niklastr commited on
Commit
ea0aa89
Β·
verified Β·
1 Parent(s): 8d10609

Normalize DIPPER checkpoint layout

Browse files
Files changed (40) hide show
  1. checkpoints/{dipper_30m/core/d_scaling/bin1024/5n/dipper_30m_core_bin1024_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/1024_d_scaling/05n/dipper_0_030B_core_1024_d_scaling_5n_step_984.ckpt} +0 -0
  2. checkpoints/{dipper_30m/core/d_scaling/bin1024/10n/dipper_30m_core_bin1024_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/1024_d_scaling/10n/dipper_0_030B_core_1024_d_scaling_10n_step_1968.ckpt} +0 -0
  3. checkpoints/{dipper_30m/core/d_scaling/bin1024/20n/dipper_30m_core_bin1024_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/1024_d_scaling/20n/dipper_0_030B_core_1024_d_scaling_20n_step_3935.ckpt} +0 -0
  4. checkpoints/{dipper_30m/core/d_scaling/bin1024/40n/dipper_30m_core_bin1024_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/1024_d_scaling/40n/dipper_0_030B_core_1024_d_scaling_40n_step_7870.ckpt} +0 -0
  5. checkpoints/{dipper_30m/core/d_scaling/bin1024/80n/dipper_30m_core_bin1024_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/1024_d_scaling/80n/dipper_0_030B_core_1024_d_scaling_80n_step_15738.ckpt} +0 -0
  6. checkpoints/{dipper_30m/core/ws_scaling/bin1024/dipper_30m_core_bin1024_ws_scaling_step_31476.ckpt β†’ 0_030B/core/1024_ws_scaling/dipper_0_030B_core_1024_ws_scaling_step_31476.ckpt} +0 -0
  7. checkpoints/{dipper_30m/core/d_scaling/bin256/5n/dipper_30m_core_bin256_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/256_d_scaling/05n/dipper_0_030B_core_256_d_scaling_5n_step_984.ckpt} +0 -0
  8. checkpoints/{dipper_30m/core/d_scaling/bin256/10n/dipper_30m_core_bin256_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/256_d_scaling/10n/dipper_0_030B_core_256_d_scaling_10n_step_1968.ckpt} +0 -0
  9. checkpoints/{dipper_30m/core/d_scaling/bin256/20n/dipper_30m_core_bin256_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/256_d_scaling/20n/dipper_0_030B_core_256_d_scaling_20n_step_3935.ckpt} +0 -0
  10. checkpoints/{dipper_30m/core/d_scaling/bin256/40n/dipper_30m_core_bin256_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/256_d_scaling/40n/dipper_0_030B_core_256_d_scaling_40n_step_7870.ckpt} +0 -0
  11. checkpoints/{dipper_30m/core/d_scaling/bin256/80n/dipper_30m_core_bin256_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/256_d_scaling/80n/dipper_0_030B_core_256_d_scaling_80n_step_15738.ckpt} +0 -0
  12. checkpoints/{dipper_30m/core/ws_scaling/bin256/dipper_30m_core_bin256_ws_scaling_step_31476.ckpt β†’ 0_030B/core/256_ws_scaling/dipper_0_030B_core_256_ws_scaling_step_31476.ckpt} +0 -0
  13. checkpoints/{dipper_30m/core/d_scaling/bin4096/5n/dipper_30m_core_bin4096_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/4096_d_scaling/05n/dipper_0_030B_core_4096_d_scaling_5n_step_984.ckpt} +0 -0
  14. checkpoints/{dipper_30m/core/d_scaling/bin4096/10n/dipper_30m_core_bin4096_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/4096_d_scaling/10n/dipper_0_030B_core_4096_d_scaling_10n_step_1968.ckpt} +0 -0
  15. checkpoints/{dipper_30m/core/d_scaling/bin4096/20n/dipper_30m_core_bin4096_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/4096_d_scaling/20n/dipper_0_030B_core_4096_d_scaling_20n_step_3935.ckpt} +0 -0
  16. checkpoints/{dipper_30m/core/d_scaling/bin4096/40n/dipper_30m_core_bin4096_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/4096_d_scaling/40n/dipper_0_030B_core_4096_d_scaling_40n_step_7870.ckpt} +0 -0
  17. checkpoints/{dipper_30m/core/d_scaling/bin4096/80n/dipper_30m_core_bin4096_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/4096_d_scaling/80n/dipper_0_030B_core_4096_d_scaling_80n_step_15738.ckpt} +0 -0
  18. checkpoints/{dipper_30m/core/ws_scaling/bin4096/dipper_30m_core_bin4096_ws_scaling_step_31476.ckpt β†’ 0_030B/core/4096_ws_scaling/dipper_0_030B_core_4096_ws_scaling_step_31476.ckpt} +0 -0
  19. checkpoints/{dipper_30m/core/d_scaling/bin65537/5n/dipper_30m_core_bin65537_d_scaling_5n_step_2128.ckpt β†’ 0_030B/core/65537_d_scaling/05n/dipper_0_030B_core_65537_d_scaling_5n_step_2128.ckpt} +0 -0
  20. checkpoints/{dipper_30m/core/d_scaling/bin65537/10n/dipper_30m_core_bin65537_d_scaling_10n_step_4256.ckpt β†’ 0_030B/core/65537_d_scaling/10n/dipper_0_030B_core_65537_d_scaling_10n_step_4256.ckpt} +0 -0
  21. checkpoints/{dipper_30m/core/d_scaling/bin65537/20n/dipper_30m_core_bin65537_d_scaling_20n_step_8510.ckpt β†’ 0_030B/core/65537_d_scaling/20n/dipper_0_030B_core_65537_d_scaling_20n_step_8510.ckpt} +0 -0
  22. checkpoints/{dipper_30m/core/d_scaling/bin65537/40n/dipper_30m_core_bin65537_d_scaling_40n_step_17019.ckpt β†’ 0_030B/core/65537_d_scaling/40n/dipper_0_030B_core_65537_d_scaling_40n_step_17019.ckpt} +0 -0
  23. checkpoints/{dipper_30m/core/d_scaling/bin65537/80n/dipper_30m_core_bin65537_d_scaling_80n_step_34037.ckpt β†’ 0_030B/core/65537_d_scaling/80n/dipper_0_030B_core_65537_d_scaling_80n_step_34037.ckpt} +0 -0
  24. checkpoints/{dipper_30m/core/ws_scaling/bin65537/dipper_30m_core_bin65537_ws_scaling_step_68073.ckpt β†’ 0_030B/core/65537_ws_scaling/dipper_0_030B_core_65537_ws_scaling_step_68073.ckpt} +0 -0
  25. checkpoints/{dipper_49m/core/d_scaling/bin1024/5n/dipper_49m_core_bin1024_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/1024_d_scaling/05n/dipper_0_049B_core_1024_d_scaling_5n_step_1847.ckpt} +0 -0
  26. checkpoints/{dipper_49m/core/d_scaling/bin1024/10n/dipper_49m_core_bin1024_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/1024_d_scaling/10n/dipper_0_049B_core_1024_d_scaling_10n_step_3694.ckpt} +0 -0
  27. checkpoints/{dipper_49m/core/d_scaling/bin1024/20n/dipper_49m_core_bin1024_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/1024_d_scaling/20n/dipper_0_049B_core_1024_d_scaling_20n_step_7386.ckpt} +0 -0
  28. checkpoints/{dipper_49m/core/d_scaling/bin1024/40n/dipper_49m_core_bin1024_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/1024_d_scaling/40n/dipper_0_049B_core_1024_d_scaling_40n_step_14771.ckpt} +0 -0
  29. checkpoints/{dipper_49m/core/d_scaling/bin1024/80n/dipper_49m_core_bin1024_d_scaling_80n_step_29541.ckpt β†’ 0_049B/core/1024_d_scaling/80n/dipper_0_049B_core_1024_d_scaling_80n_step_29541.ckpt} +0 -0
  30. checkpoints/{dipper_49m/core/d_scaling/bin256/5n/dipper_49m_core_bin256_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/256_d_scaling/05n/dipper_0_049B_core_256_d_scaling_5n_step_1847.ckpt} +0 -0
  31. checkpoints/{dipper_49m/core/d_scaling/bin256/10n/dipper_49m_core_bin256_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/256_d_scaling/10n/dipper_0_049B_core_256_d_scaling_10n_step_3694.ckpt} +0 -0
  32. checkpoints/{dipper_49m/core/d_scaling/bin256/20n/dipper_49m_core_bin256_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/256_d_scaling/20n/dipper_0_049B_core_256_d_scaling_20n_step_7386.ckpt} +0 -0
  33. checkpoints/{dipper_49m/core/d_scaling/bin256/40n/dipper_49m_core_bin256_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/256_d_scaling/40n/dipper_0_049B_core_256_d_scaling_40n_step_14771.ckpt} +0 -0
  34. checkpoints/{dipper_49m/core/d_scaling/bin256/80n/dipper_49m_core_bin256_d_scaling_80n_step_29541.ckpt β†’ 0_049B/core/256_d_scaling/80n/dipper_0_049B_core_256_d_scaling_80n_step_29541.ckpt} +0 -0
  35. checkpoints/{dipper_49m/core/d_scaling/bin4096/5n/dipper_49m_core_bin4096_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/4096_d_scaling/05n/dipper_0_049B_core_4096_d_scaling_5n_step_1847.ckpt} +0 -0
  36. checkpoints/{dipper_49m/core/d_scaling/bin4096/10n/dipper_49m_core_bin4096_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/4096_d_scaling/10n/dipper_0_049B_core_4096_d_scaling_10n_step_3694.ckpt} +0 -0
  37. checkpoints/{dipper_49m/core/d_scaling/bin4096/20n/dipper_49m_core_bin4096_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/4096_d_scaling/20n/dipper_0_049B_core_4096_d_scaling_20n_step_7386.ckpt} +0 -0
  38. checkpoints/{dipper_49m/core/d_scaling/bin4096/40n/dipper_49m_core_bin4096_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/4096_d_scaling/40n/dipper_0_049B_core_4096_d_scaling_40n_step_14771.ckpt} +0 -0
  39. checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_320000.ckpt β†’ 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_320000.ckpt} +0 -0
