| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.36496350364963503, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004866180048661801, | |
| "grad_norm": 0.6534222364425659, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 9.6643, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004866180048661801, | |
| "eval_loss": 1.717971920967102, | |
| "eval_runtime": 99.4449, | |
| "eval_samples_per_second": 1.75, | |
| "eval_steps_per_second": 0.875, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009732360097323601, | |
| "grad_norm": 0.7636905908584595, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.4849, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.014598540145985401, | |
| "grad_norm": 0.8352400660514832, | |
| "learning_rate": 0.0001, | |
| "loss": 10.5691, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.019464720194647202, | |
| "grad_norm": 1.1163321733474731, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.8908, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024330900243309004, | |
| "grad_norm": 1.1510467529296875, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.8367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.029197080291970802, | |
| "grad_norm": 1.3899632692337036, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3491, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0340632603406326, | |
| "grad_norm": 1.2129096984863281, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 11.0093, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.038929440389294405, | |
| "grad_norm": 1.380240797996521, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 11.1512, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.043795620437956206, | |
| "grad_norm": 1.4904532432556152, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.2217, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04866180048661801, | |
| "grad_norm": 1.634533166885376, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.5503, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0535279805352798, | |
| "grad_norm": 1.5645819902420044, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.7389, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.058394160583941604, | |
| "grad_norm": 1.600929856300354, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.5976, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06326034063260341, | |
| "grad_norm": 1.604222059249878, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.7785, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0681265206812652, | |
| "grad_norm": 1.727508306503296, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.7356, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 1.7615082263946533, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.9871, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07785888077858881, | |
| "grad_norm": 1.8271732330322266, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 11.0153, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0827250608272506, | |
| "grad_norm": 1.8473275899887085, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 11.4744, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08759124087591241, | |
| "grad_norm": 2.002676010131836, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.1621, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09245742092457421, | |
| "grad_norm": 2.036090850830078, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 11.6886, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09732360097323602, | |
| "grad_norm": 2.1093671321868896, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 11.2061, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10218978102189781, | |
| "grad_norm": 2.150874614715576, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.1087, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1070559610705596, | |
| "grad_norm": 2.380944013595581, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.9267, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11192214111922141, | |
| "grad_norm": 2.3676857948303223, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 11.7442, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11678832116788321, | |
| "grad_norm": 2.6119561195373535, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.3183, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12165450121654502, | |
| "grad_norm": 2.365917921066284, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 10.8457, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12165450121654502, | |
| "eval_loss": 1.371411919593811, | |
| "eval_runtime": 99.9993, | |
| "eval_samples_per_second": 1.74, | |
| "eval_steps_per_second": 0.87, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12652068126520682, | |
| "grad_norm": 2.573071241378784, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.9635, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13138686131386862, | |
| "grad_norm": 2.5956778526306152, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.7278, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1362530413625304, | |
| "grad_norm": 2.9840710163116455, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 11.3258, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1411192214111922, | |
| "grad_norm": 2.692122459411621, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 11.1816, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 2.821690559387207, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.7083, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15085158150851583, | |
| "grad_norm": 2.8995065689086914, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 11.7289, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15571776155717762, | |
| "grad_norm": 2.86710524559021, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 11.5014, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16058394160583941, | |
| "grad_norm": 3.1569883823394775, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.8144, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1654501216545012, | |
| "grad_norm": 2.958052396774292, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 11.5663, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.170316301703163, | |
| "grad_norm": 2.971606731414795, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 11.8629, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17518248175182483, | |
| "grad_norm": 3.4037623405456543, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.2805, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18004866180048662, | |
| "grad_norm": 3.7285900115966797, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 11.6089, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18491484184914841, | |
| "grad_norm": 3.6044297218322754, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 12.6734, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1897810218978102, | |
| "grad_norm": 3.859436511993408, | |
| "learning_rate": 5e-05, | |
| "loss": 11.3451, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19464720194647203, | |
| "grad_norm": 4.121180534362793, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 11.4139, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19951338199513383, | |
| "grad_norm": 4.352361679077148, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 13.3278, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20437956204379562, | |
| "grad_norm": 3.7588999271392822, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.9387, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.20924574209245742, | |
| "grad_norm": 4.562860012054443, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 12.128, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2141119221411192, | |
| "grad_norm": 4.854923725128174, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 11.4224, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.21897810218978103, | |
| "grad_norm": 4.410684585571289, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.0198, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22384428223844283, | |
| "grad_norm": 4.752728462219238, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 11.2316, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.22871046228710462, | |
| "grad_norm": 4.889558792114258, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.6528, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.23357664233576642, | |
| "grad_norm": 6.103560924530029, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.6173, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2384428223844282, | |
| "grad_norm": 6.686156749725342, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 11.7325, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24330900243309003, | |
| "grad_norm": 8.535616874694824, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.9532, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24330900243309003, | |
| "eval_loss": 1.3366206884384155, | |
| "eval_runtime": 100.0065, | |
| "eval_samples_per_second": 1.74, | |
| "eval_steps_per_second": 0.87, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24817518248175183, | |
| "grad_norm": 1.754204511642456, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 8.2569, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.25304136253041365, | |
| "grad_norm": 2.188532829284668, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 8.7464, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.25790754257907544, | |
| "grad_norm": 2.390721559524536, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 9.9108, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.26277372262773724, | |
| "grad_norm": 2.576392889022827, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.1054, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.26763990267639903, | |
| "grad_norm": 2.147494077682495, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 9.8218, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2725060827250608, | |
| "grad_norm": 2.0287535190582275, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.3552, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2773722627737226, | |
| "grad_norm": 2.4717705249786377, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.4594, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2822384428223844, | |
| "grad_norm": 2.5552027225494385, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.1801, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2871046228710462, | |
| "grad_norm": 2.0711898803710938, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.1532, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.291970802919708, | |
| "grad_norm": 2.061006546020508, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.4756, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29683698296836986, | |
| "grad_norm": 2.3004233837127686, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 9.6621, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.30170316301703165, | |
| "grad_norm": 2.1852986812591553, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3212, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.30656934306569344, | |
| "grad_norm": 2.386976957321167, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.2014, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.31143552311435524, | |
| "grad_norm": 2.3682126998901367, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.4178, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.31630170316301703, | |
| "grad_norm": 2.1567893028259277, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 9.9836, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.32116788321167883, | |
| "grad_norm": 2.226053476333618, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.4578, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3260340632603406, | |
| "grad_norm": 2.296086072921753, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.5194, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.3309002433090024, | |
| "grad_norm": 5.2668776512146, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.2628, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3357664233576642, | |
| "grad_norm": 2.316244602203369, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 9.9051, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.340632603406326, | |
| "grad_norm": 2.4800219535827637, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.9728, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.34549878345498786, | |
| "grad_norm": 2.387953281402588, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.6898, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.35036496350364965, | |
| "grad_norm": 2.5870020389556885, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.2093, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.35523114355231145, | |
| "grad_norm": 2.600900888442993, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.8837, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.36009732360097324, | |
| "grad_norm": 2.623093366622925, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 10.6526, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "grad_norm": 2.7400941848754883, | |
| "learning_rate": 0.0, | |
| "loss": 11.0227, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.36496350364963503, | |
| "eval_loss": 1.3052926063537598, | |
| "eval_runtime": 100.089, | |
| "eval_samples_per_second": 1.738, | |
| "eval_steps_per_second": 0.869, | |
| "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": 1.9422814666752e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |