explcre commited on
Commit
0ec113e
·
verified ·
1 Parent(s): 0be594c

Upload exp_phase8_through_mdlm_grpo_20260501_030216/log.jsonl with huggingface_hub

Browse files
exp_phase8_through_mdlm_grpo_20260501_030216/log.jsonl ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"step": 10, "loss": -0.0033434927463531494, "reward_mean": -0.025197006296366453, "elapsed_s": 551.1385145187378}
2
+ {"step": 20, "loss": 0.0014834851026535034, "reward_mean": -0.039679881650954485, "elapsed_s": 1104.538061618805}
3
+ {"step": 30, "loss": 0.0025977641344070435, "reward_mean": 0.15113150887191296, "elapsed_s": 1648.0217189788818}
4
+ {"step": 40, "loss": -0.001446068286895752, "reward_mean": 0.2972179651260376, "elapsed_s": 2193.1856529712677}
5
+ {"step": 50, "loss": -0.005890518426895142, "reward_mean": 0.3023329973220825, "elapsed_s": 2736.207221508026}
6
+ {"step": 60, "loss": 0.002140641212463379, "reward_mean": -0.07109672948718071, "elapsed_s": 3282.088091611862}
7
+ {"step": 70, "loss": -0.0005152970552444458, "reward_mean": -0.0013408567756414413, "elapsed_s": 3831.1661438941956}
8
+ {"step": 80, "loss": -0.002256423234939575, "reward_mean": 0.20722302421927452, "elapsed_s": 4376.643876314163}
9
+ {"step": 90, "loss": 0.0037899017333984375, "reward_mean": -0.06725826300680637, "elapsed_s": 4922.8688843250275}
10
+ {"step": 100, "loss": 0.0033878684043884277, "reward_mean": 0.4047212302684784, "elapsed_s": 5468.345854759216}
11
+ {"step": 110, "loss": -0.008908390998840332, "reward_mean": 0.17321358621120453, "elapsed_s": 6052.585865736008}
12
+ {"step": 120, "loss": 2.244114875793457e-05, "reward_mean": -0.08034981787204742, "elapsed_s": 6604.434944629669}
13
+ {"step": 130, "loss": -0.00164090096950531, "reward_mean": 0.0832110345363617, "elapsed_s": 7151.521459102631}
14
+ {"step": 140, "loss": 0.007028907537460327, "reward_mean": 0.19005918875336647, "elapsed_s": 7699.615131139755}
15
+ {"step": 150, "loss": -0.008422262966632843, "reward_mean": -0.03291196748614311, "elapsed_s": 8250.667712926865}
16
+ {"step": 160, "loss": 0.00462833046913147, "reward_mean": 0.5951388776302338, "elapsed_s": 8798.138192176819}
17
+ {"step": 170, "loss": 0.003863692283630371, "reward_mean": -0.03848662041127682, "elapsed_s": 9351.217124462128}
18
+ {"step": 180, "loss": 0.0022505223751068115, "reward_mean": 0.1965647777542472, "elapsed_s": 9898.147172927856}
19
+ {"step": 190, "loss": -0.00588613748550415, "reward_mean": -0.09092697501182556, "elapsed_s": 10444.57516503334}
20
+ {"step": 200, "loss": 0.0032180994749069214, "reward_mean": 0.005310806562192738, "elapsed_s": 10990.174492120743}
21
+ {"step": 210, "loss": -0.006533637642860413, "reward_mean": 0.34168016351759434, "elapsed_s": 11579.149308919907}
22
+ {"step": 220, "loss": 0.014650106430053711, "reward_mean": 0.3344642361626029, "elapsed_s": 12122.835254192352}
23
+ {"step": 230, "loss": -0.0021774619817733765, "reward_mean": -0.053281700471416116, "elapsed_s": 12664.70829629898}
24
+ {"step": 240, "loss": -0.003737032413482666, "reward_mean": 0.3732021749019623, "elapsed_s": 13206.25151348114}
25
+ {"step": 250, "loss": 0.0016130805015563965, "reward_mean": -0.012585937976837158, "elapsed_s": 13753.155404806137}
26
+ {"step": 260, "loss": 0.009142272174358368, "reward_mean": 0.07961295545101166, "elapsed_s": 14296.879023075104}
27
+ {"step": 270, "loss": -0.004996299743652344, "reward_mean": 0.4548053741455078, "elapsed_s": 14839.16926574707}
28
+ {"step": 280, "loss": 0.010091006755828857, "reward_mean": 0.4408704172819853, "elapsed_s": 15377.998705387115}
29
+ {"step": 290, "loss": -0.00621582567691803, "reward_mean": -0.11729404330253601, "elapsed_s": 15918.277513504028}
30
+ {"step": 300, "loss": -0.0025790631771087646, "reward_mean": 0.026717081665992737, "elapsed_s": 16462.793520212173}