  40. checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_80000.ckpt β†’ 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_80000.ckpt} +0 -0
checkpoints/{dipper_30m/core/d_scaling/bin1024/5n/dipper_30m_core_bin1024_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/1024_d_scaling/05n/dipper_0_030B_core_1024_d_scaling_5n_step_984.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin1024/10n/dipper_30m_core_bin1024_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/1024_d_scaling/10n/dipper_0_030B_core_1024_d_scaling_10n_step_1968.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin1024/20n/dipper_30m_core_bin1024_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/1024_d_scaling/20n/dipper_0_030B_core_1024_d_scaling_20n_step_3935.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin1024/40n/dipper_30m_core_bin1024_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/1024_d_scaling/40n/dipper_0_030B_core_1024_d_scaling_40n_step_7870.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin1024/80n/dipper_30m_core_bin1024_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/1024_d_scaling/80n/dipper_0_030B_core_1024_d_scaling_80n_step_15738.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/ws_scaling/bin1024/dipper_30m_core_bin1024_ws_scaling_step_31476.ckpt β†’ 0_030B/core/1024_ws_scaling/dipper_0_030B_core_1024_ws_scaling_step_31476.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin256/5n/dipper_30m_core_bin256_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/256_d_scaling/05n/dipper_0_030B_core_256_d_scaling_5n_step_984.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin256/10n/dipper_30m_core_bin256_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/256_d_scaling/10n/dipper_0_030B_core_256_d_scaling_10n_step_1968.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin256/20n/dipper_30m_core_bin256_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/256_d_scaling/20n/dipper_0_030B_core_256_d_scaling_20n_step_3935.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin256/40n/dipper_30m_core_bin256_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/256_d_scaling/40n/dipper_0_030B_core_256_d_scaling_40n_step_7870.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin256/80n/dipper_30m_core_bin256_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/256_d_scaling/80n/dipper_0_030B_core_256_d_scaling_80n_step_15738.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/ws_scaling/bin256/dipper_30m_core_bin256_ws_scaling_step_31476.ckpt β†’ 0_030B/core/256_ws_scaling/dipper_0_030B_core_256_ws_scaling_step_31476.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin4096/5n/dipper_30m_core_bin4096_d_scaling_5n_step_984.ckpt β†’ 0_030B/core/4096_d_scaling/05n/dipper_0_030B_core_4096_d_scaling_5n_step_984.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin4096/10n/dipper_30m_core_bin4096_d_scaling_10n_step_1968.ckpt β†’ 0_030B/core/4096_d_scaling/10n/dipper_0_030B_core_4096_d_scaling_10n_step_1968.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin4096/20n/dipper_30m_core_bin4096_d_scaling_20n_step_3935.ckpt β†’ 0_030B/core/4096_d_scaling/20n/dipper_0_030B_core_4096_d_scaling_20n_step_3935.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin4096/40n/dipper_30m_core_bin4096_d_scaling_40n_step_7870.ckpt β†’ 0_030B/core/4096_d_scaling/40n/dipper_0_030B_core_4096_d_scaling_40n_step_7870.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin4096/80n/dipper_30m_core_bin4096_d_scaling_80n_step_15738.ckpt β†’ 0_030B/core/4096_d_scaling/80n/dipper_0_030B_core_4096_d_scaling_80n_step_15738.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/ws_scaling/bin4096/dipper_30m_core_bin4096_ws_scaling_step_31476.ckpt β†’ 0_030B/core/4096_ws_scaling/dipper_0_030B_core_4096_ws_scaling_step_31476.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin65537/5n/dipper_30m_core_bin65537_d_scaling_5n_step_2128.ckpt β†’ 0_030B/core/65537_d_scaling/05n/dipper_0_030B_core_65537_d_scaling_5n_step_2128.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin65537/10n/dipper_30m_core_bin65537_d_scaling_10n_step_4256.ckpt β†’ 0_030B/core/65537_d_scaling/10n/dipper_0_030B_core_65537_d_scaling_10n_step_4256.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin65537/20n/dipper_30m_core_bin65537_d_scaling_20n_step_8510.ckpt β†’ 0_030B/core/65537_d_scaling/20n/dipper_0_030B_core_65537_d_scaling_20n_step_8510.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin65537/40n/dipper_30m_core_bin65537_d_scaling_40n_step_17019.ckpt β†’ 0_030B/core/65537_d_scaling/40n/dipper_0_030B_core_65537_d_scaling_40n_step_17019.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/d_scaling/bin65537/80n/dipper_30m_core_bin65537_d_scaling_80n_step_34037.ckpt β†’ 0_030B/core/65537_d_scaling/80n/dipper_0_030B_core_65537_d_scaling_80n_step_34037.ckpt} RENAMED
File without changes
checkpoints/{dipper_30m/core/ws_scaling/bin65537/dipper_30m_core_bin65537_ws_scaling_step_68073.ckpt β†’ 0_030B/core/65537_ws_scaling/dipper_0_030B_core_65537_ws_scaling_step_68073.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin1024/5n/dipper_49m_core_bin1024_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/1024_d_scaling/05n/dipper_0_049B_core_1024_d_scaling_5n_step_1847.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin1024/10n/dipper_49m_core_bin1024_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/1024_d_scaling/10n/dipper_0_049B_core_1024_d_scaling_10n_step_3694.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin1024/20n/dipper_49m_core_bin1024_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/1024_d_scaling/20n/dipper_0_049B_core_1024_d_scaling_20n_step_7386.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin1024/40n/dipper_49m_core_bin1024_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/1024_d_scaling/40n/dipper_0_049B_core_1024_d_scaling_40n_step_14771.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin1024/80n/dipper_49m_core_bin1024_d_scaling_80n_step_29541.ckpt β†’ 0_049B/core/1024_d_scaling/80n/dipper_0_049B_core_1024_d_scaling_80n_step_29541.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin256/5n/dipper_49m_core_bin256_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/256_d_scaling/05n/dipper_0_049B_core_256_d_scaling_5n_step_1847.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin256/10n/dipper_49m_core_bin256_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/256_d_scaling/10n/dipper_0_049B_core_256_d_scaling_10n_step_3694.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin256/20n/dipper_49m_core_bin256_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/256_d_scaling/20n/dipper_0_049B_core_256_d_scaling_20n_step_7386.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin256/40n/dipper_49m_core_bin256_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/256_d_scaling/40n/dipper_0_049B_core_256_d_scaling_40n_step_14771.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin256/80n/dipper_49m_core_bin256_d_scaling_80n_step_29541.ckpt β†’ 0_049B/core/256_d_scaling/80n/dipper_0_049B_core_256_d_scaling_80n_step_29541.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin4096/5n/dipper_49m_core_bin4096_d_scaling_5n_step_1847.ckpt β†’ 0_049B/core/4096_d_scaling/05n/dipper_0_049B_core_4096_d_scaling_5n_step_1847.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin4096/10n/dipper_49m_core_bin4096_d_scaling_10n_step_3694.ckpt β†’ 0_049B/core/4096_d_scaling/10n/dipper_0_049B_core_4096_d_scaling_10n_step_3694.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin4096/20n/dipper_49m_core_bin4096_d_scaling_20n_step_7386.ckpt β†’ 0_049B/core/4096_d_scaling/20n/dipper_0_049B_core_4096_d_scaling_20n_step_7386.ckpt} RENAMED
File without changes
checkpoints/{dipper_49m/core/d_scaling/bin4096/40n/dipper_49m_core_bin4096_d_scaling_40n_step_14771.ckpt β†’ 0_049B/core/4096_d_scaling/40n/dipper_0_049B_core_4096_d_scaling_40n_step_14771.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_320000.ckpt β†’ 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_320000.ckpt} RENAMED
File without changes
checkpoints/{dipper_1_7b/scaling_rescue/qwen3_1_7b_ws_scaling_rescue_step_80000.ckpt β†’ 1_7B/qwen/ws_scaling_rescue/dipper_1_7B_qwen_ws_scaling_rescue_step_80000.ckpt} RENAMED
File without changes