| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 192.64206001263068, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9869, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 48.1404574206668, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2726, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 41.79888626205312, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 18.107174654771164, | |
| "learning_rate": 2e-05, | |
| "loss": 0.694, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 30.2422290061728, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4019, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 32.685282758571375, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7553, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 18.979239258345306, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5813, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 19.764858390255736, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 22.461668082512883, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7166, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 5.772167653543795, | |
| "learning_rate": 2e-05, | |
| "loss": 0.477, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 23.763305086803346, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4109, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 19.437747488324412, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7639, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 37.05102235979124, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8183, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 23.014514492561837, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6484, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 12.77252167418251, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2884, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 11.73960064185402, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5449, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 28.512782095251783, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4911, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 12.937559735306024, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4353, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 19.839752017761988, | |
| "learning_rate": 2e-05, | |
| "loss": 0.508, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 25.83637222146644, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6268, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 7.866252327982729, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2765, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 19.173168345597215, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3429, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 7.356122490363529, | |
| "learning_rate": 2e-05, | |
| "loss": 0.673, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 25.452330672923093, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2502, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 18.193546104023437, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5538, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 10.606904391146188, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4428, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 24.98698506555314, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7371, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 12.932817524755643, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3546, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 23.09632284588474, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5592, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 12.27489087251143, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5467, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 37.77701888603335, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4446, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 44.43844469994968, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5023, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 24.744024542612852, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5357, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 23.375337882754707, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4636, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 17.471065994038756, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6389, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 17.504412137784108, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4652, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 18.34290057543399, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5353, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 10.469335873485205, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4117, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 8.574566538117475, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1914, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 34.729664060077845, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9078, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 11.83902631776558, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4132, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 19.70511531848034, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5426, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 16.283872444359304, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4625, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 11.310750776722527, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6134, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 10.965542860625407, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5924, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 13.517564564054656, | |
| "learning_rate": 2e-05, | |
| "loss": 0.6286, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 34.26880432074886, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4085, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 25.030865721860277, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3896, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 25.98960849665949, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7899, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.864625940315946, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4402, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "grad_norm": 11.40545315116504, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3358, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "grad_norm": 13.463916057621617, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3494, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 9.782398722159707, | |
| "learning_rate": 2e-05, | |
| "loss": 0.323, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "grad_norm": 13.317644626850393, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3282, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 5.139859271115599, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2077, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 7.631702619157663, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2774, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.1400000000000001, | |
| "grad_norm": 5.33820682349548, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1876, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "grad_norm": 17.796618873954458, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2024, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "grad_norm": 7.742739766893884, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2382, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 12.272583734681321, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1758, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "grad_norm": 15.072772862067511, | |
| "learning_rate": 2e-05, | |
| "loss": 0.162, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 12.379175079681959, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3106, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "grad_norm": 33.48507360806824, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1663, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 15.999333486664096, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4353, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "grad_norm": 14.39207981694989, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3389, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 13.332999614759036, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4599, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "grad_norm": 23.928605991003675, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2329, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.3599999999999999, | |
| "grad_norm": 13.34758642775842, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2337, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 24.352266155741198, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2545, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "grad_norm": 10.093768669427867, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1388, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 32.58466972795229, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3381, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 16.995622901411814, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2648, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "grad_norm": 10.97816885532189, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3115, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "grad_norm": 11.548897196049536, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2889, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 14.16697968734292, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1862, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.52, | |
| "grad_norm": 10.212597579637505, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2742, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "grad_norm": 8.91459350111025, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1768, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 4.5094557209751125, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2998, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "grad_norm": 17.12956574852988, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4823, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 9.24016552408342, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3929, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "grad_norm": 1.7011726405852587, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0779, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 5.402131687184834, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2897, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.6600000000000001, | |
| "grad_norm": 41.449093332441706, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2473, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 1.6800000000000002, | |
| "grad_norm": 6.669376800386209, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3655, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 8.23518921357868, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3253, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "grad_norm": 9.034537410146203, | |
| "learning_rate": 2e-05, | |
| "loss": 0.296, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 11.56008324710057, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3163, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 5.894931150739263, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3091, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "grad_norm": 7.0458502125313345, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2953, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "grad_norm": 6.778888500945086, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3389, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.8199999999999998, | |
| "grad_norm": 5.539170431035288, | |
| "learning_rate": 2e-05, | |
| "loss": 0.435, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.8399999999999999, | |
| "grad_norm": 3.343648740799574, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2393, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.8599999999999999, | |
| "grad_norm": 12.183313738430767, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2175, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 12.811874616374048, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3642, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "grad_norm": 9.28274328738779, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2358, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 3.6965502254399536, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1731, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "grad_norm": 23.422711462644386, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2284, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 6.007651568580575, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2029, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "grad_norm": 22.857478600516423, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2268, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 7.607530663493723, | |
| "learning_rate": 2e-05, | |
| "loss": 0.396, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 268959744000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |