| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.899601304820587, | |
| "eval_steps": 500, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07249003262051468, | |
| "grad_norm": 0.09461668878793716, | |
| "learning_rate": 0.00019992615059139993, | |
| "loss": 0.7791, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14498006524102935, | |
| "grad_norm": 0.06766393035650253, | |
| "learning_rate": 0.0001993360096097155, | |
| "loss": 0.5521, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21747009786154403, | |
| "grad_norm": 0.0734836608171463, | |
| "learning_rate": 0.00019815921288395655, | |
| "loss": 0.5053, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2899601304820587, | |
| "grad_norm": 0.060219183564186096, | |
| "learning_rate": 0.00019640271030632727, | |
| "loss": 0.4836, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3624501631025734, | |
| "grad_norm": 0.0633341521024704, | |
| "learning_rate": 0.00019407687537915269, | |
| "loss": 0.4692, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43494019572308806, | |
| "grad_norm": 0.06684491038322449, | |
| "learning_rate": 0.0001911954439513476, | |
| "loss": 0.4508, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5074302283436027, | |
| "grad_norm": 0.10767890512943268, | |
| "learning_rate": 0.00018777543309763566, | |
| "loss": 0.4432, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5799202609641174, | |
| "grad_norm": 0.06926553696393967, | |
| "learning_rate": 0.00018383704061959965, | |
| "loss": 0.4313, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6524102935846321, | |
| "grad_norm": 0.0965363085269928, | |
| "learning_rate": 0.00017940352576208688, | |
| "loss": 0.4179, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7249003262051468, | |
| "grad_norm": 0.07616274058818817, | |
| "learning_rate": 0.00017450107184943073, | |
| "loss": 0.4116, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7973903588256614, | |
| "grad_norm": 0.08681479096412659, | |
| "learning_rate": 0.00016915863165272818, | |
| "loss": 0.4044, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8698803914461761, | |
| "grad_norm": 0.07483861595392227, | |
| "learning_rate": 0.00016340775640139835, | |
| "loss": 0.4006, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.9423704240666908, | |
| "grad_norm": 0.0695137232542038, | |
| "learning_rate": 0.00015728240944884046, | |
| "loss": 0.3945, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.0148604566872055, | |
| "grad_norm": 0.09992991387844086, | |
| "learning_rate": 0.00015081876569263987, | |
| "loss": 0.3896, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.0873504893077202, | |
| "grad_norm": 0.058682847768068314, | |
| "learning_rate": 0.00014405499793389992, | |
| "loss": 0.3771, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.1598405219282348, | |
| "grad_norm": 0.054995909333229065, | |
| "learning_rate": 0.0001370310514374126, | |
| "loss": 0.3682, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.2323305545487495, | |
| "grad_norm": 0.08551865816116333, | |
| "learning_rate": 0.00012978840802406474, | |
| "loss": 0.3683, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.3048205871692642, | |
| "grad_norm": 0.06695013493299484, | |
| "learning_rate": 0.0001223698410886949, | |
| "loss": 0.3689, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.3773106197897789, | |
| "grad_norm": 0.0619310662150383, | |
| "learning_rate": 0.00011481916299021028, | |
| "loss": 0.3639, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.4498006524102935, | |
| "grad_norm": 0.05403854325413704, | |
| "learning_rate": 0.00010718096630581976, | |
| "loss": 0.3628, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.5222906850308082, | |
| "grad_norm": 0.08368243277072906, | |
| "learning_rate": 9.950036047747562e-05, | |
| "loss": 0.3612, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.594780717651323, | |
| "grad_norm": 0.05811639130115509, | |
| "learning_rate": 9.182270540583096e-05, | |
| "loss": 0.3624, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.6672707502718376, | |
| "grad_norm": 0.05284130945801735, | |
| "learning_rate": 8.419334356504496e-05, | |
| "loss": 0.3588, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.7397607828923523, | |
| "grad_norm": 0.05519060045480728, | |
| "learning_rate": 7.665733222050506e-05, | |
| "loss": 0.3594, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.812250815512867, | |
| "grad_norm": 0.0576307587325573, | |
| "learning_rate": 6.925917733092715e-05, | |
| "loss": 0.3584, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.8847408481333816, | |
| "grad_norm": 0.06832610815763474, | |
| "learning_rate": 6.204257070634643e-05, | |
| "loss": 0.3556, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.9572308807538963, | |
| "grad_norm": 0.05261433124542236, | |
| "learning_rate": 5.5050131974284314e-05, | |
| "loss": 0.3577, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.029720913374411, | |
| "grad_norm": 0.05833235755562782, | |
| "learning_rate": 4.832315687798013e-05, | |
| "loss": 0.3453, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.102210945994926, | |
| "grad_norm": 0.05576351657509804, | |
| "learning_rate": 4.190137339317991e-05, | |
| "loss": 0.3488, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.1747009786154403, | |
| "grad_norm": 0.05975164473056793, | |
| "learning_rate": 3.5822707103802e-05, | |
| "loss": 0.3448, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 0.05862308666110039, | |
| "learning_rate": 3.0123057222115836e-05, | |
| "loss": 0.3441, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.3196810438564697, | |
| "grad_norm": 0.06690463423728943, | |
| "learning_rate": 2.483608457620823e-05, | |
| "loss": 0.3513, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.3921710764769846, | |
| "grad_norm": 0.0602315217256546, | |
| "learning_rate": 1.99930128168345e-05, | |
| "loss": 0.3441, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.464661109097499, | |
| "grad_norm": 0.05553460866212845, | |
| "learning_rate": 1.562244401768144e-05, | |
| "loss": 0.3444, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.537151141718014, | |
| "grad_norm": 0.05820445343852043, | |
| "learning_rate": 1.1750189758064211e-05, | |
| "loss": 0.3465, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.6096411743385284, | |
| "grad_norm": 0.06841924786567688, | |
| "learning_rate": 8.399118685644858e-06, | |
| "loss": 0.3486, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.6821312069590433, | |
| "grad_norm": 0.06084201857447624, | |
| "learning_rate": 5.589021459431787e-06, | |
| "loss": 0.3426, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.7546212395795577, | |
| "grad_norm": 0.06527499854564667, | |
| "learning_rate": 3.3364938706757275e-06, | |
| "loss": 0.3428, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.8271112722000726, | |
| "grad_norm": 0.06700863689184189, | |
| "learning_rate": 1.6548388319239105e-06, | |
| "loss": 0.3414, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.899601304820587, | |
| "grad_norm": 0.08079268038272858, | |
| "learning_rate": 5.539878130623732e-07, | |
| "loss": 0.3453, | |
| "step": 4000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 4137, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.493402810056704e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |