| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.272408527964712, | |
| "eval_steps": 500, | |
| "global_step": 22500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028205562136853386, | |
| "grad_norm": 0.20581459999084473, | |
| "learning_rate": 4.929486094657867e-05, | |
| "loss": 2.15, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05641112427370677, | |
| "grad_norm": 0.14948038756847382, | |
| "learning_rate": 4.858972189315733e-05, | |
| "loss": 0.0702, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.08461668641056017, | |
| "grad_norm": 0.18362277746200562, | |
| "learning_rate": 4.7884582839736e-05, | |
| "loss": 0.0657, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.11282224854741355, | |
| "grad_norm": 0.13676001131534576, | |
| "learning_rate": 4.7179443786314666e-05, | |
| "loss": 0.0647, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.14102781068426692, | |
| "grad_norm": 0.1710374653339386, | |
| "learning_rate": 4.6474304732893334e-05, | |
| "loss": 0.0641, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.16923337282112033, | |
| "grad_norm": 0.10585477948188782, | |
| "learning_rate": 4.5769165679471995e-05, | |
| "loss": 0.0645, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.1974389349579737, | |
| "grad_norm": 0.10310818254947662, | |
| "learning_rate": 4.506402662605066e-05, | |
| "loss": 0.063, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2256444970948271, | |
| "grad_norm": 0.12138450145721436, | |
| "learning_rate": 4.4358887572629323e-05, | |
| "loss": 0.063, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.25385005923168047, | |
| "grad_norm": 0.11205188930034637, | |
| "learning_rate": 4.3653748519207984e-05, | |
| "loss": 0.0616, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.28205562136853385, | |
| "grad_norm": 0.11399635672569275, | |
| "learning_rate": 4.294860946578665e-05, | |
| "loss": 0.0624, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3102611835053873, | |
| "grad_norm": 0.11061274260282516, | |
| "learning_rate": 4.224347041236532e-05, | |
| "loss": 0.0631, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.33846674564224066, | |
| "grad_norm": 0.08492901921272278, | |
| "learning_rate": 4.153833135894399e-05, | |
| "loss": 0.0615, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.36667230777909404, | |
| "grad_norm": 0.09080592542886734, | |
| "learning_rate": 4.083319230552265e-05, | |
| "loss": 0.0616, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.3948778699159474, | |
| "grad_norm": 0.09771362692117691, | |
| "learning_rate": 4.0128053252101316e-05, | |
| "loss": 0.0616, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.4230834320528008, | |
| "grad_norm": 0.09805440902709961, | |
| "learning_rate": 3.9422914198679984e-05, | |
| "loss": 0.0621, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.4512889941896542, | |
| "grad_norm": 0.11397408694028854, | |
| "learning_rate": 3.8717775145258645e-05, | |
| "loss": 0.0605, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.4794945563265076, | |
| "grad_norm": 0.10463790595531464, | |
| "learning_rate": 3.801263609183731e-05, | |
| "loss": 0.0618, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.5077001184633609, | |
| "grad_norm": 0.09112311899662018, | |
| "learning_rate": 3.730749703841598e-05, | |
| "loss": 0.061, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.5359056806002144, | |
| "grad_norm": 0.09545386582612991, | |
| "learning_rate": 3.660235798499465e-05, | |
| "loss": 0.0604, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.5641112427370677, | |
| "grad_norm": 0.08686262369155884, | |
| "learning_rate": 3.589721893157331e-05, | |
| "loss": 0.0605, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.5923168048739211, | |
| "grad_norm": 0.09380181133747101, | |
| "learning_rate": 3.5192079878151976e-05, | |
| "loss": 0.0612, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.6205223670107746, | |
| "grad_norm": 0.10441367328166962, | |
| "learning_rate": 3.448694082473064e-05, | |
| "loss": 0.0611, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.6487279291476279, | |
| "grad_norm": 0.11171282082796097, | |
| "learning_rate": 3.3781801771309305e-05, | |
| "loss": 0.0611, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.6769334912844813, | |
| "grad_norm": 0.08861543238162994, | |
| "learning_rate": 3.3076662717887966e-05, | |
| "loss": 0.0602, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7051390534213346, | |
| "grad_norm": 0.09776312112808228, | |
| "learning_rate": 3.237152366446663e-05, | |
| "loss": 0.0597, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.7333446155581881, | |
| "grad_norm": 0.10567035526037216, | |
| "learning_rate": 3.16663846110453e-05, | |
| "loss": 0.0607, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.7615501776950414, | |
| "grad_norm": 0.08531802147626877, | |
| "learning_rate": 3.096124555762396e-05, | |
| "loss": 0.0602, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.7897557398318948, | |
| "grad_norm": 0.08937925100326538, | |
| "learning_rate": 3.025610650420263e-05, | |
| "loss": 0.0606, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.8179613019687483, | |
| "grad_norm": 0.0823800340294838, | |
| "learning_rate": 2.9550967450781297e-05, | |
| "loss": 0.0602, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.8461668641056016, | |
| "grad_norm": 0.09639054536819458, | |
| "learning_rate": 2.8845828397359958e-05, | |
| "loss": 0.0603, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.874372426242455, | |
| "grad_norm": 0.08088058978319168, | |
| "learning_rate": 2.8140689343938626e-05, | |
| "loss": 0.0609, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.9025779883793084, | |
| "grad_norm": 0.06688382476568222, | |
| "learning_rate": 2.7435550290517293e-05, | |
| "loss": 0.06, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.9307835505161618, | |
| "grad_norm": 0.07398771494626999, | |
| "learning_rate": 2.6730411237095958e-05, | |
| "loss": 0.0603, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.9613753322400045, | |
| "grad_norm": 0.08878236263990402, | |
| "learning_rate": 2.596561669399989e-05, | |
| "loss": 0.0579, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.989651077305887, | |
| "grad_norm": 0.0783604308962822, | |
| "learning_rate": 2.5258723067352823e-05, | |
| "loss": 0.0593, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.0179268223717695, | |
| "grad_norm": 0.10440826416015625, | |
| "learning_rate": 2.4551829440705764e-05, | |
| "loss": 0.0583, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.046202567437652, | |
| "grad_norm": 0.11020490527153015, | |
| "learning_rate": 2.3844935814058702e-05, | |
| "loss": 0.0596, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.0744783125035344, | |
| "grad_norm": 0.09160757064819336, | |
| "learning_rate": 2.313804218741164e-05, | |
| "loss": 0.0587, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.102754057569417, | |
| "grad_norm": 0.10222485661506653, | |
| "learning_rate": 2.2431148560764577e-05, | |
| "loss": 0.0592, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.1310298026352994, | |
| "grad_norm": 0.09362111240625381, | |
| "learning_rate": 2.1724254934117515e-05, | |
| "loss": 0.0594, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.159305547701182, | |
| "grad_norm": 0.0931045264005661, | |
| "learning_rate": 2.1017361307470452e-05, | |
| "loss": 0.0596, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.1875812927670644, | |
| "grad_norm": 0.0950915515422821, | |
| "learning_rate": 2.0310467680823393e-05, | |
| "loss": 0.0592, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.215857037832947, | |
| "grad_norm": 0.09537334740161896, | |
| "learning_rate": 1.960357405417633e-05, | |
| "loss": 0.0591, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.2441327828988293, | |
| "grad_norm": 0.08932538330554962, | |
| "learning_rate": 1.889668042752927e-05, | |
| "loss": 0.059, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.272408527964712, | |
| "grad_norm": 0.07329034805297852, | |
| "learning_rate": 1.8189786800882206e-05, | |
| "loss": 0.0592, | |
| "step": 22500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 35366, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 1500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |