| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.5080113100848256, | |
| "eval_steps": 500, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03770028275212064, | |
| "grad_norm": 2.404820680618286, | |
| "learning_rate": 4.9995083170283816e-05, | |
| "loss": 4.2968, | |
| "num_input_tokens_seen": 51872, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07540056550424128, | |
| "grad_norm": 1.080649971961975, | |
| "learning_rate": 4.998033461515242e-05, | |
| "loss": 3.9725, | |
| "num_input_tokens_seen": 107024, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11310084825636192, | |
| "grad_norm": 2.0493686199188232, | |
| "learning_rate": 4.9955760135896534e-05, | |
| "loss": 3.8314, | |
| "num_input_tokens_seen": 160080, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.15080113100848255, | |
| "grad_norm": 0.927135169506073, | |
| "learning_rate": 4.992136939879856e-05, | |
| "loss": 3.7, | |
| "num_input_tokens_seen": 208816, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1885014137606032, | |
| "grad_norm": 0.9066221714019775, | |
| "learning_rate": 4.9877175931330346e-05, | |
| "loss": 3.6029, | |
| "num_input_tokens_seen": 262448, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22620169651272384, | |
| "grad_norm": 1.361427903175354, | |
| "learning_rate": 4.982319711683221e-05, | |
| "loss": 3.4859, | |
| "num_input_tokens_seen": 315552, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2639019792648445, | |
| "grad_norm": 6.180077075958252, | |
| "learning_rate": 4.975945418767529e-05, | |
| "loss": 3.4653, | |
| "num_input_tokens_seen": 366992, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3016022620169651, | |
| "grad_norm": 1.7034149169921875, | |
| "learning_rate": 4.968597221690986e-05, | |
| "loss": 3.485, | |
| "num_input_tokens_seen": 418816, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3393025447690858, | |
| "grad_norm": 2.64639949798584, | |
| "learning_rate": 4.96027801084029e-05, | |
| "loss": 3.4304, | |
| "num_input_tokens_seen": 469936, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3770028275212064, | |
| "grad_norm": 1.302827000617981, | |
| "learning_rate": 4.950991058546893e-05, | |
| "loss": 3.4635, | |
| "num_input_tokens_seen": 525120, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.41470311027332707, | |
| "grad_norm": 1.5340975522994995, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 3.3626, | |
| "num_input_tokens_seen": 576944, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.4524033930254477, | |
| "grad_norm": 1.2329437732696533, | |
| "learning_rate": 4.929528920808854e-05, | |
| "loss": 3.3347, | |
| "num_input_tokens_seen": 628544, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49010367577756836, | |
| "grad_norm": 1.7281228303909302, | |
| "learning_rate": 4.917362177418342e-05, | |
| "loss": 3.3347, | |
| "num_input_tokens_seen": 681392, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.527803958529689, | |
| "grad_norm": 1.3272786140441895, | |
| "learning_rate": 4.904244573372733e-05, | |
| "loss": 3.3173, | |
| "num_input_tokens_seen": 734928, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.5655042412818096, | |
| "grad_norm": 1.3057860136032104, | |
| "learning_rate": 4.8901812684340564e-05, | |
| "loss": 3.3863, | |
| "num_input_tokens_seen": 785840, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6032045240339302, | |
| "grad_norm": 1.3130522966384888, | |
| "learning_rate": 4.8751777943523634e-05, | |
| "loss": 3.2669, | |
| "num_input_tokens_seen": 838112, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.6409048067860509, | |
| "grad_norm": 1.4002560377120972, | |
| "learning_rate": 4.8592400526898314e-05, | |
| "loss": 3.249, | |
| "num_input_tokens_seen": 886784, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.6786050895381716, | |
| "grad_norm": 1.5897698402404785, | |
| "learning_rate": 4.842374312499405e-05, | |
| "loss": 3.3248, | |
| "num_input_tokens_seen": 936880, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7163053722902922, | |
| "grad_norm": 2.1904706954956055, | |
| "learning_rate": 4.824587207858888e-05, | |
| "loss": 3.1471, | |
| "num_input_tokens_seen": 988864, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.7540056550424128, | |
| "grad_norm": 1.859395980834961, | |
| "learning_rate": 4.805885735261454e-05, | |
| "loss": 3.2406, | |
| "num_input_tokens_seen": 1044400, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.7917059377945335, | |
| "grad_norm": 1.6112860441207886, | |
| "learning_rate": 4.786277250863599e-05, | |
| "loss": 3.1418, | |
| "num_input_tokens_seen": 1097376, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.8294062205466541, | |
| "grad_norm": 1.3354580402374268, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 3.1452, | |
| "num_input_tokens_seen": 1153456, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.8671065032987747, | |
| "grad_norm": 1.9464856386184692, | |
| "learning_rate": 4.744370452107789e-05, | |
| "loss": 3.2019, | |
| "num_input_tokens_seen": 1205536, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9048067860508954, | |
| "grad_norm": 1.3771345615386963, | |
| "learning_rate": 4.722088621637309e-05, | |
| "loss": 3.2528, | |
| "num_input_tokens_seen": 1256080, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.942507068803016, | |
| "grad_norm": 1.5059542655944824, | |
| "learning_rate": 4.698932740657479e-05, | |
| "loss": 3.0824, | |
| "num_input_tokens_seen": 1308592, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.9802073515551367, | |
| "grad_norm": 1.4657851457595825, | |
| "learning_rate": 4.6749119174501975e-05, | |
| "loss": 3.2487, | |
| "num_input_tokens_seen": 1355792, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.0179076343072573, | |
| "grad_norm": 1.5458085536956787, | |
| "learning_rate": 4.6500356005192514e-05, | |
| "loss": 3.12, | |
| "num_input_tokens_seen": 1402560, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.055607917059378, | |
| "grad_norm": 1.4856982231140137, | |
| "learning_rate": 4.6243135748737864e-05, | |
| "loss": 3.1617, | |
| "num_input_tokens_seen": 1453152, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.0933081998114986, | |
| "grad_norm": 1.728014588356018, | |
| "learning_rate": 4.597755958179406e-05, | |
| "loss": 3.0912, | |
| "num_input_tokens_seen": 1505744, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.1310084825636193, | |
| "grad_norm": 1.727301836013794, | |
| "learning_rate": 4.570373196778427e-05, | |
| "loss": 2.9448, | |
| "num_input_tokens_seen": 1559264, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.1687087653157398, | |
| "grad_norm": 1.8649897575378418, | |
| "learning_rate": 4.5421760615808474e-05, | |
| "loss": 3.1383, | |
| "num_input_tokens_seen": 1604368, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.2064090480678604, | |
| "grad_norm": 1.8682725429534912, | |
| "learning_rate": 4.513175643827647e-05, | |
| "loss": 3.0526, | |
| "num_input_tokens_seen": 1657168, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.244109330819981, | |
| "grad_norm": 1.723254680633545, | |
| "learning_rate": 4.4833833507280884e-05, | |
| "loss": 3.0386, | |
| "num_input_tokens_seen": 1704960, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.2818096135721018, | |
| "grad_norm": 1.6712509393692017, | |
| "learning_rate": 4.4528109009727336e-05, | |
| "loss": 2.9411, | |
| "num_input_tokens_seen": 1756400, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.3195098963242224, | |
| "grad_norm": 2.0004794597625732, | |
| "learning_rate": 4.42147032012394e-05, | |
| "loss": 3.1312, | |
| "num_input_tokens_seen": 1806976, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.3572101790763431, | |
| "grad_norm": 1.872934103012085, | |
| "learning_rate": 4.389373935885646e-05, | |
| "loss": 3.0785, | |
| "num_input_tokens_seen": 1861264, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.3949104618284638, | |
| "grad_norm": 1.8472355604171753, | |
| "learning_rate": 4.356534373254316e-05, | |
| "loss": 3.0567, | |
| "num_input_tokens_seen": 1917872, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.4326107445805842, | |
| "grad_norm": 2.1023237705230713, | |
| "learning_rate": 4.322964549552943e-05, | |
| "loss": 3.0526, | |
| "num_input_tokens_seen": 1971888, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.4703110273327051, | |
| "grad_norm": 1.9663615226745605, | |
| "learning_rate": 4.288677669350066e-05, | |
| "loss": 3.0147, | |
| "num_input_tokens_seen": 2022112, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.5080113100848256, | |
| "grad_norm": 2.509061574935913, | |
| "learning_rate": 4.2536872192658036e-05, | |
| "loss": 3.0681, | |
| "num_input_tokens_seen": 2073088, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 792, | |
| "num_input_tokens_seen": 2073088, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.819916695771546e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |