hbfreed's picture
Add files using upload-large-folder tool
9d757f9 verified
Raw
History Blame Contribute Delete
16.1 kB
{"step": 1, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.21866693885562322, "tokens": 120000, "cumulative_loss_tokens": 120000, "grad_norm": 0.703125, "lr": 6e-06, "finish_rate": 0.907, "comp_len": 508.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.3, "frames": {"chat": 236}, "mem_gb": 9.77}
{"step": 2, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2799584766006718, "tokens": 120000, "cumulative_loss_tokens": 240000, "grad_norm": 0.80078125, "lr": 9e-06, "finish_rate": 0.781, "comp_len": 558.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.1, "frames": {"chat": 215}, "mem_gb": 9.96}
{"step": 3, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.30753459547261397, "tokens": 120000, "cumulative_loss_tokens": 360000, "grad_norm": 0.89453125, "lr": 1.2e-05, "finish_rate": 0.825, "comp_len": 553.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.2, "frames": {"chat": 217}, "mem_gb": 9.83}
{"step": 4, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2795702153430631, "tokens": 120000, "cumulative_loss_tokens": 480000, "grad_norm": 0.796875, "lr": 1.5e-05, "finish_rate": 0.8, "comp_len": 585.4, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.5, "frames": {"chat": 205}, "mem_gb": 9.89}
{"step": 5, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.21330304649956525, "tokens": 120000, "cumulative_loss_tokens": 600000, "grad_norm": 0.62890625, "lr": 1.8e-05, "finish_rate": 0.834, "comp_len": 524.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.9, "frames": {"chat": 229}, "mem_gb": 9.86}
{"step": 6, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3496002516084661, "tokens": 120000, "cumulative_loss_tokens": 720000, "grad_norm": 1.3046875, "lr": 2.1e-05, "finish_rate": 0.812, "comp_len": 538.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.3, "frames": {"chat": 223}, "mem_gb": 9.93}
{"step": 7, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.23970425274328638, "tokens": 120000, "cumulative_loss_tokens": 840000, "grad_norm": 0.5546875, "lr": 2.4e-05, "finish_rate": 0.708, "comp_len": 594.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.6, "frames": {"chat": 202}, "mem_gb": 9.97}
{"step": 8, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.30002466305767495, "tokens": 120000, "cumulative_loss_tokens": 960000, "grad_norm": 0.78125, "lr": 2.7000000000000002e-05, "finish_rate": 0.77, "comp_len": 574.2, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.9, "frames": {"chat": 209}, "mem_gb": 9.94}
{"step": 9, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.212053201504983, "tokens": 120000, "cumulative_loss_tokens": 1080000, "grad_norm": 0.5703125, "lr": 3e-05, "finish_rate": 0.885, "comp_len": 528.6, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.5, "frames": {"chat": 227}, "mem_gb": 9.92}
{"step": 10, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.21668653630129994, "tokens": 120000, "cumulative_loss_tokens": 1200000, "grad_norm": 0.625, "lr": 3e-05, "finish_rate": 0.848, "comp_len": 521.7, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.9, "frames": {"chat": 230}, "mem_gb": 9.99}
{"step": 11, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2133969509905825, "tokens": 120000, "cumulative_loss_tokens": 1320000, "grad_norm": 0.5234375, "lr": 3e-05, "finish_rate": 0.879, "comp_len": 519.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.0, "frames": {"chat": 231}, "mem_gb": 9.84}
{"step": 12, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.23584020635082076, "tokens": 120000, "cumulative_loss_tokens": 1440000, "grad_norm": 0.62890625, "lr": 3e-05, "finish_rate": 0.882, "comp_len": 489.8, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.3, "frames": {"chat": 245}, "mem_gb": 9.92}
{"step": 13, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2676902946660916, "tokens": 120000, "cumulative_loss_tokens": 1560000, "grad_norm": 0.73828125, "lr": 3e-05, "finish_rate": 0.81, "comp_len": 571.4, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.7, "frames": {"chat": 210}, "mem_gb": 9.92}
{"step": 14, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2706234162639827, "tokens": 120000, "cumulative_loss_tokens": 1680000, "grad_norm": 0.6796875, "lr": 3e-05, "finish_rate": 0.758, "comp_len": 568.7, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.3, "frames": {"chat": 211}, "mem_gb": 9.92}
{"step": 15, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2641084919450184, "tokens": 120000, "cumulative_loss_tokens": 1800000, "grad_norm": 0.5625, "lr": 3e-05, "finish_rate": 0.819, "comp_len": 543.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.0, "frames": {"chat": 221}, "mem_gb": 9.98}
{"step": 16, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.22626812014766037, "tokens": 120000, "cumulative_loss_tokens": 1920000, "grad_norm": 0.6171875, "lr": 3e-05, "finish_rate": 0.912, "comp_len": 480.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.1, "frames": {"chat": 250}, "mem_gb": 9.79}
{"step": 17, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2563031171383957, "tokens": 120000, "cumulative_loss_tokens": 2040000, "grad_norm": 0.77734375, "lr": 3e-05, "finish_rate": 0.79, "comp_len": 524.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.9, "frames": {"chat": 229}, "mem_gb": 9.96}
{"step": 18, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2224606094551583, "tokens": 120000, "cumulative_loss_tokens": 2160000, "grad_norm": 0.7734375, "lr": 3e-05, "finish_rate": 0.888, "comp_len": 480.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.7, "frames": {"chat": 250}, "mem_gb": 9.94}
{"step": 19, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.33548496402837336, "tokens": 120000, "cumulative_loss_tokens": 2280000, "grad_norm": 2.703125, "lr": 3e-05, "finish_rate": 0.844, "comp_len": 519.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.6, "frames": {"chat": 231}, "mem_gb": 9.81}
{"step": 20, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3303738610186924, "tokens": 120000, "cumulative_loss_tokens": 2400000, "grad_norm": 1.359375, "lr": 3e-05, "finish_rate": 0.844, "comp_len": 535.7, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.6, "frames": {"chat": 224}, "mem_gb": 9.86}
{"step": 21, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.34314939406849443, "tokens": 120000, "cumulative_loss_tokens": 2520000, "grad_norm": 1.765625, "lr": 3e-05, "finish_rate": 0.802, "comp_len": 566.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.9, "frames": {"chat": 212}, "mem_gb": 9.9}
{"step": 22, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2919851597140233, "tokens": 120000, "cumulative_loss_tokens": 2640000, "grad_norm": 1.4765625, "lr": 3e-05, "finish_rate": 0.87, "comp_len": 504.2, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.9, "frames": {"chat": 238}, "mem_gb": 9.85}
{"step": 23, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2560206384329746, "tokens": 120000, "cumulative_loss_tokens": 2760000, "grad_norm": 1.4375, "lr": 3e-05, "finish_rate": 0.903, "comp_len": 466.9, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.9, "frames": {"chat": 257}, "mem_gb": 9.73}
{"step": 24, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.2622432756399115, "tokens": 120000, "cumulative_loss_tokens": 2880000, "grad_norm": 1.5, "lr": 3e-05, "finish_rate": 0.868, "comp_len": 528.6, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.8, "frames": {"chat": 227}, "mem_gb": 9.92}
{"step": 25, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.341244488842537, "tokens": 120000, "cumulative_loss_tokens": 3000000, "grad_norm": 2.359375, "lr": 3e-05, "finish_rate": 0.838, "comp_len": 526.3, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.9, "frames": {"chat": 228}, "mem_gb": 9.95}
{"step": 26, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.34149345571982365, "tokens": 120000, "cumulative_loss_tokens": 3120000, "grad_norm": 1.7734375, "lr": 3e-05, "finish_rate": 0.803, "comp_len": 515.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.1, "frames": {"chat": 233}, "mem_gb": 9.94}
{"step": 27, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3296166067738086, "tokens": 120000, "cumulative_loss_tokens": 3240000, "grad_norm": 3.125, "lr": 3e-05, "finish_rate": 0.863, "comp_len": 515.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.3, "frames": {"chat": 233}, "mem_gb": 9.94}
{"step": 28, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3747903925770273, "tokens": 120000, "cumulative_loss_tokens": 3360000, "grad_norm": 4.84375, "lr": 3e-05, "finish_rate": 0.731, "comp_len": 609.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.3, "frames": {"chat": 197}, "mem_gb": 10.03}
{"step": 29, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3595357739796241, "tokens": 120000, "cumulative_loss_tokens": 3480000, "grad_norm": 4.3125, "lr": 3e-05, "finish_rate": 0.862, "comp_len": 502.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.0, "frames": {"chat": 239}, "mem_gb": 9.79}
{"step": 30, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3622890787899494, "tokens": 120000, "cumulative_loss_tokens": 3600000, "grad_norm": 2.34375, "lr": 3e-05, "finish_rate": 0.83, "comp_len": 535.7, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.1, "frames": {"chat": 224}, "mem_gb": 9.83}
{"step": 31, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3522596547845751, "tokens": 120000, "cumulative_loss_tokens": 3720000, "grad_norm": 2.53125, "lr": 3e-05, "finish_rate": 0.788, "comp_len": 553.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.4, "frames": {"chat": 217}, "mem_gb": 9.95}
{"step": 32, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3673709363542497, "tokens": 120000, "cumulative_loss_tokens": 3840000, "grad_norm": 1.7734375, "lr": 3e-05, "finish_rate": 0.876, "comp_len": 497.9, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.2, "frames": {"chat": 241}, "mem_gb": 9.95}
{"step": 33, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.344472995601967, "tokens": 120000, "cumulative_loss_tokens": 3960000, "grad_norm": 1.71875, "lr": 3e-05, "finish_rate": 0.835, "comp_len": 550.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.0, "frames": {"chat": 218}, "mem_gb": 9.92}
{"step": 34, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3761791281307737, "tokens": 120000, "cumulative_loss_tokens": 4080000, "grad_norm": 1.6953125, "lr": 3e-05, "finish_rate": 0.767, "comp_len": 582.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.9, "frames": {"chat": 206}, "mem_gb": 9.93}
{"step": 35, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.40928577872092525, "tokens": 120000, "cumulative_loss_tokens": 4200000, "grad_norm": 4.65625, "lr": 3e-05, "finish_rate": 0.845, "comp_len": 517.2, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.0, "frames": {"chat": 232}, "mem_gb": 9.97}
{"step": 36, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4327475581978758, "tokens": 120000, "cumulative_loss_tokens": 4320000, "grad_norm": 2.234375, "lr": 3e-05, "finish_rate": 0.771, "comp_len": 550.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.6, "frames": {"chat": 218}, "mem_gb": 9.99}
{"step": 37, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4185904825979223, "tokens": 120000, "cumulative_loss_tokens": 4440000, "grad_norm": 1.7734375, "lr": 3e-05, "finish_rate": 0.779, "comp_len": 563.4, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.9, "frames": {"chat": 213}, "mem_gb": 9.95}
{"step": 38, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.39999025528704124, "tokens": 120000, "cumulative_loss_tokens": 4560000, "grad_norm": 2.109375, "lr": 3e-05, "finish_rate": 0.887, "comp_len": 483.9, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.5, "frames": {"chat": 248}, "mem_gb": 9.92}
{"step": 39, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3818524689834565, "tokens": 120000, "cumulative_loss_tokens": 4680000, "grad_norm": 3.625, "lr": 3e-05, "finish_rate": 0.803, "comp_len": 550.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.2, "frames": {"chat": 218}, "mem_gb": 9.99}
{"step": 40, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4018356613169114, "tokens": 120000, "cumulative_loss_tokens": 4800000, "grad_norm": 1.9765625, "lr": 3e-05, "finish_rate": 0.851, "comp_len": 543.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.7, "frames": {"chat": 221}, "mem_gb": 9.94}
{"step": 41, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.3970720124833286, "tokens": 120000, "cumulative_loss_tokens": 4920000, "grad_norm": 1.8828125, "lr": 3e-05, "finish_rate": 0.894, "comp_len": 508.5, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.5, "frames": {"chat": 236}, "mem_gb": 9.87}
{"step": 42, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.41181738175004723, "tokens": 120000, "cumulative_loss_tokens": 5040000, "grad_norm": 2.96875, "lr": 3e-05, "finish_rate": 0.858, "comp_len": 487.8, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 27.6, "frames": {"chat": 246}, "mem_gb": 9.79}
{"step": 43, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.41396116232958935, "tokens": 120000, "cumulative_loss_tokens": 5160000, "grad_norm": 1.5390625, "lr": 3e-05, "finish_rate": 0.838, "comp_len": 512.8, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.9, "frames": {"chat": 234}, "mem_gb": 10.05}
{"step": 44, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4312684536229819, "tokens": 120000, "cumulative_loss_tokens": 5280000, "grad_norm": 3.03125, "lr": 3e-05, "finish_rate": 0.748, "comp_len": 594.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.7, "frames": {"chat": 202}, "mem_gb": 9.93}
{"step": 45, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4649944137908518, "tokens": 120000, "cumulative_loss_tokens": 5400000, "grad_norm": 3.171875, "lr": 3e-05, "finish_rate": 0.811, "comp_len": 553.0, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.2, "frames": {"chat": 217}, "mem_gb": 9.94}
{"step": 46, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4571197036482394, "tokens": 120000, "cumulative_loss_tokens": 5520000, "grad_norm": 5.46875, "lr": 3e-05, "finish_rate": 0.866, "comp_len": 535.7, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.4, "frames": {"chat": 224}, "mem_gb": 9.94}
{"step": 47, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.47359946348716814, "tokens": 120000, "cumulative_loss_tokens": 5640000, "grad_norm": 2.3125, "lr": 3e-05, "finish_rate": 0.753, "comp_len": 558.1, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 25.2, "frames": {"chat": 215}, "mem_gb": 9.96}
{"step": 48, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.478707897759974, "tokens": 120000, "cumulative_loss_tokens": 5760000, "grad_norm": 13.5625, "lr": 3e-05, "finish_rate": 0.884, "comp_len": 463.3, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.6, "frames": {"chat": 259}, "mem_gb": 9.87}
{"step": 49, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.4946964275722702, "tokens": 120000, "cumulative_loss_tokens": 5880000, "grad_norm": 15.3125, "lr": 3e-05, "finish_rate": 0.829, "comp_len": 571.4, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 24.5, "frames": {"chat": 210}, "mem_gb": 9.94}
{"step": 50, "epoch": 0, "training_mode": "off-policy", "forward_topk_kl": 0.5027643982246518, "tokens": 120000, "cumulative_loss_tokens": 6000000, "grad_norm": 8.5625, "lr": 3e-05, "finish_rate": 0.77, "comp_len": 563.4, "t_data_s": 0.0, "t_rollout_s": 0.0, "t_step_s": 26.4, "frames": {"chat": 213}, "mem_gb": 9.99}