Upload exp_phase8_through_mdlm_dapo_20260501_030216/log.jsonl with huggingface_hub
Browse files
exp_phase8_through_mdlm_dapo_20260501_030216/log.jsonl
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"step": 10, "loss": -0.0025562942028045654, "reward_mean": -0.0414877962321043, "elapsed_s": 565.0437264442444}
|
| 2 |
+
{"step": 20, "loss": 0.0008833259344100952, "reward_mean": -0.039813229348510504, "elapsed_s": 1126.7192077636719}
|
| 3 |
+
{"step": 30, "loss": 0.010403767228126526, "reward_mean": 0.10703995451331139, "elapsed_s": 1687.8455390930176}
|
| 4 |
+
{"step": 40, "loss": -0.002799093723297119, "reward_mean": 0.49303649365901947, "elapsed_s": 2240.5196924209595}
|
| 5 |
+
{"step": 50, "loss": -0.0063104331493377686, "reward_mean": 0.24993474781513214, "elapsed_s": 2793.26838183403}
|
| 6 |
+
{"step": 60, "loss": 0.007162690162658691, "reward_mean": -0.07944699004292488, "elapsed_s": 3344.3151874542236}
|
| 7 |
+
{"step": 70, "loss": -0.012678802013397217, "reward_mean": -0.002159707248210907, "elapsed_s": 3892.8130497932434}
|
| 8 |
+
{"step": 80, "loss": -0.003923147916793823, "reward_mean": 0.28788023442029953, "elapsed_s": 4440.892716407776}
|
| 9 |
+
{"step": 90, "loss": 0.0060828328132629395, "reward_mean": -0.07222479209303856, "elapsed_s": 5000.93599152565}
|
| 10 |
+
{"step": 100, "loss": -0.0016068816184997559, "reward_mean": 0.7107889652252197, "elapsed_s": 5557.579958438873}
|
| 11 |
+
{"step": 110, "loss": 0.0021146684885025024, "reward_mean": 0.7855450212955475, "elapsed_s": 6153.823330163956}
|
| 12 |
+
{"step": 120, "loss": 0.0073776766657829285, "reward_mean": 0.08973605558276176, "elapsed_s": 6713.7822415828705}
|
| 13 |
+
{"step": 130, "loss": 0.006254255771636963, "reward_mean": 0.06911695748567581, "elapsed_s": 7272.460590600967}
|
| 14 |
+
{"step": 140, "loss": -0.00035369396209716797, "reward_mean": 0.26761745661497116, "elapsed_s": 7831.599906682968}
|
| 15 |
+
{"step": 150, "loss": 0.011403657495975494, "reward_mean": -0.020937922410666943, "elapsed_s": 8392.139001131058}
|
| 16 |
+
{"step": 160, "loss": 0.006631344556808472, "reward_mean": 0.12494794651865959, "elapsed_s": 8952.17051577568}
|
| 17 |
+
{"step": 170, "loss": 0.007765814661979675, "reward_mean": 0.194949209690094, "elapsed_s": 9510.947650909424}
|
| 18 |
+
{"step": 180, "loss": 0.004343755543231964, "reward_mean": 0.3052072189748287, "elapsed_s": 10069.180739402771}
|
| 19 |
+
{"step": 190, "loss": -0.007063001394271851, "reward_mean": -0.10958028584718704, "elapsed_s": 10628.569958925247}
|
| 20 |
+
{"step": 200, "loss": -0.0016530603170394897, "reward_mean": -0.006728062871843576, "elapsed_s": 11187.833948373795}
|
| 21 |
+
{"step": 210, "loss": -0.0013205111026763916, "reward_mean": 0.1193685382604599, "elapsed_s": 11793.474682807922}
|
| 22 |
+
{"step": 220, "loss": 0.030853047966957092, "reward_mean": 0.2714747046120465, "elapsed_s": 12354.273264408112}
|
| 23 |
+
{"step": 230, "loss": -0.0058530643582344055, "reward_mean": -0.09769823402166367, "elapsed_s": 12913.481647729874}
|
| 24 |
+
{"step": 240, "loss": 0.011614024639129639, "reward_mean": 0.29820017889142036, "elapsed_s": 13471.913754224777}
|
| 25 |
+
{"step": 250, "loss": -0.014542058110237122, "reward_mean": -0.020933538675308228, "elapsed_s": 14029.693528413773}
|
| 26 |
+
{"step": 260, "loss": 0.009914800524711609, "reward_mean": -0.05361515749245882, "elapsed_s": 14588.536241292953}
|
| 27 |
+
{"step": 270, "loss": 0.0022788867354393005, "reward_mean": 0.26175590278580785, "elapsed_s": 15136.175908088684}
|
| 28 |
+
{"step": 280, "loss": 0.0007024705410003662, "reward_mean": 0.02863766998052597, "elapsed_s": 15684.365940093994}
|
| 29 |
+
{"step": 290, "loss": 0.0027166008949279785, "reward_mean": -0.146273635327816, "elapsed_s": 16230.387699127197}
|
| 30 |
+
{"step": 300, "loss": 0.0016746073961257935, "reward_mean": 0.16494493931531906, "elapsed_s": 16784.035522699356}
|