nanochat-cache / report /midtraining.md
ttj's picture
Add files using upload-large-folder tool
85a524c verified

Midtraining

timestamp: 2025-11-03 09:23:03

  • run: fal-mid
  • device_type:
  • dtype: bfloat16
  • num_iterations: -1
  • max_seq_len: 2048
  • device_batch_size: 32
  • unembedding_lr: 0.0040
  • embedding_lr: 0.2000
  • matrix_lr: 0.0200
  • init_lr_frac: 1.0000
  • weight_decay: 0.0000
  • eval_every: 150
  • eval_tokens: 10,485,760
  • total_batch_size: 524,288
  • dry_run: 0
  • Number of iterations: 809
  • DDP world size: 8
  • Minimum validation bpb: 0.3953