| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 282, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03546099290780142, |
| "grad_norm": 1.3688955307006836, |
| "learning_rate": 9e-05, |
| "loss": 3.273609924316406, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.07092198581560284, |
| "grad_norm": 1.6823779344558716, |
| "learning_rate": 0.00019, |
| "loss": 2.013600540161133, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.10638297872340426, |
| "grad_norm": 1.3549606800079346, |
| "learning_rate": 0.0001994182576820673, |
| "loss": 0.9827978134155273, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.14184397163120568, |
| "grad_norm": 0.704963207244873, |
| "learning_rate": 0.00019741598475167175, |
| "loss": 0.6513552665710449, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.1773049645390071, |
| "grad_norm": 0.5734719038009644, |
| "learning_rate": 0.0001940147464327637, |
| "loss": 0.5401387691497803, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2127659574468085, |
| "grad_norm": 0.7053222060203552, |
| "learning_rate": 0.00018926338701612738, |
| "loss": 0.5485860347747803, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.24822695035460993, |
| "grad_norm": 0.5607346892356873, |
| "learning_rate": 0.00018323013952726875, |
| "loss": 0.5408585071563721, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.28368794326241137, |
| "grad_norm": 0.6696723699569702, |
| "learning_rate": 0.00017600164584984546, |
| "loss": 0.5451176166534424, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.3191489361702128, |
| "grad_norm": 0.6198937892913818, |
| "learning_rate": 0.00016768171248431602, |
| "loss": 0.4622413158416748, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.3546099290780142, |
| "grad_norm": 0.49034929275512695, |
| "learning_rate": 0.00015838981981003273, |
| "loss": 0.5463218688964844, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3900709219858156, |
| "grad_norm": 0.46550455689430237, |
| "learning_rate": 0.00014825940625887342, |
| "loss": 0.45171518325805665, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 0.3953458368778229, |
| "learning_rate": 0.0001374359520409444, |
| "loss": 0.43686976432800295, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.46099290780141844, |
| "grad_norm": 0.4815589487552643, |
| "learning_rate": 0.00012607488994146704, |
| "loss": 0.518321418762207, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.49645390070921985, |
| "grad_norm": 0.37568503618240356, |
| "learning_rate": 0.00011433937319134511, |
| "loss": 0.34571166038513185, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.5319148936170213, |
| "grad_norm": 0.5359418392181396, |
| "learning_rate": 0.00010239793246643819, |
| "loss": 0.48325700759887696, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.5673758865248227, |
| "grad_norm": 0.5425746440887451, |
| "learning_rate": 9.042205566275951e-05, |
| "loss": 0.429827356338501, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.6028368794326241, |
| "grad_norm": 0.5164040923118591, |
| "learning_rate": 7.858372520381119e-05, |
| "loss": 0.4601579189300537, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.6382978723404256, |
| "grad_norm": 0.5248101949691772, |
| "learning_rate": 6.705294824614004e-05, |
| "loss": 0.3804056644439697, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.6737588652482269, |
| "grad_norm": 0.34143301844596863, |
| "learning_rate": 5.5995315251183734e-05, |
| "loss": 0.3424631118774414, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.7092198581560284, |
| "grad_norm": 0.5679530501365662, |
| "learning_rate": 4.556962198411631e-05, |
| "loss": 0.46054668426513673, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.7446808510638298, |
| "grad_norm": 0.46360042691230774, |
| "learning_rate": 3.592558908954295e-05, |
| "loss": 0.41877241134643556, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.7801418439716312, |
| "grad_norm": 0.4703761041164398, |
| "learning_rate": 2.720171199261987e-05, |
| "loss": 0.4663556575775146, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.8156028368794326, |
| "grad_norm": 0.530480146408081, |
| "learning_rate": 1.9523272002603742e-05, |
| "loss": 0.4497820377349854, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 0.48615142703056335, |
| "learning_rate": 1.3000537180852212e-05, |
| "loss": 0.3560842275619507, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.8865248226950354, |
| "grad_norm": 0.4983954131603241, |
| "learning_rate": 7.727178810136093e-06, |
| "loss": 0.45021347999572753, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.9219858156028369, |
| "grad_norm": 0.5884110927581787, |
| "learning_rate": 3.778926205933342e-06, |
| "loss": 0.4234372615814209, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.9574468085106383, |
| "grad_norm": 0.4866378903388977, |
| "learning_rate": 1.212479187605897e-06, |
| "loss": 0.4674375534057617, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.9929078014184397, |
| "grad_norm": 0.4536786377429962, |
| "learning_rate": 6.469382717563255e-08, |
| "loss": 0.4669623374938965, |
| "step": 280 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 282, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3881477709846528.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
