| { | |
| "best_metric": 0.009419742971658707, | |
| "best_model_checkpoint": "verbnet_train_derived/checkpoint-5272500", | |
| "epoch": 22.0, | |
| "eval_steps": 500, | |
| "global_step": 5799750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.0011935352813452482, | |
| "learning_rate": 1.9600150213371268e-05, | |
| "loss": 0.237, | |
| "step": 263625 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.0812821313738823, | |
| "eval_runtime": 657.1184, | |
| "eval_samples_per_second": 168.919, | |
| "eval_steps_per_second": 21.115, | |
| "step": 263625 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.0008472450426779687, | |
| "learning_rate": 1.9200294357515412e-05, | |
| "loss": 0.0675, | |
| "step": 527250 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.04395299404859543, | |
| "eval_runtime": 635.1223, | |
| "eval_samples_per_second": 174.769, | |
| "eval_steps_per_second": 21.846, | |
| "step": 527250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.0005161144654266536, | |
| "learning_rate": 1.8800440018966338e-05, | |
| "loss": 0.0402, | |
| "step": 790875 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.03021380864083767, | |
| "eval_runtime": 631.9338, | |
| "eval_samples_per_second": 175.651, | |
| "eval_steps_per_second": 21.956, | |
| "step": 790875 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.3789523109153379e-05, | |
| "learning_rate": 1.8400591749644382e-05, | |
| "loss": 0.0269, | |
| "step": 1054500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.02329804003238678, | |
| "eval_runtime": 635.8959, | |
| "eval_samples_per_second": 174.557, | |
| "eval_steps_per_second": 21.82, | |
| "step": 1054500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.8203951185569167e-05, | |
| "learning_rate": 1.8000737411095308e-05, | |
| "loss": 0.019, | |
| "step": 1318125 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.01786634884774685, | |
| "eval_runtime": 635.4082, | |
| "eval_samples_per_second": 174.691, | |
| "eval_steps_per_second": 21.836, | |
| "step": 1318125 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.00018590281251817942, | |
| "learning_rate": 1.7600884589853015e-05, | |
| "loss": 0.0144, | |
| "step": 1581750 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.016473863273859024, | |
| "eval_runtime": 633.0357, | |
| "eval_samples_per_second": 175.346, | |
| "eval_steps_per_second": 21.918, | |
| "step": 1581750 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 4.66911842522677e-06, | |
| "learning_rate": 1.7201034803224278e-05, | |
| "loss": 0.0115, | |
| "step": 1845375 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.015895597636699677, | |
| "eval_runtime": 641.0505, | |
| "eval_samples_per_second": 173.153, | |
| "eval_steps_per_second": 21.644, | |
| "step": 1845375 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.0007661374402232468, | |
| "learning_rate": 1.6801183499288766e-05, | |
| "loss": 0.0093, | |
| "step": 2109000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.014273108914494514, | |
| "eval_runtime": 643.6593, | |
| "eval_samples_per_second": 172.451, | |
| "eval_steps_per_second": 21.556, | |
| "step": 2109000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 8.322523353854194e-05, | |
| "learning_rate": 1.640133219535325e-05, | |
| "loss": 0.0078, | |
| "step": 2372625 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.014644059352576733, | |
| "eval_runtime": 650.6057, | |
| "eval_samples_per_second": 170.61, | |
| "eval_steps_per_second": 21.326, | |
| "step": 2372625 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 5.2284158300608397e-05, | |
| "learning_rate": 1.6001473304883833e-05, | |
| "loss": 0.0067, | |
| "step": 2636250 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.012359824031591415, | |
| "eval_runtime": 641.3289, | |
| "eval_samples_per_second": 173.078, | |
| "eval_steps_per_second": 21.635, | |
| "step": 2636250 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 3.8969083107076585e-06, | |
| "learning_rate": 1.5601615931721196e-05, | |
| "loss": 0.0058, | |
| "step": 2899875 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.01156603079289198, | |
| "eval_runtime": 652.3223, | |
| "eval_samples_per_second": 170.161, | |
| "eval_steps_per_second": 21.27, | |
| "step": 2899875 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 0.0002835058548953384, | |
| "learning_rate": 1.5201769179706023e-05, | |
| "loss": 0.005, | |
| "step": 3163500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.01072214636951685, | |
| "eval_runtime": 641.4082, | |
| "eval_samples_per_second": 173.057, | |
| "eval_steps_per_second": 21.632, | |
| "step": 3163500 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 0.00011918282689293846, | |
| "learning_rate": 1.4801914841156947e-05, | |
| "loss": 0.0044, | |
| "step": 3427125 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.010954467579722404, | |
| "eval_runtime": 629.2662, | |
| "eval_samples_per_second": 176.396, | |
| "eval_steps_per_second": 22.049, | |
| "step": 3427125 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 0.007161498535424471, | |
| "learning_rate": 1.4402065054528213e-05, | |
| "loss": 0.004, | |
| "step": 3690750 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.010908876545727253, | |
| "eval_runtime": 629.2988, | |
| "eval_samples_per_second": 176.387, | |
| "eval_steps_per_second": 22.048, | |
| "step": 3690750 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 7.312962679861812e-07, | |
| "learning_rate": 1.4002209198672358e-05, | |
| "loss": 0.0037, | |
| "step": 3954375 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.010052459314465523, | |
| "eval_runtime": 635.7428, | |
| "eval_samples_per_second": 174.599, | |
| "eval_steps_per_second": 21.825, | |
| "step": 3954375 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 4.2960027712979354e-07, | |
| "learning_rate": 1.3602357894736844e-05, | |
| "loss": 0.0033, | |
| "step": 4218000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.010330937802791595, | |
| "eval_runtime": 629.6541, | |
| "eval_samples_per_second": 176.287, | |
| "eval_steps_per_second": 22.036, | |
| "step": 4218000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 0.0008307069656439126, | |
| "learning_rate": 1.320250659080133e-05, | |
| "loss": 0.0031, | |
| "step": 4481625 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 0.01024313922971487, | |
| "eval_runtime": 635.1679, | |
| "eval_samples_per_second": 174.757, | |
| "eval_steps_per_second": 21.845, | |
| "step": 4481625 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 0.0025596776977181435, | |
| "learning_rate": 1.2802655286865814e-05, | |
| "loss": 0.0029, | |
| "step": 4745250 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 0.009656715206801891, | |
| "eval_runtime": 636.6325, | |
| "eval_samples_per_second": 174.355, | |
| "eval_steps_per_second": 21.794, | |
| "step": 4745250 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 8.333265633098108e-09, | |
| "learning_rate": 1.2402803982930301e-05, | |
| "loss": 0.0026, | |
| "step": 5008875 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 0.010165048763155937, | |
| "eval_runtime": 634.6836, | |
| "eval_samples_per_second": 174.89, | |
| "eval_steps_per_second": 21.861, | |
| "step": 5008875 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.680733190985052e-09, | |
| "learning_rate": 1.2002948127074444e-05, | |
| "loss": 0.0025, | |
| "step": 5272500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 0.009419742971658707, | |
| "eval_runtime": 634.1323, | |
| "eval_samples_per_second": 175.042, | |
| "eval_steps_per_second": 21.88, | |
| "step": 5272500 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 6.09518974670209e-05, | |
| "learning_rate": 1.1603090753911807e-05, | |
| "loss": 0.0023, | |
| "step": 5536125 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_loss": 0.009624071419239044, | |
| "eval_runtime": 642.1241, | |
| "eval_samples_per_second": 172.864, | |
| "eval_steps_per_second": 21.608, | |
| "step": 5536125 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 1.189944759971695e-05, | |
| "learning_rate": 1.1203236415362733e-05, | |
| "loss": 0.0022, | |
| "step": 5799750 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_loss": 0.009889870882034302, | |
| "eval_runtime": 641.6364, | |
| "eval_samples_per_second": 172.995, | |
| "eval_steps_per_second": 21.624, | |
| "step": 5799750 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13181250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.202109132801867e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |