| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 14.646464646464647, | |
| "eval_steps": 20, | |
| "global_step": 580, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25252525252525254, | |
| "grad_norm": 13.126054763793945, | |
| "learning_rate": 1.6949152542372882e-06, | |
| "loss": 0.8683, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 17.31291961669922, | |
| "learning_rate": 3.3898305084745763e-06, | |
| "loss": 0.7248, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 8.053046226501465, | |
| "learning_rate": 5.084745762711865e-06, | |
| "loss": 0.6134, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0101010101010102, | |
| "grad_norm": 9.220598220825195, | |
| "learning_rate": 6.779661016949153e-06, | |
| "loss": 0.5526, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2626262626262625, | |
| "grad_norm": 27.968978881835938, | |
| "learning_rate": 8.47457627118644e-06, | |
| "loss": 0.4393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 5.585519313812256, | |
| "learning_rate": 9.980988593155894e-06, | |
| "loss": 0.34, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.7676767676767677, | |
| "grad_norm": 4.464208602905273, | |
| "learning_rate": 9.790874524714829e-06, | |
| "loss": 0.3483, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.0202020202020203, | |
| "grad_norm": 11.554718017578125, | |
| "learning_rate": 9.600760456273765e-06, | |
| "loss": 0.3142, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 6.658814907073975, | |
| "learning_rate": 9.4106463878327e-06, | |
| "loss": 0.2071, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.525252525252525, | |
| "grad_norm": 6.011457443237305, | |
| "learning_rate": 9.220532319391637e-06, | |
| "loss": 0.2287, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 9.19509220123291, | |
| "learning_rate": 9.030418250950572e-06, | |
| "loss": 0.2189, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 3.0303030303030303, | |
| "grad_norm": 4.081284523010254, | |
| "learning_rate": 8.840304182509506e-06, | |
| "loss": 0.1807, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.282828282828283, | |
| "grad_norm": 4.492301940917969, | |
| "learning_rate": 8.650190114068441e-06, | |
| "loss": 0.1727, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.5353535353535355, | |
| "grad_norm": 5.772425174713135, | |
| "learning_rate": 8.460076045627376e-06, | |
| "loss": 0.128, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.787878787878788, | |
| "grad_norm": 24.84961700439453, | |
| "learning_rate": 8.269961977186313e-06, | |
| "loss": 0.1993, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.040404040404041, | |
| "grad_norm": 2.998711585998535, | |
| "learning_rate": 8.079847908745247e-06, | |
| "loss": 0.1502, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.292929292929293, | |
| "grad_norm": 6.577826499938965, | |
| "learning_rate": 7.889733840304184e-06, | |
| "loss": 0.1225, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.545454545454545, | |
| "grad_norm": 8.288976669311523, | |
| "learning_rate": 7.699619771863119e-06, | |
| "loss": 0.1113, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.797979797979798, | |
| "grad_norm": 8.804610252380371, | |
| "learning_rate": 7.509505703422054e-06, | |
| "loss": 0.1692, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.05050505050505, | |
| "grad_norm": 5.5263752937316895, | |
| "learning_rate": 7.319391634980989e-06, | |
| "loss": 0.1364, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.303030303030303, | |
| "grad_norm": 3.2428457736968994, | |
| "learning_rate": 7.129277566539925e-06, | |
| "loss": 0.0863, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 6.467748165130615, | |
| "learning_rate": 6.93916349809886e-06, | |
| "loss": 0.1099, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.808080808080808, | |
| "grad_norm": 8.438054084777832, | |
| "learning_rate": 6.749049429657795e-06, | |
| "loss": 0.1037, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.0606060606060606, | |
| "grad_norm": 2.7920687198638916, | |
| "learning_rate": 6.55893536121673e-06, | |
| "loss": 0.1054, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.313131313131313, | |
| "grad_norm": 14.06596565246582, | |
| "learning_rate": 6.368821292775666e-06, | |
| "loss": 0.0708, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.565656565656566, | |
| "grad_norm": 3.4552762508392334, | |
| "learning_rate": 6.1787072243346015e-06, | |
| "loss": 0.0963, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.818181818181818, | |
| "grad_norm": 4.3161234855651855, | |
| "learning_rate": 5.988593155893536e-06, | |
| "loss": 0.1237, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.070707070707071, | |
| "grad_norm": 3.9048163890838623, | |
| "learning_rate": 5.798479087452472e-06, | |
| "loss": 0.0868, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.3232323232323235, | |
| "grad_norm": 8.73560905456543, | |
| "learning_rate": 5.608365019011407e-06, | |
| "loss": 0.0681, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.575757575757576, | |
| "grad_norm": 3.1624324321746826, | |
| "learning_rate": 5.418250950570343e-06, | |
| "loss": 0.0912, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.828282828282829, | |
| "grad_norm": 3.010721206665039, | |
| "learning_rate": 5.228136882129278e-06, | |
| "loss": 0.0618, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 8.080808080808081, | |
| "grad_norm": 2.488093137741089, | |
| "learning_rate": 5.038022813688214e-06, | |
| "loss": 0.0484, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 44.87844467163086, | |
| "learning_rate": 4.847908745247149e-06, | |
| "loss": 0.0665, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.585858585858587, | |
| "grad_norm": 5.052587032318115, | |
| "learning_rate": 4.657794676806084e-06, | |
| "loss": 0.0643, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.83838383838384, | |
| "grad_norm": 1.7123836278915405, | |
| "learning_rate": 4.467680608365019e-06, | |
| "loss": 0.0575, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 9.090909090909092, | |
| "grad_norm": 1.540806770324707, | |
| "learning_rate": 4.277566539923955e-06, | |
| "loss": 0.0669, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.343434343434343, | |
| "grad_norm": 6.937175750732422, | |
| "learning_rate": 4.08745247148289e-06, | |
| "loss": 0.0502, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.595959595959595, | |
| "grad_norm": 1.7217215299606323, | |
| "learning_rate": 3.897338403041825e-06, | |
| "loss": 0.0586, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.848484848484848, | |
| "grad_norm": 2.884972095489502, | |
| "learning_rate": 3.707224334600761e-06, | |
| "loss": 0.0691, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 10.1010101010101, | |
| "grad_norm": 3.5889267921447754, | |
| "learning_rate": 3.517110266159696e-06, | |
| "loss": 0.0717, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.353535353535353, | |
| "grad_norm": 3.033485174179077, | |
| "learning_rate": 3.3269961977186314e-06, | |
| "loss": 0.0491, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.606060606060606, | |
| "grad_norm": 1.5832382440567017, | |
| "learning_rate": 3.136882129277567e-06, | |
| "loss": 0.0457, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.858585858585858, | |
| "grad_norm": 0.04450301453471184, | |
| "learning_rate": 2.9467680608365023e-06, | |
| "loss": 0.0687, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 4.540256977081299, | |
| "learning_rate": 2.756653992395438e-06, | |
| "loss": 0.0593, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 11.363636363636363, | |
| "grad_norm": 4.446552753448486, | |
| "learning_rate": 2.5665399239543728e-06, | |
| "loss": 0.0404, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.616161616161616, | |
| "grad_norm": 1.007643222808838, | |
| "learning_rate": 2.3764258555133084e-06, | |
| "loss": 0.0402, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 11.868686868686869, | |
| "grad_norm": 0.96592116355896, | |
| "learning_rate": 2.1863117870722437e-06, | |
| "loss": 0.0448, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 12.121212121212121, | |
| "grad_norm": 6.914277076721191, | |
| "learning_rate": 1.996197718631179e-06, | |
| "loss": 0.0536, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 12.373737373737374, | |
| "grad_norm": 4.67967414855957, | |
| "learning_rate": 1.8060836501901142e-06, | |
| "loss": 0.0487, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 12.626262626262626, | |
| "grad_norm": 2.039752721786499, | |
| "learning_rate": 1.6159695817490494e-06, | |
| "loss": 0.0468, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.878787878787879, | |
| "grad_norm": 7.157741546630859, | |
| "learning_rate": 1.4258555133079848e-06, | |
| "loss": 0.0317, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 13.131313131313131, | |
| "grad_norm": 4.240894317626953, | |
| "learning_rate": 1.2357414448669203e-06, | |
| "loss": 0.0424, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 13.383838383838384, | |
| "grad_norm": 1.8747172355651855, | |
| "learning_rate": 1.0456273764258558e-06, | |
| "loss": 0.0396, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 13.636363636363637, | |
| "grad_norm": 1.3047974109649658, | |
| "learning_rate": 8.555133079847909e-07, | |
| "loss": 0.0403, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 13.88888888888889, | |
| "grad_norm": 1.6948643922805786, | |
| "learning_rate": 6.653992395437263e-07, | |
| "loss": 0.0372, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 14.141414141414142, | |
| "grad_norm": 3.19494891166687, | |
| "learning_rate": 4.752851711026616e-07, | |
| "loss": 0.0422, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 14.393939393939394, | |
| "grad_norm": 0.13894398510456085, | |
| "learning_rate": 2.85171102661597e-07, | |
| "loss": 0.0292, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 14.646464646464647, | |
| "grad_norm": 0.04802278056740761, | |
| "learning_rate": 9.505703422053233e-08, | |
| "loss": 0.0377, | |
| "step": 580 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 585, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5658543749477888e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |