉ": 201,
+  "ĉ": 202,
+  "Ċ": 203,
+  "ċ": 204,
+  "Č": 205,
+  "č": 206,
+  "Ď": 207,
+  "ď": 208,
+  "Đ": 209,
+  "đ": 210,
+  "Ē": 211,
+  "ē": 212,
+  "Ĕ": 213,
+  "ĕ": 214,
+  "Ė": 215,
+  "ė": 216,
+  "Ę": 217,
+  "ę": 218,
+  "Ě": 219,
+  "ě": 220,
+  "Ĝ": 221,
+  "ĝ": 222,
+  "Ğ": 223,
+  "ğ": 224,
+  "Ġ": 225,
+  "ġ": 226,
+  "Ģ": 227,
+  "ģ": 228,
+  "Ĥ": 229,
+  "ĥ": 230,
+  "Ħ": 231,
+  "ħ": 232,
+  "Ĩ": 233,
+  "ĩ": 234,
+  "Ī": 235,
+  "ī": 236,
+  "Ĭ": 237,
+  "ĭ": 238,
+  "Į": 239,
+  "į": 240,
+  "İ": 241,
+  "ı": 242,
+  "IJ": 243,
+  "ij": 244,
+  "Ĵ": 245,
+  "ĵ": 246,
+  "Ķ": 247,
+  "ķ": 248,
+  "ĸ": 249,
+  "Ĺ": 250,
+  "ĺ": 251,
+  "Ļ": 252,
+  "ļ": 253,
+  "Ľ": 254,
+  "ľ": 255,
+  "Ŀ": 256,
+  "ŀ": 257,
+  "Ł": 258,
+  "ł": 259,
+  "Ń": 260
+}