Loading checkpoint shards:   0%|          | 0/3 [00:00<?, ?it/s]/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/bitsandbytes/backends/cuda/ops.py:213: FutureWarning: _check_is_size will be removed in a future PyTorch release along with guard_size_oblivious.     Use _check(i >= 0) instead.
  torch._check_is_size(blocksize)

Loading checkpoint shards:  33%|███▎      | 1/3 [00:02<00:04,  2.21s/it]
Loading checkpoint shards:  67%|██████▋   | 2/3 [00:04<00:02,  2.17s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:06<00:00,  1.99s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:06<00:00,  2.04s/it]
/home/henry/Documents/PythonProjects/variable-reap/.venv/lib/python3.12/site-packages/bitsandbytes/backends/cuda/ops.py:468: FutureWarning: _check_is_size will be removed in a future PyTorch release along with guard_size_oblivious.     Use _check(i >= 0) instead.
  torch._check_is_size(blocksize)
shard shard_00000.pt: cumulative 73031 tokens
shard shard_00001.pt: cumulative 142706 tokens
shard shard_00002.pt: cumulative 221592 tokens
{
  "quant": "nf4",
  "shards": 3,
  "tokens": 221592,
  "kl_mean_nats": 0.03224208885256773,
  "kl_median_nats": 0.00010718336125137284,
  "kl_p95_nats": 0.15037551522254944,
  "kl_max_nats": 14.360836029052734,
  "top128_jaccard_mean": 0.7352590498594933,
  "top1_agreement": 0.9612215242427524,
  "captured_mass_bf16": 0.9997188871511677,
  "captured_mass_quant_at_bf16_support": 0.9996136682180469
}