| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 5746, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01740341106856944, | |
| "grad_norm": 0.046589791774749756, | |
| "learning_rate": 4.351610095735422e-07, | |
| "loss": 2.7999, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03480682213713888, | |
| "grad_norm": 0.04616040736436844, | |
| "learning_rate": 8.703220191470844e-07, | |
| "loss": 2.7996, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05221023320570832, | |
| "grad_norm": 0.05549981817603111, | |
| "learning_rate": 1.305483028720627e-06, | |
| "loss": 2.797, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.06961364427427776, | |
| "grad_norm": 0.063571035861969, | |
| "learning_rate": 1.7406440382941688e-06, | |
| "loss": 2.7909, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0870170553428472, | |
| "grad_norm": 0.08422163128852844, | |
| "learning_rate": 2.1758050478677113e-06, | |
| "loss": 2.7951, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10442046641141664, | |
| "grad_norm": 0.09257014095783234, | |
| "learning_rate": 2.610966057441254e-06, | |
| "loss": 2.7803, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12182387747998608, | |
| "grad_norm": 0.11055697500705719, | |
| "learning_rate": 3.046127067014796e-06, | |
| "loss": 2.7681, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.1392272885485555, | |
| "grad_norm": 0.10759040713310242, | |
| "learning_rate": 3.4812880765883376e-06, | |
| "loss": 2.7611, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.15663069961712495, | |
| "grad_norm": 0.12318646907806396, | |
| "learning_rate": 3.9164490861618806e-06, | |
| "loss": 2.7402, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.1740341106856944, | |
| "grad_norm": 0.12962989509105682, | |
| "learning_rate": 4.351610095735423e-06, | |
| "loss": 2.7451, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.19143752175426385, | |
| "grad_norm": 0.13981275260448456, | |
| "learning_rate": 4.786771105308965e-06, | |
| "loss": 2.735, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.20884093282283328, | |
| "grad_norm": 0.14711035788059235, | |
| "learning_rate": 5.221932114882508e-06, | |
| "loss": 2.7469, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.22624434389140272, | |
| "grad_norm": 0.15727241337299347, | |
| "learning_rate": 5.657093124456049e-06, | |
| "loss": 2.7327, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.24364775495997215, | |
| "grad_norm": 0.15055705606937408, | |
| "learning_rate": 6.092254134029592e-06, | |
| "loss": 2.7234, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2610511660285416, | |
| "grad_norm": 0.16661331057548523, | |
| "learning_rate": 6.527415143603134e-06, | |
| "loss": 2.7174, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.278454577097111, | |
| "grad_norm": 0.17976854741573334, | |
| "learning_rate": 6.962576153176675e-06, | |
| "loss": 2.719, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.2958579881656805, | |
| "grad_norm": 0.1790621429681778, | |
| "learning_rate": 7.397737162750218e-06, | |
| "loss": 2.7173, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3132613992342499, | |
| "grad_norm": 0.19079644978046417, | |
| "learning_rate": 7.832898172323761e-06, | |
| "loss": 2.7131, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.33066481030281936, | |
| "grad_norm": 0.19005636870861053, | |
| "learning_rate": 8.268059181897302e-06, | |
| "loss": 2.7168, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.3480682213713888, | |
| "grad_norm": 0.19910404086112976, | |
| "learning_rate": 8.703220191470845e-06, | |
| "loss": 2.7061, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3654716324399582, | |
| "grad_norm": 0.20510949194431305, | |
| "learning_rate": 9.138381201044387e-06, | |
| "loss": 2.6862, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3828750435085277, | |
| "grad_norm": 0.20418143272399902, | |
| "learning_rate": 9.57354221061793e-06, | |
| "loss": 2.6802, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.4002784545770971, | |
| "grad_norm": 0.21713656187057495, | |
| "learning_rate": 1.000870322019147e-05, | |
| "loss": 2.6923, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.41768186564566656, | |
| "grad_norm": 0.2298802137374878, | |
| "learning_rate": 1.0443864229765015e-05, | |
| "loss": 2.6818, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.43508527671423597, | |
| "grad_norm": 0.2294008880853653, | |
| "learning_rate": 1.0879025239338557e-05, | |
| "loss": 2.6896, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45248868778280543, | |
| "grad_norm": 0.21464629471302032, | |
| "learning_rate": 1.1314186248912098e-05, | |
| "loss": 2.6805, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4698920988513749, | |
| "grad_norm": 0.25449061393737793, | |
| "learning_rate": 1.174934725848564e-05, | |
| "loss": 2.6806, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.4872955099199443, | |
| "grad_norm": 0.24079586565494537, | |
| "learning_rate": 1.2184508268059184e-05, | |
| "loss": 2.6844, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5046989209885138, | |
| "grad_norm": 0.2414436638355255, | |
| "learning_rate": 1.2619669277632725e-05, | |
| "loss": 2.6817, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.5221023320570832, | |
| "grad_norm": 0.2530564069747925, | |
| "learning_rate": 1.3054830287206268e-05, | |
| "loss": 2.6556, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.5395057431256526, | |
| "grad_norm": 0.26441535353660583, | |
| "learning_rate": 1.348999129677981e-05, | |
| "loss": 2.6749, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.556909154194222, | |
| "grad_norm": 0.2584131062030792, | |
| "learning_rate": 1.392515230635335e-05, | |
| "loss": 2.6575, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5743125652627915, | |
| "grad_norm": 0.25025609135627747, | |
| "learning_rate": 1.4360313315926895e-05, | |
| "loss": 2.6658, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.591715976331361, | |
| "grad_norm": 0.26518625020980835, | |
| "learning_rate": 1.4795474325500436e-05, | |
| "loss": 2.6586, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.6091193873999304, | |
| "grad_norm": 0.26597312092781067, | |
| "learning_rate": 1.5230635335073978e-05, | |
| "loss": 2.6451, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6265227984684998, | |
| "grad_norm": 0.2725384831428528, | |
| "learning_rate": 1.5665796344647522e-05, | |
| "loss": 2.6521, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.6439262095370692, | |
| "grad_norm": 0.2752222716808319, | |
| "learning_rate": 1.6100957354221064e-05, | |
| "loss": 2.6398, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6613296206056387, | |
| "grad_norm": 0.2558598518371582, | |
| "learning_rate": 1.6536118363794605e-05, | |
| "loss": 2.6486, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.6787330316742082, | |
| "grad_norm": 0.26938167214393616, | |
| "learning_rate": 1.697127937336815e-05, | |
| "loss": 2.641, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6961364427427776, | |
| "grad_norm": 0.28793784976005554, | |
| "learning_rate": 1.740644038294169e-05, | |
| "loss": 2.6344, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.713539853811347, | |
| "grad_norm": 0.2677360773086548, | |
| "learning_rate": 1.7841601392515232e-05, | |
| "loss": 2.6542, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.7309432648799165, | |
| "grad_norm": 0.28143930435180664, | |
| "learning_rate": 1.8276762402088773e-05, | |
| "loss": 2.6446, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.7483466759484859, | |
| "grad_norm": 0.28870299458503723, | |
| "learning_rate": 1.8711923411662314e-05, | |
| "loss": 2.6243, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7657500870170554, | |
| "grad_norm": 0.296633780002594, | |
| "learning_rate": 1.914708442123586e-05, | |
| "loss": 2.6306, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7831534980856247, | |
| "grad_norm": 0.2806219160556793, | |
| "learning_rate": 1.95822454308094e-05, | |
| "loss": 2.6356, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8005569091541942, | |
| "grad_norm": 0.2914940416812897, | |
| "learning_rate": 1.999940297883134e-05, | |
| "loss": 2.644, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.8179603202227637, | |
| "grad_norm": 0.28510311245918274, | |
| "learning_rate": 1.9599117132813187e-05, | |
| "loss": 2.6357, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.8353637312913331, | |
| "grad_norm": 0.3171123266220093, | |
| "learning_rate": 1.8486908682093175e-05, | |
| "loss": 2.6307, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.8527671423599026, | |
| "grad_norm": 0.2955775558948517, | |
| "learning_rate": 1.674526503944611e-05, | |
| "loss": 2.6315, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.8701705534284719, | |
| "grad_norm": 0.2767013907432556, | |
| "learning_rate": 1.450335594635761e-05, | |
| "loss": 2.6138, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8875739644970414, | |
| "grad_norm": 0.27960339188575745, | |
| "learning_rate": 1.1927453544210397e-05, | |
| "loss": 2.6305, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.9049773755656109, | |
| "grad_norm": 0.31521016359329224, | |
| "learning_rate": 9.20860073020234e-06, | |
| "loss": 2.6249, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.9223807866341803, | |
| "grad_norm": 0.2640378773212433, | |
| "learning_rate": 6.548442379624425e-06, | |
| "loss": 2.6257, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.9397841977027498, | |
| "grad_norm": 0.28068870306015015, | |
| "learning_rate": 4.144270267924306e-06, | |
| "loss": 2.6261, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.9571876087713191, | |
| "grad_norm": 0.2999429702758789, | |
| "learning_rate": 2.1743908422712135e-06, | |
| "loss": 2.6245, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9745910198398886, | |
| "grad_norm": 0.2793658971786499, | |
| "learning_rate": 7.849010480670938e-07, | |
| "loss": 2.6209, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9919944309084581, | |
| "grad_norm": 0.30049070715904236, | |
| "learning_rate": 7.885298685522235e-08, | |
| "loss": 2.6215, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 5746, | |
| "total_flos": 8.372955480242258e+17, | |
| "train_loss": 2.6846868539578486, | |
| "train_runtime": 1624.688, | |
| "train_samples_per_second": 56.585, | |
| "train_steps_per_second": 3.537 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5746, | |
| "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": 8.372955480242258e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |