Preserve complete v5.5 scaling checkpoint code-heavy__32m__10tpp__regex
Browse files- refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/complete.json +18 -0
- refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/rl.pt +3 -0
- refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/sft.pt +3 -0
- refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/terminal-sft.json +7 -0
- refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/validated.json +29 -0
refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/complete.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sft_tokens": 2097152,
|
| 3 |
+
"sft_budget": 2097152,
|
| 4 |
+
"rl_rollouts": 65536,
|
| 5 |
+
"rl_budget": 65536,
|
| 6 |
+
"terminal_sft_hash": "83b840bc836924e5503f2dffeba22b218e7b14ae4628f915171e7a9450d4f881",
|
| 7 |
+
"final_rl_hash": "4db7282161e6260c455231bfb10fa34bb50efc8d0d511ea60a895ae7edb4b6c1",
|
| 8 |
+
"difficulty": {
|
| 9 |
+
"missing": 2,
|
| 10 |
+
"bundle": 1,
|
| 11 |
+
"band": -1,
|
| 12 |
+
"candidates": 0
|
| 13 |
+
},
|
| 14 |
+
"sft_seconds": 224.37167515046895,
|
| 15 |
+
"rl_seconds": 1328.3600416705012,
|
| 16 |
+
"hardware": "NVIDIA GeForce RTX 3090",
|
| 17 |
+
"no_checkpoint_selection": true
|
| 18 |
+
}
|
refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/rl.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78160980f68eaae5ccce94c8707f1168d3ef6e29461e51bc5bbaf36f09714b0d
|
| 3 |
+
size 128309045
|
refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/sft.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c4af045ed782ac32ba69c849a4b6d37c3e44ec2ca5ef41fdfaeea1526ef7fc9
|
| 3 |
+
size 128309181
|
refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/terminal-sft.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokens": 2097152,
|
| 3 |
+
"budget": 2097152,
|
| 4 |
+
"weights_sha256": "83b840bc836924e5503f2dffeba22b218e7b14ae4628f915171e7a9450d4f881",
|
| 5 |
+
"seconds": 224.37167515046895,
|
| 6 |
+
"step": 1789
|
| 7 |
+
}
|
refined-tasks-v5.5-scaling/runs/code-heavy__32m__10tpp__regex/validated.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"case": "code-heavy__32m__10tpp__regex",
|
| 3 |
+
"mix": "code-heavy",
|
| 4 |
+
"model": "32m",
|
| 5 |
+
"tpp": 10,
|
| 6 |
+
"source": "/nlp/scr/dhei/tiny-rl/experiments/refined-tasks-v5.5-scaling/source/8a8524d8e178b23e",
|
| 7 |
+
"pretrained_completion_verified": true,
|
| 8 |
+
"model_sha256": "7b72786d43a62f32d781ff884881d955a51df5f73e6562ce96442659d76b5247",
|
| 9 |
+
"complete": {
|
| 10 |
+
"sft_tokens": 2097152,
|
| 11 |
+
"sft_budget": 2097152,
|
| 12 |
+
"rl_rollouts": 65536,
|
| 13 |
+
"rl_budget": 65536,
|
| 14 |
+
"terminal_sft_hash": "83b840bc836924e5503f2dffeba22b218e7b14ae4628f915171e7a9450d4f881",
|
| 15 |
+
"final_rl_hash": "4db7282161e6260c455231bfb10fa34bb50efc8d0d511ea60a895ae7edb4b6c1",
|
| 16 |
+
"difficulty": {
|
| 17 |
+
"missing": 2,
|
| 18 |
+
"bundle": 1,
|
| 19 |
+
"band": -1,
|
| 20 |
+
"candidates": 0
|
| 21 |
+
},
|
| 22 |
+
"sft_seconds": 224.37167515046895,
|
| 23 |
+
"rl_seconds": 1328.3600416705012,
|
| 24 |
+
"hardware": "NVIDIA GeForce RTX 3090",
|
| 25 |
+
"no_checkpoint_selection": true
|
| 26 |
+
},
|
| 27 |
+
"smoke": false,
|
| 28 |
+
"raw_initialization_verified": true
|
| 29 |
+
}
|