| { | |
| "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": 0.06301224231719971, | |
| "learning_rate": 0.00019992615059139993, | |
| "loss": 0.7675, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14498006524102935, | |
| "grad_norm": 0.10580525547266006, | |
| "learning_rate": 0.0001993360096097155, | |
| "loss": 0.5641, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.21747009786154403, | |
| "grad_norm": 0.07278159260749817, | |
| "learning_rate": 0.00019815921288395655, | |
| "loss": 0.5124, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2899601304820587, | |
| "grad_norm": 0.07537836581468582, | |
| "learning_rate": 0.00019640271030632727, | |
| "loss": 0.4841, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3624501631025734, | |
| "grad_norm": 0.09485650062561035, | |
| "learning_rate": 0.00019407687537915269, | |
| "loss": 0.4602, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.43494019572308806, | |
| "grad_norm": 0.07589354366064072, | |
| "learning_rate": 0.0001911954439513476, | |
| "loss": 0.4577, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5074302283436027, | |
| "grad_norm": 0.0784345343708992, | |
| "learning_rate": 0.00018777543309763566, | |
| "loss": 0.4435, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5799202609641174, | |
| "grad_norm": 0.13163290917873383, | |
| "learning_rate": 0.00018383704061959965, | |
| "loss": 0.4362, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6524102935846321, | |
| "grad_norm": 0.10098472982645035, | |
| "learning_rate": 0.00017940352576208688, | |
| "loss": 0.4244, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.7249003262051468, | |
| "grad_norm": 0.08392923325300217, | |
| "learning_rate": 0.00017450107184943073, | |
| "loss": 0.4194, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7973903588256614, | |
| "grad_norm": 0.08855585008859634, | |
| "learning_rate": 0.00016915863165272818, | |
| "loss": 0.401, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8698803914461761, | |
| "grad_norm": 0.07977194339036942, | |
| "learning_rate": 0.00016340775640139835, | |
| "loss": 0.401, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.9423704240666908, | |
| "grad_norm": 0.049693815410137177, | |
| "learning_rate": 0.00015728240944884046, | |
| "loss": 0.3995, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.0148604566872055, | |
| "grad_norm": 0.05138128623366356, | |
| "learning_rate": 0.00015081876569263987, | |
| "loss": 0.3858, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.0873504893077202, | |
| "grad_norm": 0.09676031768321991, | |
| "learning_rate": 0.00014405499793389992, | |
| "loss": 0.3771, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.1598405219282348, | |
| "grad_norm": 0.08200570940971375, | |
| "learning_rate": 0.0001370310514374126, | |
| "loss": 0.3714, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.2323305545487495, | |
| "grad_norm": 0.0593099370598793, | |
| "learning_rate": 0.00012978840802406474, | |
| "loss": 0.3689, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.3048205871692642, | |
| "grad_norm": 0.07377779483795166, | |
| "learning_rate": 0.0001223698410886949, | |
| "loss": 0.3683, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.3773106197897789, | |
| "grad_norm": 0.07046964764595032, | |
| "learning_rate": 0.00011481916299021028, | |
| "loss": 0.3655, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.4498006524102935, | |
| "grad_norm": 0.054052457213401794, | |
| "learning_rate": 0.00010718096630581976, | |
| "loss": 0.3662, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.5222906850308082, | |
| "grad_norm": 0.05863339453935623, | |
| "learning_rate": 9.950036047747562e-05, | |
| "loss": 0.3631, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.594780717651323, | |
| "grad_norm": 0.07018906623125076, | |
| "learning_rate": 9.182270540583096e-05, | |
| "loss": 0.3625, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.6672707502718376, | |
| "grad_norm": 0.07417762279510498, | |
| "learning_rate": 8.419334356504496e-05, | |
| "loss": 0.362, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.7397607828923523, | |
| "grad_norm": 0.06391692906618118, | |
| "learning_rate": 7.665733222050506e-05, | |
| "loss": 0.3621, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.812250815512867, | |
| "grad_norm": 0.05379035323858261, | |
| "learning_rate": 6.925917733092715e-05, | |
| "loss": 0.3549, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.8847408481333816, | |
| "grad_norm": 0.06350132077932358, | |
| "learning_rate": 6.204257070634643e-05, | |
| "loss": 0.3564, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.9572308807538963, | |
| "grad_norm": 0.07076149433851242, | |
| "learning_rate": 5.5050131974284314e-05, | |
| "loss": 0.3543, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.029720913374411, | |
| "grad_norm": 0.07655489444732666, | |
| "learning_rate": 4.832315687798013e-05, | |
| "loss": 0.3538, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.102210945994926, | |
| "grad_norm": 0.0633474811911583, | |
| "learning_rate": 4.190137339317991e-05, | |
| "loss": 0.345, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.1747009786154403, | |
| "grad_norm": 0.05732415243983269, | |
| "learning_rate": 3.5822707103802e-05, | |
| "loss": 0.3409, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.247191011235955, | |
| "grad_norm": 0.059786632657051086, | |
| "learning_rate": 3.0123057222115836e-05, | |
| "loss": 0.3481, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.3196810438564697, | |
| "grad_norm": 0.06117291748523712, | |
| "learning_rate": 2.483608457620823e-05, | |
| "loss": 0.3483, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.3921710764769846, | |
| "grad_norm": 0.06071442365646362, | |
| "learning_rate": 1.99930128168345e-05, | |
| "loss": 0.342, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.464661109097499, | |
| "grad_norm": 0.05658793821930885, | |
| "learning_rate": 1.562244401768144e-05, | |
| "loss": 0.3386, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.537151141718014, | |
| "grad_norm": 0.0743192508816719, | |
| "learning_rate": 1.1750189758064211e-05, | |
| "loss": 0.3465, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.6096411743385284, | |
| "grad_norm": 0.05902181193232536, | |
| "learning_rate": 8.399118685644858e-06, | |
| "loss": 0.3501, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.6821312069590433, | |
| "grad_norm": 0.07102780789136887, | |
| "learning_rate": 5.589021459431787e-06, | |
| "loss": 0.3427, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.7546212395795577, | |
| "grad_norm": 0.05868164449930191, | |
| "learning_rate": 3.3364938706757275e-06, | |
| "loss": 0.3486, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.8271112722000726, | |
| "grad_norm": 0.06294699013233185, | |
| "learning_rate": 1.6548388319239105e-06, | |
| "loss": 0.3454, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.899601304820587, | |
| "grad_norm": 0.06135398522019386, | |
| "learning_rate": 5.539878130623732e-07, | |
| "loss": 0.3456, | |
| "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 | |
| } | |