Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -19,5 +19,4 @@ It documents a V5 run on the official FineWeb sp1024 path using a longer sequenc
- `submission.json`
- `results.tsv`
- `train_gpt.py`
- `train.log`
- `final_model.int8.ptz`
Original file line number Diff line number Diff line change
@@ -1,7 +1,2 @@
run_idtrackgputokenizertrain_seq_leniterationswarmup_stepsval_loss_exactval_bpb_exactbytes_total
v5_sp1024_top10_anon-record-16mb1xH100sp102440966000302.050297521.2143016815841388
EOFls /workspace/parameter-golf-v-5/records/track_non_record_16mb/2026-04-17_V5_SP1024_SEQ4096_1xH100_121430168
cd /workspace/parameter-golf-v-5
git add .
git commit -m "Add V5 non-record submission (1.2143 bpb)"
git push
run_id track gpu tokenizer train_seq_len iterations warmup_steps val_loss_exact val_bpb_exact bytes_total
v5_sp1024_top10_a non-record-16mb 1xH100 sp1024 4096 6000 30 2.05029752 1.21430168 15841388
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,3 @@
"bytes_code": null,
"gpu": "1xH100"
}
EOFcat > /workspace/parameter-golf-v-5/records/track_non_record_16mb/2026-04-17_V5_SP1024_SEQ4096_1xH100_121430168/results.tsv <<'EOF'
run_id track gpu tokenizer train_seq_len iterations warmup_steps val_loss_exact val_bpb_exact bytes_total
v5_sp1024_top10_a non-record-16mb 1xH100 sp1024 4096 6000 30 2.05029752 1.21430168 15841388
Loading