yamalies/experiment-v2-data / data /sources_eval.json
yamalies's picture
download
raw
1.42 kB
{
"version": 2,
"name": "training_v2-teutonic-II-110B-synced",
"description": "Synced eval_weight from remote manifest (updated=None policy=None). train weight from train_init_weights.json; eval from remote manifest (train_only keep eval_weight=0). See docs/HOW_INITIAL_RATIO_WAS_CHOSEN.md.",
"seq_len": 2048,
"dtype": "uint32",
"train_seed": 86,
"eval_seed": 1234,
"eval_total": 2000,
"default_train_sequences": 5000000,
"train_init": {
"mode": "train_init",
"file": "train_init_weights.json"
},
"remote_meta": {
"updated": "2026-08-24T08:54:23.452204Z",
"source_mix_policy": "finewebedu",
"sequence_length": 2048,
"generated_at": "2026-08-24T08:54:23.452204Z",
"config_version": "7f8db63fd8812e5f6389e9ff8d2c07799c235b5abc0b2fabc783f354487f96f3",
"chain": {
"competition": "Teutonic-II-110B",
"generation": "teutonic-II-110B-hf-8f971f030f5d801f812540007b396058f69cc08a",
"name": "Teutonic-II-110B",
"netuid": 3
}
},
"remote_name_map": {
"finewebedu": "finewebedu"
},
"sources": [
{
"name": "finewebedu",
"weight": 1.0,
"eval_weight": 1.0,
"num_shards": 200,
"eval_num_shards": 80,
"bucket": "stevendev/corpus",
"manifest": "dataset/finewebedu/manifest.json",
"r2_manifest_url": "https://pub-d923bc4e8fcb45f6b703bc750bcf8aa6.r2.dev/finewebedu/manifest.json"
}
]
}

Xet Storage Details

Size:
1.42 kB
·
Xet hash:
6c24ddcc57e08a54e0d3ebf4a34275ac9e6728bdf62c24a6daae8c60173883d1

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.