| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.33860045146726864, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004514672686230248, | |
| "grad_norm": 0.2097034901380539, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 10.373, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004514672686230248, | |
| "eval_loss": 10.375733375549316, | |
| "eval_runtime": 0.8437, | |
| "eval_samples_per_second": 885.415, | |
| "eval_steps_per_second": 111.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009029345372460496, | |
| "grad_norm": 0.2812159061431885, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 10.3854, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013544018058690745, | |
| "grad_norm": 0.26076751947402954, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01805869074492099, | |
| "grad_norm": 0.29294630885124207, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 10.3729, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.022573363431151242, | |
| "grad_norm": 0.32354286313056946, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 10.3737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02708803611738149, | |
| "grad_norm": 0.3050222396850586, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03160270880361174, | |
| "grad_norm": 0.3262760043144226, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3741, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03611738148984198, | |
| "grad_norm": 0.3407396078109741, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 10.3659, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.040632054176072234, | |
| "grad_norm": 0.3092776834964752, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3737, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.045146726862302484, | |
| "grad_norm": 0.3717252016067505, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 10.3749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04966139954853273, | |
| "grad_norm": 0.3295835256576538, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3654, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05417607223476298, | |
| "grad_norm": 0.3482324779033661, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3798, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05869074492099323, | |
| "grad_norm": 0.26642000675201416, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 10.3821, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06320541760722348, | |
| "grad_norm": 0.27966997027397156, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 10.3704, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06772009029345373, | |
| "grad_norm": 0.2982044219970703, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3582, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07223476297968397, | |
| "grad_norm": 0.3566233515739441, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 10.3664, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07674943566591422, | |
| "grad_norm": 0.38742393255233765, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 10.3639, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08126410835214447, | |
| "grad_norm": 0.37786632776260376, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3614, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08577878103837472, | |
| "grad_norm": 0.3594924211502075, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3551, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09029345372460497, | |
| "grad_norm": 0.44353124499320984, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 10.3685, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09480812641083522, | |
| "grad_norm": 0.45142099261283875, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3599, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09932279909706546, | |
| "grad_norm": 0.4849018156528473, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 10.3541, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.1038374717832957, | |
| "grad_norm": 0.3611159324645996, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.3518, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10835214446952596, | |
| "grad_norm": 0.34617334604263306, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3578, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "grad_norm": 0.41652998328208923, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 10.3594, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11286681715575621, | |
| "eval_loss": 10.347956657409668, | |
| "eval_runtime": 0.8398, | |
| "eval_samples_per_second": 889.453, | |
| "eval_steps_per_second": 111.926, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11738148984198646, | |
| "grad_norm": 0.3440849781036377, | |
| "learning_rate": 7.68649804173412e-05, | |
| "loss": 10.3604, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12189616252821671, | |
| "grad_norm": 0.46047431230545044, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3535, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.12641083521444696, | |
| "grad_norm": 0.4075244069099426, | |
| "learning_rate": 7.308743066175172e-05, | |
| "loss": 10.3506, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1309255079006772, | |
| "grad_norm": 0.3751038610935211, | |
| "learning_rate": 7.113091308703498e-05, | |
| "loss": 10.3532, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.13544018058690746, | |
| "grad_norm": 0.4397486448287964, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3374, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1399548532731377, | |
| "grad_norm": 0.5865473747253418, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3264, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.14446952595936793, | |
| "grad_norm": 0.4633133113384247, | |
| "learning_rate": 6.503528997521366e-05, | |
| "loss": 10.3369, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1489841986455982, | |
| "grad_norm": 0.5107329487800598, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3342, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15349887133182843, | |
| "grad_norm": 0.47929638624191284, | |
| "learning_rate": 6.0821980696905146e-05, | |
| "loss": 10.34, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1580135440180587, | |
| "grad_norm": 0.4484359920024872, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3541, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16252821670428894, | |
| "grad_norm": 0.42778682708740234, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.353, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.1670428893905192, | |
| "grad_norm": 0.4300452768802643, | |
| "learning_rate": 5.435778713738292e-05, | |
| "loss": 10.3391, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17155756207674944, | |
| "grad_norm": 0.45499032735824585, | |
| "learning_rate": 5.218096936826681e-05, | |
| "loss": 10.3304, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.17607223476297967, | |
| "grad_norm": 0.5377456545829773, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3295, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18058690744920994, | |
| "grad_norm": 0.49316221475601196, | |
| "learning_rate": 4.781903063173321e-05, | |
| "loss": 10.3386, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18510158013544017, | |
| "grad_norm": 0.5076413750648499, | |
| "learning_rate": 4.564221286261709e-05, | |
| "loss": 10.3365, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.18961625282167044, | |
| "grad_norm": 0.4477654993534088, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3443, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.19413092550790068, | |
| "grad_norm": 0.5417852997779846, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 10.3234, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1986455981941309, | |
| "grad_norm": 0.4367150366306305, | |
| "learning_rate": 3.917801930309486e-05, | |
| "loss": 10.3257, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20316027088036118, | |
| "grad_norm": 0.45080235600471497, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3438, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2076749435665914, | |
| "grad_norm": 0.5051379203796387, | |
| "learning_rate": 3.4964710024786354e-05, | |
| "loss": 10.3313, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21218961625282168, | |
| "grad_norm": 0.44620585441589355, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 10.3198, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.21670428893905191, | |
| "grad_norm": 0.40200865268707275, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3412, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22121896162528218, | |
| "grad_norm": 0.4732573330402374, | |
| "learning_rate": 2.886908691296504e-05, | |
| "loss": 10.3381, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "grad_norm": 0.5160777568817139, | |
| "learning_rate": 2.6912569338248315e-05, | |
| "loss": 10.3322, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22573363431151242, | |
| "eval_loss": 10.320771217346191, | |
| "eval_runtime": 0.8387, | |
| "eval_samples_per_second": 890.713, | |
| "eval_steps_per_second": 112.084, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23024830699774265, | |
| "grad_norm": 0.3788678050041199, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3373, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.23476297968397292, | |
| "grad_norm": 0.5251423120498657, | |
| "learning_rate": 2.3135019582658802e-05, | |
| "loss": 10.3287, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.23927765237020315, | |
| "grad_norm": 0.47069135308265686, | |
| "learning_rate": 2.132117818244771e-05, | |
| "loss": 10.3243, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.24379232505643342, | |
| "grad_norm": 0.5533862113952637, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3245, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.24830699774266365, | |
| "grad_norm": 0.49693864583969116, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 10.3315, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2528216704288939, | |
| "grad_norm": 0.4767528176307678, | |
| "learning_rate": 1.622048961921699e-05, | |
| "loss": 10.3282, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.25733634311512416, | |
| "grad_norm": 0.5245794057846069, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3109, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2618510158013544, | |
| "grad_norm": 0.528092622756958, | |
| "learning_rate": 1.3136133159493802e-05, | |
| "loss": 10.3253, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.26636568848758463, | |
| "grad_norm": 0.48516395688056946, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 10.3179, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2708803611738149, | |
| "grad_norm": 0.5142610669136047, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3337, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27539503386004516, | |
| "grad_norm": 0.46665993332862854, | |
| "learning_rate": 9.042397785550405e-06, | |
| "loss": 10.3302, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2799097065462754, | |
| "grad_norm": 0.4745612144470215, | |
| "learning_rate": 7.830427709355725e-06, | |
| "loss": 10.3278, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.28442437923250563, | |
| "grad_norm": 0.47112610936164856, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3299, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.28893905191873587, | |
| "grad_norm": 0.4482511281967163, | |
| "learning_rate": 5.649458341088915e-06, | |
| "loss": 10.3211, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.29345372460496616, | |
| "grad_norm": 0.41518616676330566, | |
| "learning_rate": 4.684610648167503e-06, | |
| "loss": 10.3289, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2979683972911964, | |
| "grad_norm": 0.5024863481521606, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3281, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.30248306997742663, | |
| "grad_norm": 0.48448967933654785, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 10.3213, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.30699774266365687, | |
| "grad_norm": 0.5250627994537354, | |
| "learning_rate": 2.314152462588659e-06, | |
| "loss": 10.3258, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3115124153498871, | |
| "grad_norm": 0.5482112765312195, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3122, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3160270880361174, | |
| "grad_norm": 0.5217831134796143, | |
| "learning_rate": 1.1851996440033319e-06, | |
| "loss": 10.3159, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.32054176072234764, | |
| "grad_norm": 0.4971349537372589, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 10.3243, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.32505643340857787, | |
| "grad_norm": 0.5446459054946899, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3197, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3295711060948081, | |
| "grad_norm": 0.4364243149757385, | |
| "learning_rate": 1.9026509541272275e-07, | |
| "loss": 10.3398, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3340857787810384, | |
| "grad_norm": 0.38337594270706177, | |
| "learning_rate": 4.7588920907110094e-08, | |
| "loss": 10.3286, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.33860045146726864, | |
| "grad_norm": 0.5091402530670166, | |
| "learning_rate": 0.0, | |
| "loss": 10.3228, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.33860045146726864, | |
| "eval_loss": 10.315568923950195, | |
| "eval_runtime": 0.831, | |
| "eval_samples_per_second": 898.891, | |
| "eval_steps_per_second": 113.114, | |
| "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": 32076044697600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |