| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013095290060674844, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017460386747566458, | |
| "grad_norm": 0.7365045547485352, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.8112, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017460386747566458, | |
| "eval_loss": 1.5676409006118774, | |
| "eval_runtime": 538.1585, | |
| "eval_samples_per_second": 8.962, | |
| "eval_steps_per_second": 4.482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00034920773495132916, | |
| "grad_norm": 1.230597972869873, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 2.0408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005238116024269937, | |
| "grad_norm": 1.01038658618927, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5271, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006984154699026583, | |
| "grad_norm": 1.0910125970840454, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 1.5123, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008730193373783229, | |
| "grad_norm": 1.1756590604782104, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 1.3788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0010476232048539874, | |
| "grad_norm": 1.2190275192260742, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.6374, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001222227072329652, | |
| "grad_norm": 1.3136614561080933, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.4122, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013968309398053166, | |
| "grad_norm": 1.3199424743652344, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 1.4148, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015714348072809812, | |
| "grad_norm": 1.2985801696777344, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017460386747566458, | |
| "grad_norm": 1.776046872138977, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 1.2455, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019206425422323104, | |
| "grad_norm": 1.5616651773452759, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.396, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002095246409707975, | |
| "grad_norm": 1.5658314228057861, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2894, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022698502771836397, | |
| "grad_norm": 1.3641587495803833, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 1.1194, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.002444454144659304, | |
| "grad_norm": 1.3050167560577393, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 1.3872, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.002619058012134969, | |
| "grad_norm": 1.1339519023895264, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.5126, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0027936618796106333, | |
| "grad_norm": 1.3289313316345215, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 1.4058, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002968265747086298, | |
| "grad_norm": 1.438923954963684, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 1.2404, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0031428696145619625, | |
| "grad_norm": 1.2848269939422607, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.2624, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0033174734820376273, | |
| "grad_norm": 1.341930866241455, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 1.3761, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0034920773495132917, | |
| "grad_norm": 1.1548206806182861, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 1.5395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036666812169889565, | |
| "grad_norm": 1.1897963285446167, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.4114, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003841285084464621, | |
| "grad_norm": 1.1397008895874023, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 1.6104, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.004015888951940286, | |
| "grad_norm": 1.6328984498977661, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 1.5125, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00419049281941595, | |
| "grad_norm": 1.214820384979248, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.222, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0043650966868916145, | |
| "grad_norm": 1.469793677330017, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 1.1239, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0043650966868916145, | |
| "eval_loss": 1.2938027381896973, | |
| "eval_runtime": 539.1895, | |
| "eval_samples_per_second": 8.945, | |
| "eval_steps_per_second": 4.473, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004539700554367279, | |
| "grad_norm": 1.3989931344985962, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 1.0884, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.004714304421842944, | |
| "grad_norm": 1.6388263702392578, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1209, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004888908289318608, | |
| "grad_norm": 1.3612502813339233, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 1.4583, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.005063512156794273, | |
| "grad_norm": 1.323246955871582, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 1.3841, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.005238116024269938, | |
| "grad_norm": 1.2201770544052124, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3537, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005412719891745603, | |
| "grad_norm": 1.169925570487976, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 1.0672, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0055873237592212665, | |
| "grad_norm": 1.8130548000335693, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 1.2598, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.005761927626696931, | |
| "grad_norm": 1.4853343963623047, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2338, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.005936531494172596, | |
| "grad_norm": 1.5606756210327148, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 1.1368, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00611113536164826, | |
| "grad_norm": 1.3997530937194824, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 1.0479, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006285739229123925, | |
| "grad_norm": 1.3681511878967285, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3044, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.00646034309659959, | |
| "grad_norm": 1.387187123298645, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 1.4802, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.006634946964075255, | |
| "grad_norm": 1.53128182888031, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 1.2611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0068095508315509186, | |
| "grad_norm": 1.3304214477539062, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4855, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.006984154699026583, | |
| "grad_norm": 1.5679274797439575, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 1.0539, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007158758566502248, | |
| "grad_norm": 1.6547032594680786, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 1.3219, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.007333362433977913, | |
| "grad_norm": 1.4425872564315796, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2929, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.007507966301453577, | |
| "grad_norm": 1.4797848463058472, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.9107, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.007682570168929242, | |
| "grad_norm": 1.6376514434814453, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 1.2856, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.007857174036404907, | |
| "grad_norm": 1.8783955574035645, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.378, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008031777903880571, | |
| "grad_norm": 1.9573678970336914, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 1.2765, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.008206381771356236, | |
| "grad_norm": 1.8132413625717163, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.2729, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0083809856388319, | |
| "grad_norm": 1.527602195739746, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9316, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.008555589506307564, | |
| "grad_norm": 2.0688371658325195, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 1.2326, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.008730193373783229, | |
| "grad_norm": 3.0766944885253906, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 1.3781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008730193373783229, | |
| "eval_loss": 1.292413592338562, | |
| "eval_runtime": 537.8588, | |
| "eval_samples_per_second": 8.967, | |
| "eval_steps_per_second": 4.484, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008904797241258894, | |
| "grad_norm": 0.8374080657958984, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7621, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.009079401108734559, | |
| "grad_norm": 0.9951280951499939, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 1.3985, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.009254004976210223, | |
| "grad_norm": 1.160885214805603, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 1.7472, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.009428608843685888, | |
| "grad_norm": 1.3874828815460205, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4435, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.009603212711161551, | |
| "grad_norm": 1.014530897140503, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.5598, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.009777816578637216, | |
| "grad_norm": 0.8571755290031433, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 1.4335, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.009952420446112881, | |
| "grad_norm": 1.069875717163086, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9947, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.010127024313588546, | |
| "grad_norm": 0.9428219199180603, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 1.4383, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.01030162818106421, | |
| "grad_norm": 0.9815278649330139, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.4594, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.010476232048539875, | |
| "grad_norm": 1.117757797241211, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6801, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01065083591601554, | |
| "grad_norm": 1.043749213218689, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 1.2292, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.010825439783491205, | |
| "grad_norm": 1.0151351690292358, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 1.3968, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.011000043650966868, | |
| "grad_norm": 1.138023853302002, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.4304, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.011174647518442533, | |
| "grad_norm": 1.0070977210998535, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 1.2263, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.011349251385918198, | |
| "grad_norm": 1.4350625276565552, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 1.5576, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.011523855253393863, | |
| "grad_norm": 1.046802282333374, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2175, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.011698459120869528, | |
| "grad_norm": 1.1393954753875732, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.1448, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.011873062988345192, | |
| "grad_norm": 1.213820219039917, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 1.2862, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.012047666855820857, | |
| "grad_norm": 1.0615662336349487, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2547, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01222227072329652, | |
| "grad_norm": 2.1386613845825195, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 1.3689, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.012396874590772185, | |
| "grad_norm": 1.4475680589675903, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.0843, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01257147845824785, | |
| "grad_norm": 1.0686284303665161, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.2531, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.012746082325723515, | |
| "grad_norm": 1.3505923748016357, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 1.2997, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.01292068619319918, | |
| "grad_norm": 1.0805271863937378, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 1.5371, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.013095290060674844, | |
| "grad_norm": 1.453600525856018, | |
| "learning_rate": 0.0, | |
| "loss": 1.4003, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.013095290060674844, | |
| "eval_loss": 1.2775593996047974, | |
| "eval_runtime": 538.056, | |
| "eval_samples_per_second": 8.964, | |
| "eval_steps_per_second": 4.483, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1208807043773235e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |