| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9979123173277662, | |
| "eval_steps": 500, | |
| "global_step": 239, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0041753653444676405, | |
| "grad_norm": 246.54318237304688, | |
| "learning_rate": 1.2499999999999999e-05, | |
| "loss": 61.2653, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020876826722338204, | |
| "grad_norm": 167.91546630859375, | |
| "learning_rate": 6.25e-05, | |
| "loss": 57.2994, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04175365344467641, | |
| "grad_norm": 55.05445098876953, | |
| "learning_rate": 0.000125, | |
| "loss": 39.4333, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06263048016701461, | |
| "grad_norm": 11.497955322265625, | |
| "learning_rate": 0.00018749999999999998, | |
| "loss": 28.8784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08350730688935282, | |
| "grad_norm": 5.737508296966553, | |
| "learning_rate": 0.00025, | |
| "loss": 26.1913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10438413361169102, | |
| "grad_norm": 7.255920886993408, | |
| "learning_rate": 0.0002999839868651235, | |
| "loss": 24.3236, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12526096033402923, | |
| "grad_norm": 15.379908561706543, | |
| "learning_rate": 0.000299423886051382, | |
| "loss": 21.9388, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14613778705636743, | |
| "grad_norm": 33.49028015136719, | |
| "learning_rate": 0.0002980665441538907, | |
| "loss": 17.5803, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16701461377870563, | |
| "grad_norm": 26.615882873535156, | |
| "learning_rate": 0.0002959192031789579, | |
| "loss": 9.5405, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18789144050104384, | |
| "grad_norm": 11.625475883483887, | |
| "learning_rate": 0.00029299332011978107, | |
| "loss": 4.2328, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.20876826722338204, | |
| "grad_norm": 7.6320953369140625, | |
| "learning_rate": 0.0002893045058284311, | |
| "loss": 3.3569, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22964509394572025, | |
| "grad_norm": 3.013658046722412, | |
| "learning_rate": 0.00028487244172520246, | |
| "loss": 2.6923, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.25052192066805845, | |
| "grad_norm": 1.2317618131637573, | |
| "learning_rate": 0.0002797207747897198, | |
| "loss": 2.3357, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.27139874739039666, | |
| "grad_norm": 1.4713289737701416, | |
| "learning_rate": 0.0002738769913940706, | |
| "loss": 2.1407, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29227557411273486, | |
| "grad_norm": 2.603315830230713, | |
| "learning_rate": 0.0002673722706511174, | |
| "loss": 2.0293, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.31315240083507306, | |
| "grad_norm": 1.713528037071228, | |
| "learning_rate": 0.0002602413180604401, | |
| "loss": 1.9588, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.33402922755741127, | |
| "grad_norm": 1.0197381973266602, | |
| "learning_rate": 0.00025252218033947993, | |
| "loss": 1.8649, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.35490605427974947, | |
| "grad_norm": 1.7586902379989624, | |
| "learning_rate": 0.0002442560424278399, | |
| "loss": 1.8165, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3757828810020877, | |
| "grad_norm": 0.7099477052688599, | |
| "learning_rate": 0.00023548700774781242, | |
| "loss": 1.7875, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3966597077244259, | |
| "grad_norm": 1.7081629037857056, | |
| "learning_rate": 0.00022626186289353913, | |
| "loss": 1.7534, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4175365344467641, | |
| "grad_norm": 1.0658154487609863, | |
| "learning_rate": 0.0002166298280042877, | |
| "loss": 1.7108, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4384133611691023, | |
| "grad_norm": 2.1622581481933594, | |
| "learning_rate": 0.00020664229415371266, | |
| "loss": 1.6766, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4592901878914405, | |
| "grad_norm": 1.4109694957733154, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 1.6531, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4801670146137787, | |
| "grad_norm": 1.4766782522201538, | |
| "learning_rate": 0.00018581549325353126, | |
| "loss": 1.6751, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5010438413361169, | |
| "grad_norm": 1.5826843976974487, | |
| "learning_rate": 0.00017508734619791966, | |
| "loss": 1.6815, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5219206680584552, | |
| "grad_norm": 3.7113709449768066, | |
| "learning_rate": 0.00016422534729572738, | |
| "loss": 1.6347, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5427974947807933, | |
| "grad_norm": 3.043349504470825, | |
| "learning_rate": 0.0001532874500107902, | |
| "loss": 1.6568, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5636743215031316, | |
| "grad_norm": 1.7148481607437134, | |
| "learning_rate": 0.00014233201275765494, | |
| "loss": 1.6368, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5845511482254697, | |
| "grad_norm": 1.1068930625915527, | |
| "learning_rate": 0.0001314174875341878, | |
| "loss": 1.6307, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.605427974947808, | |
| "grad_norm": 1.1382430791854858, | |
| "learning_rate": 0.00012060210805487529, | |
| "loss": 1.6002, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6263048016701461, | |
| "grad_norm": 2.5895371437072754, | |
| "learning_rate": 0.00010994357904876106, | |
| "loss": 1.6034, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6471816283924844, | |
| "grad_norm": 1.033100962638855, | |
| "learning_rate": 9.949876837974944e-05, | |
| "loss": 1.5718, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6680584551148225, | |
| "grad_norm": 1.1252257823944092, | |
| "learning_rate": 8.932340363194595e-05, | |
| "loss": 1.5784, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6889352818371608, | |
| "grad_norm": 0.9897239208221436, | |
| "learning_rate": 7.947177477888472e-05, | |
| "loss": 1.5788, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7098121085594989, | |
| "grad_norm": 0.583287239074707, | |
| "learning_rate": 6.999644452302975e-05, | |
| "loss": 1.5694, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7306889352818372, | |
| "grad_norm": 0.5677323341369629, | |
| "learning_rate": 6.0947967851014405e-05, | |
| "loss": 1.5585, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7515657620041754, | |
| "grad_norm": 0.8589930534362793, | |
| "learning_rate": 5.237462230091467e-05, | |
| "loss": 1.5493, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7724425887265136, | |
| "grad_norm": 0.8215327858924866, | |
| "learning_rate": 4.432215038069449e-05, | |
| "loss": 1.5355, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.7933194154488518, | |
| "grad_norm": 1.1147032976150513, | |
| "learning_rate": 3.6833515512134606e-05, | |
| "loss": 1.5415, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.81419624217119, | |
| "grad_norm": 0.535895049571991, | |
| "learning_rate": 2.9948672802388135e-05, | |
| "loss": 1.5408, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8350730688935282, | |
| "grad_norm": 0.9226528406143188, | |
| "learning_rate": 2.3704355866196373e-05, | |
| "loss": 1.5579, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8559498956158664, | |
| "grad_norm": 0.6188579201698303, | |
| "learning_rate": 1.813388083616068e-05, | |
| "loss": 1.5622, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8768267223382046, | |
| "grad_norm": 0.8158935904502869, | |
| "learning_rate": 1.326696860675981e-05, | |
| "loss": 1.5408, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8977035490605428, | |
| "grad_norm": 0.7256779074668884, | |
| "learning_rate": 9.129586260518634e-06, | |
| "loss": 1.5425, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.918580375782881, | |
| "grad_norm": 0.6823407411575317, | |
| "learning_rate": 5.743808522387544e-06, | |
| "loss": 1.5164, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9394572025052192, | |
| "grad_norm": 0.5680382251739502, | |
| "learning_rate": 3.1276999815337544e-06, | |
| "loss": 1.5424, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9603340292275574, | |
| "grad_norm": 0.7831110954284668, | |
| "learning_rate": 1.2952187089419642e-06, | |
| "loss": 1.5414, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9812108559498957, | |
| "grad_norm": 0.7384339570999146, | |
| "learning_rate": 2.5614178506644934e-07, | |
| "loss": 1.5231, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.9979123173277662, | |
| "eval_loss": 2.1233069896698, | |
| "eval_runtime": 1.3241, | |
| "eval_samples_per_second": 1.511, | |
| "eval_steps_per_second": 0.755, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.9979123173277662, | |
| "step": 239, | |
| "total_flos": 3.643769119309824e+17, | |
| "train_loss": 6.227835292097914, | |
| "train_runtime": 3162.5403, | |
| "train_samples_per_second": 2.42, | |
| "train_steps_per_second": 0.076 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 239, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.643769119309824e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |