| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5847953216374269, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007797270955165692, | |
| "grad_norm": 0.2942213714122772, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.3545, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007797270955165692, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.737, | |
| "eval_samples_per_second": 147.901, | |
| "eval_steps_per_second": 74.629, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015594541910331383, | |
| "grad_norm": 0.3197149336338043, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023391812865497075, | |
| "grad_norm": 0.27089622616767883, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3939, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.031189083820662766, | |
| "grad_norm": 0.2828482687473297, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.3962, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03898635477582846, | |
| "grad_norm": 0.33342134952545166, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": 0.3048103153705597, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3606, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05458089668615984, | |
| "grad_norm": 0.3553928732872009, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.4386, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06237816764132553, | |
| "grad_norm": 0.3461388945579529, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.3639, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 0.31583553552627563, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3434, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07797270955165692, | |
| "grad_norm": 0.368663489818573, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.3556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08576998050682261, | |
| "grad_norm": 0.37907612323760986, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.4034, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": 0.38438519835472107, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3928, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10136452241715399, | |
| "grad_norm": 0.4186666011810303, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.4229, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.10916179337231968, | |
| "grad_norm": 0.3805326819419861, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.3638, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 0.446143239736557, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3885, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12475633528265107, | |
| "grad_norm": 0.42059049010276794, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 10.4032, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13255360623781676, | |
| "grad_norm": 0.44713813066482544, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.3868, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 0.5422891974449158, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.4051, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.5048491358757019, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3233, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15594541910331383, | |
| "grad_norm": 0.5079050660133362, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.348, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16374269005847952, | |
| "grad_norm": 0.5826595425605774, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3681, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17153996101364521, | |
| "grad_norm": 0.4828285574913025, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.3418, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1793372319688109, | |
| "grad_norm": 0.6563220024108887, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3172, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1871345029239766, | |
| "grad_norm": 0.6469476222991943, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "grad_norm": 0.5231078267097473, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 10.323, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1949317738791423, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.736, | |
| "eval_samples_per_second": 148.088, | |
| "eval_steps_per_second": 74.723, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20272904483430798, | |
| "grad_norm": 0.803300678730011, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.3143, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.6602361798286438, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3813, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.21832358674463936, | |
| "grad_norm": 0.739231526851654, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 10.3064, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22612085769980506, | |
| "grad_norm": 0.7824051380157471, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.3064, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "grad_norm": 1.0254789590835571, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24171539961013644, | |
| "grad_norm": 0.8810551762580872, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3302, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.24951267056530213, | |
| "grad_norm": 1.4386115074157715, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 10.4164, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2573099415204678, | |
| "grad_norm": 0.4788445234298706, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3391, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2651072124756335, | |
| "grad_norm": 0.47968441247940063, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 10.3176, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2729044834307992, | |
| "grad_norm": 0.5276753902435303, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3632, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.607767641544342, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3526, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2884990253411306, | |
| "grad_norm": 0.6070165634155273, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.2895, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2962962962962963, | |
| "grad_norm": 0.8148685097694397, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 10.3767, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.30409356725146197, | |
| "grad_norm": 0.6928004622459412, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3613, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.31189083820662766, | |
| "grad_norm": 0.647136390209198, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 10.3009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.31968810916179335, | |
| "grad_norm": 0.6418548822402954, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 10.3371, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.32748538011695905, | |
| "grad_norm": 0.6654731631278992, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3056, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.33528265107212474, | |
| "grad_norm": 0.6930279731750488, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.315, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.34307992202729043, | |
| "grad_norm": 0.8335940837860107, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.3535, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.7898197770118713, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3541, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3586744639376218, | |
| "grad_norm": 0.9156711101531982, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 10.3129, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3664717348927875, | |
| "grad_norm": 0.7727612853050232, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.2579, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3742690058479532, | |
| "grad_norm": 0.8964085578918457, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.35, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3820662768031189, | |
| "grad_norm": 0.8759742975234985, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 10.2866, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3898635477582846, | |
| "grad_norm": 0.8049792647361755, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.343, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3898635477582846, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7541, | |
| "eval_samples_per_second": 144.545, | |
| "eval_steps_per_second": 72.936, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39766081871345027, | |
| "grad_norm": 1.0288301706314087, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3383, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.40545808966861596, | |
| "grad_norm": 0.8088068962097168, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.301, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.41325536062378165, | |
| "grad_norm": 1.6339895725250244, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 10.3504, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.6204891800880432, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.2676, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.42884990253411304, | |
| "grad_norm": 0.8382387757301331, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.2947, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.43664717348927873, | |
| "grad_norm": 1.020254373550415, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.2983, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.956863284111023, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3088, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4522417153996101, | |
| "grad_norm": 1.101438283920288, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.2818, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4600389863547758, | |
| "grad_norm": 1.2617967128753662, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3324, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.4678362573099415, | |
| "grad_norm": 1.7285469770431519, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3599, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4756335282651072, | |
| "grad_norm": 1.031049370765686, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 10.2724, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4834307992202729, | |
| "grad_norm": 1.2741031646728516, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3325, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 1.2693265676498413, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3215, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.49902534113060426, | |
| "grad_norm": 1.5057166814804077, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.326, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.50682261208577, | |
| "grad_norm": 0.6832972168922424, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.3157, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5146198830409356, | |
| "grad_norm": 0.9456722736358643, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3463, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5224171539961013, | |
| "grad_norm": 0.7365139722824097, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.3414, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.530214424951267, | |
| "grad_norm": 0.7288162708282471, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.3149, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5380116959064327, | |
| "grad_norm": 1.0187373161315918, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3163, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.5458089668615984, | |
| "grad_norm": 0.978813886642456, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.3537, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5536062378167641, | |
| "grad_norm": 0.6140927672386169, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.3226, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.7399495840072632, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.2881, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5692007797270955, | |
| "grad_norm": 0.6788749694824219, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.2779, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5769980506822612, | |
| "grad_norm": 0.6670129895210266, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 10.2904, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5847953216374269, | |
| "grad_norm": 0.8559417724609375, | |
| "learning_rate": 0.0, | |
| "loss": 10.2837, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5847953216374269, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.7351, | |
| "eval_samples_per_second": 148.283, | |
| "eval_steps_per_second": 74.822, | |
| "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 | |
| } | |