Upload folder using huggingface_hub

llm/fw57M-multi-tied/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

llm/fw57M-multi-tied/README.md

@@ -0,0 +1,92 @@
+---
+{}
+---
+## Experiment Configuration
+```yaml
+callbacks:
+  grad_accum:
+    _target_: src.callbacks.gradient_accumulation.GradientAccumulationScheduler
+    scheduling:
+      0: 2
+  grad_norm:
+    _target_: src.callbacks.grad_norm.GradNorm
+    check_clipping: false
+    group_separator: /
+    histogram_freq: null
+    log_weight_distribution: false
+    norm_type: 2
+    only_total: true
+  lr_monitor:
+    _target_: src.callbacks.lr_monitor.SimpleLearningRateMonitor
+  model_checkpoint:
+    _target_: src.callbacks.model_checkpoint.ModelCheckpoint
+    dirpath: .checkpoints
+    enable_version_counter: false
+    every_n_train_steps: 1000
+    filename: '{step}'
+    save_initial_checkpoint: true
+    save_last: link
+    save_top_k: -1
+    verbose: true
+  speed_monitor:
+    _target_: src.callbacks.speed_monitor.SpeedMonitor
+data:
+  batch_size: 64
+  drop_last: false
+  eval_batch_size: 64
+  multiprocessing_context: null
+  num_workers: 12
+  persistent_workers: false
+  pin_memory: true
+  prefetch_factor: 2
+  shuffle: true
+dataset: common-corpus
+evaluation:
+  blimp: false
+loggers:
+  tensorboard:
+    _target_: src.trainer.TensorBoardLogger
+    name: ''
+    save_dir: ./
+    version: null
+model: fw57M-tied
+optim:
+  lr: 0.0006
+  num_warmup_steps: 2000
+  optim_kwargs:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    fused: true
+  optim_name: adamw
+  scheduler_kwargs:
+    min_lr_ratio: 0.01
+    num_decay_steps: 4000
+    num_stable_steps: 44000
+  scheduler_name: warmup_stable_decay
+  weight_decay: 0.01
+out_parent_folder: model_train
+pwd: /home/zg258/rds/hpc-work/infotokenization
+resume_from_checkpoint: .checkpoints/last.ckpt
+run_folder: .
+save_initial_checkpoint: true
+seed: 42
+tok_name: bytelevel2
+torch_compile: true
+train_data_path: /home/zg258/rds/hpc-work/infotokenization/data/common-corpus/bytelevel2/train
+trainer:
+  accelerator: gpu
+  deterministic: false
+  devices: 1
+  enable_progress_bar: true
+  fast_dev_run: false
+  gradient_clip_algorithm: norm
+  gradient_clip_val: 1.0
+  limit_val_batches: 500
+  log_every_n_steps: 1
+  max_steps: 50000
+  precision: bf16-true
+  val_check_interval: 1000
+val_data_path: /home/zg258/rds/hpc-work/infotokenization/data/common-corpus/bytelevel2/validation
+```

llm/fw57M-multi-tied/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "eos_token_id": 1,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 24,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 258
+}

llm/fw57M-multi-tied/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

llm/fw57M-multi-tied/hparams.yaml

@@ -0,0 +1,86 @@
+loggers:
+  tensorboard:
+    _target_: src.trainer.TensorBoardLogger
+    save_dir: ./
+    name: ''
+    version: null
+callbacks:
+  lr_monitor:
+    _target_: src.callbacks.lr_monitor.SimpleLearningRateMonitor
+  grad_norm:
+    _target_: src.callbacks.grad_norm.GradNorm
+    norm_type: 2
+    group_separator: /
+    histogram_freq: null
+    check_clipping: false
+    log_weight_distribution: false
+    only_total: true
+  speed_monitor:
+    _target_: src.callbacks.speed_monitor.SpeedMonitor
+  grad_accum:
+    _target_: src.callbacks.gradient_accumulation.GradientAccumulationScheduler
+    scheduling:
+      0: 2
+  model_checkpoint:
+    _target_: src.callbacks.model_checkpoint.ModelCheckpoint
+    dirpath: .checkpoints
+    filename: '{step}'
+    enable_version_counter: false
+    every_n_train_steps: 1000
+    save_top_k: -1
+    save_last: link
+    verbose: true
+    save_initial_checkpoint: true
+out_parent_folder: model_train
+tok_name: bytelevel2
+run_folder: .
+dataset: common-corpus
+pwd: /home/zg258/rds/hpc-work/infotokenization
+train_data_path: /home/zg258/rds/hpc-work/infotokenization/data/common-corpus/bytelevel2/train
+val_data_path: /home/zg258/rds/hpc-work/infotokenization/data/common-corpus/bytelevel2/validation
+model: fw57M-tied
+resume_from_checkpoint: .checkpoints/last.ckpt
+save_initial_checkpoint: true
+seed: 42
+torch_compile: true
+data:
+  batch_size: 64
+  eval_batch_size: 64
+  shuffle: true
+  drop_last: false
+  num_workers: 12
+  pin_memory: true
+  persistent_workers: false
+  prefetch_factor: 2
+  multiprocessing_context: null
+optim:
+  optim_name: adamw
+  lr: 0.0006
+  weight_decay: 0.01
+  optim_kwargs:
+    fused: true
+    eps: 1.0e-08
+    betas:
+    - 0.9
+    - 0.95
+  scheduler_name: warmup_stable_decay
+  num_warmup_steps: 2000
+  scheduler_kwargs:
+    num_stable_steps: 44000
+    num_decay_steps: 4000
+    min_lr_ratio: 0.01
+trainer:
+  accelerator: gpu
+  devices: 1
+  precision: bf16-true
+  deterministic: false
+  log_every_n_steps: 1
+  enable_progress_bar: true
+  fast_dev_run: false
+  gradient_clip_val: 1.0
+  gradient_clip_algorithm: norm
+  val_check_interval: 1000
+  max_steps: 50000
+  limit_val_batches: 500
+evaluation:
+  blimp: false

llm/fw57M-multi-tied/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46e8376f4ccad540d1d57130e2d242b2e1f39f9544d3d4ea4f9b0a16ae187b0
+size 113668624

llm/fw57M-multi-tied/special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llm/fw57M-multi-tied/tokenizer.json

@@ -0,0 +1,315 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|padding|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|padding|>": 0,
+      "<|endoftext|>": 1,
+      "!": 2,
+      "\"": 3,
+      "#": 4,
+      "$": 5,
+      "%": 6,
+      "&": 7,
+      "'": 8,
+      "(": 9,
+      ")": 10,
+      "*": 11,
+      "+": 12,
+      ",": 13,
+      "-": 14,
+      ".": 15,
+      "/": 16,
+      "0": 17,
+      "1": 18,
+      "2": 19,
+      "3": 20,
+      "4": 21,
+      "5": 22,
+      "6": 23,
+      "7": 24,
+      "8": 25,
+      "9": 26,
+      ":": 27,
+      ";": 28,
+      "<": 29,
+      "=": 30,
+      ">": 31,
+      "?": 32,
+      "@": 33,
+      "A": 34,
+      "B": 35,
+      "C": 36,
+      "D": 37,
+      "E": 38,
+      "F": 39,
+      "G": 40,
+      "H": 41,
+      "I": 42,
+      "J": 43,
+      "K": 44,
+      "L": 45,
+      "M": 46,
+      "N": 47,
+      "O": 48,
+      "P": 49,
+      "Q": 50,
+      "R": 51,
+      "S": 52,
+      "T": 53,
+      "U": 54,
+      "V": 55,
+      "W": 56,
+      "X": 57,
+      "Y": 58,
+      "Z": 59,
+      "[": 60,
+      "\\": 61,
+      "]": 62,
+      "^": 63,
+      "_": 64,
+      "`": 65,
+      "a": 66,
+      "b": 67,
+      "c": 68,
+      "d": 69,
+      "e": 70,
+      "f": 71,
+      "g": 72,
+      "h": 73,
+      "i": 74,
+      "j": 75,
+      "k": 76,
+      "l": 77,
+      "m": 78,
+      "n": 79,
+      "o": 80,
+      "p": 81,
+      "q": 82,
+      "r": 83,
+      "s": 84,
+      "t": 85,
+      "u": 86,
+      "v": 87,
+      "w": 88,
+      "x": 89,
+      "y": 90,
+      "z": 91,
+      "{": 92,
+      "|": 93,
+      "}": 94,
+      "~": 95,
+      "¡": 96,
+      "¢": 97,
+      "£": 98,
+      "¤": 99,
+      "¥": 100,
+      "¦": 101,
+      "§": 102,
+      "¨": 103,
+      "©": 104,
+      "ª": 105,
+      "«": 106,
+      "¬": 107,
+      "®": 108,
+      "¯": 109,
+      "°": 110,
+      "±": 111,
+      "²": 112,
+      "³": 113,
+      "´": 114,
+      "µ": 115,
+      "¶": 116,
+      "·": 117,
+      "¸": 118,
+      "¹": 119,
+      "º": 120,
+      "»": 121,
+      "¼": 122,
+      "½": 123,
+      "¾": 124,
+      "¿": 125,
+      "À": 126,
+      "Á": 127,
+      "Â": 128,
+      "Ã": 129,
+      "Ä": 130,
+      "Å": 131,
+      "Æ": 132,
+      "Ç": 133,
+      "È": 134,
+      "É": 135,
+      "Ê": 136,
+      "Ë": 137,
+      "Ì": 138,
+      "Í": 139,
+      "Î": 140,
+      "Ï": 141,
+      "Ð": 142,
+      "Ñ": 143,
+      "Ò": 144,
+      "Ó": 145,
+      "Ô": 146,
+      "Õ": 147,
+      "Ö": 148,
+      "×": 149,
+      "Ø": 150,
+      "Ù": 151,
+      "Ú": 152,
+      "Û": 153,
+      "Ü": 154,
+      "Ý": 155,
+      "Þ": 156,
+      "ß": 157,
+      "à": 158,
+      "á": 159,
+      "â": 160,
+      "ã": 161,
+      "ä": 162,
+      "å": 163,
+      "æ": 164,
+      "ç": 165,
+      "è": 166,
+      "é": 167,
+      "ê": 168,
+      "ë": 169,
+      "ì": 170,
+      "í": 171,
+      "î": 172,
+      "ï": 173,
+      "ð": 174,
+      "ñ": 175,
+      "ò": 176,
+      "ó": 177,
+      "ô": 178,
+      "õ": 179,
+      "ö": 180,
+      "÷": 181,
+      "ø": 182,
+      "ù": 183,
+      "ú": 184,
+      "û": 185,
+      "ü": 186,
+      "ý": 187,
+      "þ": 188,
+      "ÿ": 189,
+      "Ā": 190,
+      "ā": 191,
+      "Ă": 192,
+      "ă": 193,
+      "Ą": 194,
+      "ą": 195,
+      "Ć": 196,
+      "ć": 197,
+      "Ĉ": 198,
+      "ĉ": 199,
+      "Ċ": 200,
+      "ċ": 201,
+      "Č": 202,
+      "č": 203,
+      "Ď": 204,
+      "ď": 205,
+      "Đ": 206,
+      "đ": 207,
+      "Ē": 208,
+      "ē": 209,
+      "Ĕ": 210,
+      "ĕ": 211,
+      "Ė": 212,
+      "ė": 213,
+      "Ę": 214,
+      "ę": 215,
+      "Ě": 216,
+      "ě": 217,
+      "Ĝ": 218,
+      "ĝ": 219,
+      "Ğ": 220,
+      "ğ": 221,
+      "Ġ": 222,
+      "ġ": 223,
+      "Ģ": 224,
+      "ģ": 225,
+      "Ĥ": 226,
+      "ĥ": 227,
+      "Ħ": 228,
+      "��": 229,
+      "Ĩ": 230,
+      "ĩ": 231,
+      "Ī": 232,
+      "ī": 233,
+      "Ĭ": 234,
+      "ĭ": 235,
+      "Į": 236,
+      "į": 237,
+      "İ": 238,
+      "ı": 239,
+      "IJ": 240,
+      "ij": 241,
+      "Ĵ": 242,
+      "ĵ": 243,
+      "Ķ": 244,
+      "ķ": 245,
+      "ĸ": 246,
+      "Ĺ": 247,
+      "ĺ": 248,
+      "Ļ": 249,
+      "ļ": 250,
+      "Ľ": 251,
+      "ľ": 252,
+      "Ŀ": 253,
+      "ŀ": 254,
+      "Ł": 255,
+      "ł": 256,
+      "Ń": 257
+    },
+    "merges": []
+  }
+}

llm/fw57M-multi-tied/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}