| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07716049382716049, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00102880658436214, | |
| "grad_norm": 0.03394113853573799, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3785, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00102880658436214, | |
| "eval_loss": 10.375594139099121, | |
| "eval_runtime": 3.9062, | |
| "eval_samples_per_second": 209.668, | |
| "eval_steps_per_second": 104.962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00205761316872428, | |
| "grad_norm": 0.03017851896584034, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3758, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0030864197530864196, | |
| "grad_norm": 0.04688714072108269, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3742, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00411522633744856, | |
| "grad_norm": 0.04803881794214249, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0051440329218107, | |
| "grad_norm": 0.05451498180627823, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.3723, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006172839506172839, | |
| "grad_norm": 0.05231399089097977, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00720164609053498, | |
| "grad_norm": 0.054329585283994675, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3694, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00823045267489712, | |
| "grad_norm": 0.05516041815280914, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.3699, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009259259259259259, | |
| "grad_norm": 0.05256799980998039, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3726, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0102880658436214, | |
| "grad_norm": 0.056837018579244614, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.3745, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01131687242798354, | |
| "grad_norm": 0.05345076322555542, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3692, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.012345679012345678, | |
| "grad_norm": 0.06539875268936157, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3711, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013374485596707819, | |
| "grad_norm": 0.05985588580369949, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.3711, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01440329218106996, | |
| "grad_norm": 0.05929071828722954, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.3693, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.015432098765432098, | |
| "grad_norm": 0.05690442770719528, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3725, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01646090534979424, | |
| "grad_norm": 0.0646103173494339, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 10.3673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01748971193415638, | |
| "grad_norm": 0.06523853540420532, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.3711, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.018518518518518517, | |
| "grad_norm": 0.059872936457395554, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3699, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01954732510288066, | |
| "grad_norm": 0.07299160957336426, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3705, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0205761316872428, | |
| "grad_norm": 0.0650302916765213, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.3667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021604938271604937, | |
| "grad_norm": 0.07766956835985184, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.371, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02263374485596708, | |
| "grad_norm": 0.07958979904651642, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.3704, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.023662551440329218, | |
| "grad_norm": 0.07455561310052872, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3692, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.024691358024691357, | |
| "grad_norm": 0.05922195315361023, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3689, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0257201646090535, | |
| "grad_norm": 0.08674026280641556, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 10.3688, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0257201646090535, | |
| "eval_loss": 10.371575355529785, | |
| "eval_runtime": 3.8995, | |
| "eval_samples_per_second": 210.026, | |
| "eval_steps_per_second": 105.141, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026748971193415638, | |
| "grad_norm": 0.06006744131445885, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.3693, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.027777777777777776, | |
| "grad_norm": 0.061292968690395355, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3781, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02880658436213992, | |
| "grad_norm": 0.05729150399565697, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 10.3698, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.029835390946502057, | |
| "grad_norm": 0.0738535150885582, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.377, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "grad_norm": 0.08201771229505539, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3743, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03189300411522634, | |
| "grad_norm": 0.06121494248509407, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3732, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03292181069958848, | |
| "grad_norm": 0.06989278644323349, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 10.3769, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.033950617283950615, | |
| "grad_norm": 0.0654149129986763, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3745, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03497942386831276, | |
| "grad_norm": 0.07070856541395187, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 10.3761, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0360082304526749, | |
| "grad_norm": 0.06659887731075287, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3724, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.037037037037037035, | |
| "grad_norm": 0.06675346195697784, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3737, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03806584362139918, | |
| "grad_norm": 0.07385862618684769, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.375, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03909465020576132, | |
| "grad_norm": 0.07189275324344635, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 10.3731, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.040123456790123455, | |
| "grad_norm": 0.06958039849996567, | |
| "learning_rate": 5e-05, | |
| "loss": 10.377, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0411522633744856, | |
| "grad_norm": 0.06426934152841568, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 10.3661, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04218106995884774, | |
| "grad_norm": 0.05699732154607773, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 10.373, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.043209876543209874, | |
| "grad_norm": 0.07567627727985382, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3706, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.044238683127572016, | |
| "grad_norm": 0.06678629666566849, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3735, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04526748971193416, | |
| "grad_norm": 0.07194814831018448, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.3711, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.046296296296296294, | |
| "grad_norm": 0.07632729411125183, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.047325102880658436, | |
| "grad_norm": 0.07104772329330444, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 10.3695, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04835390946502058, | |
| "grad_norm": 0.06831281632184982, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.3702, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04938271604938271, | |
| "grad_norm": 0.06835275888442993, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3736, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.050411522633744855, | |
| "grad_norm": 0.07666638493537903, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 10.3718, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.051440329218107, | |
| "grad_norm": 0.09056751430034637, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.3703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.051440329218107, | |
| "eval_loss": 10.367652893066406, | |
| "eval_runtime": 3.8772, | |
| "eval_samples_per_second": 211.233, | |
| "eval_steps_per_second": 105.745, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05246913580246913, | |
| "grad_norm": 0.061358969658613205, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3722, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.053497942386831275, | |
| "grad_norm": 0.0457032136619091, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.3713, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.05452674897119342, | |
| "grad_norm": 0.08451968431472778, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 10.3633, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.0813678428530693, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3638, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.056584362139917695, | |
| "grad_norm": 0.0976748913526535, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3635, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.05761316872427984, | |
| "grad_norm": 0.08876488357782364, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.3666, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05864197530864197, | |
| "grad_norm": 0.10705621540546417, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.362, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.059670781893004114, | |
| "grad_norm": 0.08955643326044083, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.363, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.060699588477366256, | |
| "grad_norm": 0.09573681652545929, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3604, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06172839506172839, | |
| "grad_norm": 0.09486616402864456, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.367, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06275720164609054, | |
| "grad_norm": 0.10614409297704697, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 10.3655, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.06378600823045268, | |
| "grad_norm": 0.10627195239067078, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3636, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.06481481481481481, | |
| "grad_norm": 0.09814492613077164, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3602, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.06584362139917696, | |
| "grad_norm": 0.10285503417253494, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.3605, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.0668724279835391, | |
| "grad_norm": 0.10218602418899536, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.3639, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.06790123456790123, | |
| "grad_norm": 0.10725147277116776, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3627, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06893004115226338, | |
| "grad_norm": 0.11580110341310501, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.3592, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06995884773662552, | |
| "grad_norm": 0.10592279583215714, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.3645, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.07098765432098765, | |
| "grad_norm": 0.11137183010578156, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3579, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0720164609053498, | |
| "grad_norm": 0.0957491472363472, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.3616, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07304526748971193, | |
| "grad_norm": 0.12764863669872284, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.3658, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 0.11922897398471832, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3637, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.07510288065843622, | |
| "grad_norm": 0.11078738421201706, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.3613, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.07613168724279835, | |
| "grad_norm": 0.10038205981254578, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 10.3676, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.07716049382716049, | |
| "grad_norm": 0.10171519964933395, | |
| "learning_rate": 0.0, | |
| "loss": 10.3676, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07716049382716049, | |
| "eval_loss": 10.366857528686523, | |
| "eval_runtime": 3.8777, | |
| "eval_samples_per_second": 211.206, | |
| "eval_steps_per_second": 105.732, | |
| "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": 8019011174400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |