moncefem commited on
Commit
9a6c537
·
1 Parent(s): 09dc9c5

autopush: h200_run checkpoint @ 2026-07-25T13:52:07Z

Browse files
.gitattributes CHANGED
@@ -3,3 +3,4 @@
3
  data/docs/*.jsonl filter=lfs diff=lfs merge=lfs -text
4
  data/qna/*.jsonl filter=lfs diff=lfs merge=lfs -text
5
  data/commitpack/*.jsonl filter=lfs diff=lfs merge=lfs -text
 
 
3
  data/docs/*.jsonl filter=lfs diff=lfs merge=lfs -text
4
  data/qna/*.jsonl filter=lfs diff=lfs merge=lfs -text
5
  data/commitpack/*.jsonl filter=lfs diff=lfs merge=lfs -text
6
+ runs/h200_run/*.pt filter=lfs diff=lfs merge=lfs -text
runs/h200_run/head.best.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0fc72c956a80af85c67f321d47562d47af1ca3c251181aa131bcbf4c9434b9
3
+ size 3001716868
runs/h200_run/metrics.jsonl ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {"step": 400, "epoch": 0, "end_of_epoch": false, "eval_loss": 5.608470782055079, "suites": {"cr_val": {"eval_loss": 5.608470782055079, "n_docs": 60, "n_tokens": 13481, "baseline_loss": 7.980483633289969, "delta_vs_baseline": -2.3720128512348904}, "cr_test": {"eval_loss": 5.570762737579796, "n_docs": 60, "n_tokens": 14254, "baseline_loss": 8.065613950872816, "delta_vs_baseline": -2.4948512132930203}, "_diag": {"adapter_cosine": 0.04115094244480133, "adapter_delta_fro": 3.36551570892334}}}
2
+ {"step": 800, "epoch": 0, "end_of_epoch": false, "eval_loss": 3.1739312672011977, "suites": {"cr_val": {"eval_loss": 3.1739312672011977, "n_docs": 60, "n_tokens": 13481, "baseline_loss": 7.980483633289969, "delta_vs_baseline": -4.806552366088772}, "cr_test": {"eval_loss": 3.1755788231257287, "n_docs": 60, "n_tokens": 14254, "baseline_loss": 8.065613950872816, "delta_vs_baseline": -4.890035127747087}, "_diag": {"adapter_cosine": 0.2494429349899292, "adapter_delta_fro": 3.353330612182617}}}
3
+ {"step": 1200, "epoch": 0, "end_of_epoch": false, "eval_loss": 2.8912936294744687, "suites": {"cr_val": {"eval_loss": 2.8912936294744687, "n_docs": 60, "n_tokens": 13481, "baseline_loss": 7.980483633289969, "delta_vs_baseline": -5.089190003815501}, "cr_test": {"eval_loss": 2.8929684969692087, "n_docs": 60, "n_tokens": 14254, "baseline_loss": 8.065613950872816, "delta_vs_baseline": -5.172645453903607}, "_diag": {"adapter_cosine": 0.34518808126449585, "adapter_delta_fro": 3.3041810989379883}}}
4
+ {"step": 1600, "epoch": 0, "end_of_epoch": false, "eval_loss": 2.7959226398243056, "suites": {"cr_val": {"eval_loss": 2.7959226398243056, "n_docs": 60, "n_tokens": 13481, "baseline_loss": 7.980483633289969, "delta_vs_baseline": -5.184560993465664}, "cr_test": {"eval_loss": 2.7954453304169538, "n_docs": 60, "n_tokens": 14254, "baseline_loss": 8.065613950872816, "delta_vs_baseline": -5.270168620455863}, "_diag": {"adapter_cosine": 0.36626213788986206, "adapter_delta_fro": 3.252228260040283}}}