Backup runs/R1_aligned_v2/training.jsonl (52,859 bytes)
Browse files
byte_repair_v1/runs/R1_aligned_v2/training.jsonl
CHANGED
|
@@ -168,3 +168,13 @@
|
|
| 168 |
{"model": "R1", "step": 16800, "bytes_seen": 550502400, "loss": 2.450496289730072, "throughput_bytes_per_second": 110993.76752021418, "gpu_hours": 1.3777109899930555, "lr": 0.0002936306148598877, "base_loss": 1.1685312986373901, "on_policy_rollout_loss": 3.187481164932251, "rollout_steps": 2}
|
| 169 |
{"model": "R1", "step": 16900, "bytes_seen": 553779200, "loss": 2.4372637462615967, "throughput_bytes_per_second": 111007.61858147415, "gpu_hours": 1.3857387224522222, "lr": 0.00029083267291260144, "base_loss": 1.1884676218032837, "on_policy_rollout_loss": 3.096510887145996, "rollout_steps": 2}
|
| 170 |
{"model": "R1", "step": 17000, "bytes_seen": 557056000, "loss": 2.4655599713325502, "throughput_bytes_per_second": 111021.11371277596, "gpu_hours": 1.3937689201902776, "lr": 0.00028803902095462136, "base_loss": 1.0301244258880615, "on_policy_rollout_loss": 3.075671434402466, "rollout_steps": 2}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
{"model": "R1", "step": 16800, "bytes_seen": 550502400, "loss": 2.450496289730072, "throughput_bytes_per_second": 110993.76752021418, "gpu_hours": 1.3777109899930555, "lr": 0.0002936306148598877, "base_loss": 1.1685312986373901, "on_policy_rollout_loss": 3.187481164932251, "rollout_steps": 2}
|
| 169 |
{"model": "R1", "step": 16900, "bytes_seen": 553779200, "loss": 2.4372637462615967, "throughput_bytes_per_second": 111007.61858147415, "gpu_hours": 1.3857387224522222, "lr": 0.00029083267291260144, "base_loss": 1.1884676218032837, "on_policy_rollout_loss": 3.096510887145996, "rollout_steps": 2}
|
| 170 |
{"model": "R1", "step": 17000, "bytes_seen": 557056000, "loss": 2.4655599713325502, "throughput_bytes_per_second": 111021.11371277596, "gpu_hours": 1.3937689201902776, "lr": 0.00028803902095462136, "base_loss": 1.0301244258880615, "on_policy_rollout_loss": 3.075671434402466, "rollout_steps": 2}
|
| 171 |
+
{"model": "R1", "step": 17100, "bytes_seen": 560332800, "loss": 2.437816548347473, "throughput_bytes_per_second": 110915.53312488107, "gpu_hours": 1.4033020949802777, "lr": 0.0002852499649740739, "base_loss": 1.1878968477249146, "on_policy_rollout_loss": 3.121201992034912, "rollout_steps": 2}
|
| 172 |
+
{"model": "R1", "step": 17200, "bytes_seen": 563609600, "loss": 2.427800962924957, "throughput_bytes_per_second": 110929.46194863284, "gpu_hours": 1.4113313043447222, "lr": 0.00028246581045568875, "base_loss": 0.7966513633728027, "on_policy_rollout_loss": 3.1530773639678955, "rollout_steps": 2}
|
| 173 |
+
{"model": "R1", "step": 17300, "bytes_seen": 566886400, "loss": 2.4310819268226624, "throughput_bytes_per_second": 110943.24402883345, "gpu_hours": 1.419360374963611, "lr": 0.00027968686234733944, "base_loss": 1.146569013595581, "on_policy_rollout_loss": 3.131131887435913, "rollout_steps": 2}
|
| 174 |
+
{"model": "R1", "step": 17400, "bytes_seen": 570163200, "loss": 2.442524697780609, "throughput_bytes_per_second": 110957.17053970818, "gpu_hours": 1.4273855929841666, "lr": 0.0002769134250266428, "base_loss": 1.116336703300476, "on_policy_rollout_loss": 3.139105796813965, "rollout_steps": 2}
|
| 175 |
+
{"model": "R1", "step": 17500, "bytes_seen": 573440000, "loss": 2.442802221775055, "throughput_bytes_per_second": 110970.88205437186, "gpu_hours": 1.4354115777041665, "lr": 0.0002741458022676197, "base_loss": 1.2089418172836304, "on_policy_rollout_loss": 3.1713595390319824, "rollout_steps": 2}
|
| 176 |
+
{"model": "R1", "step": 17600, "bytes_seen": 576716800, "loss": 2.4372392201423647, "throughput_bytes_per_second": 110984.41374943154, "gpu_hours": 1.443437917983611, "lr": 0.0002713842972074237, "base_loss": 1.0894792079925537, "on_policy_rollout_loss": 3.167813301086426, "rollout_steps": 2}
|
| 177 |
+
{"model": "R1", "step": 17700, "bytes_seen": 579993600, "loss": 2.447715611457825, "throughput_bytes_per_second": 110997.91454300977, "gpu_hours": 1.4514627053727776, "lr": 0.00026862921231313804, "base_loss": 1.0317988395690918, "on_policy_rollout_loss": 3.0999438762664795, "rollout_steps": 2}
|
| 178 |
+
{"model": "R1", "step": 17800, "bytes_seen": 583270400, "loss": 2.436496477127075, "throughput_bytes_per_second": 111010.82677911254, "gpu_hours": 1.4594932787766668, "lr": 0.0002658808493486461, "base_loss": 1.0955450534820557, "on_policy_rollout_loss": 3.1452417373657227, "rollout_steps": 2}
|
| 179 |
+
{"model": "R1", "step": 17900, "bytes_seen": 586547200, "loss": 2.452021291255951, "throughput_bytes_per_second": 111023.74493371957, "gpu_hours": 1.4675219060125, "lr": 0.0002631395093415802, "base_loss": 1.0479291677474976, "on_policy_rollout_loss": 3.2235982418060303, "rollout_steps": 2}
|
| 180 |
+
{"model": "R1", "step": 18000, "bytes_seen": 589824000, "loss": 2.4407072854042053, "throughput_bytes_per_second": 111036.82137767266, "gpu_hours": 1.4755465616466668, "lr": 0.00026040549255034926, "base_loss": 1.1615465879440308, "on_policy_rollout_loss": 3.116551160812378, "rollout_steps": 2}
|