| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6812375816065853, | |
| "eval_steps": 50, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022707919386886176, | |
| "grad_norm": 0.5527037382125854, | |
| "learning_rate": 0.00019770114942528738, | |
| "loss": 0.0749, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04541583877377235, | |
| "grad_norm": 0.18355610966682434, | |
| "learning_rate": 0.0001931034482758621, | |
| "loss": 0.0973, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06812375816065853, | |
| "grad_norm": 0.15812426805496216, | |
| "learning_rate": 0.00018850574712643678, | |
| "loss": 0.089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0908316775475447, | |
| "grad_norm": 0.19676333665847778, | |
| "learning_rate": 0.0001839080459770115, | |
| "loss": 0.0885, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11353959693443089, | |
| "grad_norm": 0.23726195096969604, | |
| "learning_rate": 0.0001793103448275862, | |
| "loss": 0.0865, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11353959693443089, | |
| "eval_loss": 0.09350696206092834, | |
| "eval_runtime": 246.8339, | |
| "eval_samples_per_second": 0.81, | |
| "eval_steps_per_second": 0.81, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13624751632131707, | |
| "grad_norm": 0.18502545356750488, | |
| "learning_rate": 0.00017471264367816095, | |
| "loss": 0.0823, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15895543570820322, | |
| "grad_norm": 0.38577064871788025, | |
| "learning_rate": 0.00017011494252873563, | |
| "loss": 0.0813, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1816633550950894, | |
| "grad_norm": 0.27274832129478455, | |
| "learning_rate": 0.00016551724137931035, | |
| "loss": 0.0887, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2043712744819756, | |
| "grad_norm": 0.18888869881629944, | |
| "learning_rate": 0.00016091954022988506, | |
| "loss": 0.088, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22707919386886177, | |
| "grad_norm": 0.19606022536754608, | |
| "learning_rate": 0.0001563218390804598, | |
| "loss": 0.0896, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.22707919386886177, | |
| "eval_loss": 0.09240507334470749, | |
| "eval_runtime": 239.9776, | |
| "eval_samples_per_second": 0.833, | |
| "eval_steps_per_second": 0.833, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24978711325574796, | |
| "grad_norm": 0.21395204961299896, | |
| "learning_rate": 0.00015172413793103449, | |
| "loss": 0.0782, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27249503264263414, | |
| "grad_norm": 0.22302134335041046, | |
| "learning_rate": 0.0001471264367816092, | |
| "loss": 0.0794, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2952029520295203, | |
| "grad_norm": 0.27699050307273865, | |
| "learning_rate": 0.0001425287356321839, | |
| "loss": 0.0802, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.31791087141640645, | |
| "grad_norm": 0.24119599163532257, | |
| "learning_rate": 0.00013793103448275863, | |
| "loss": 0.0829, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.34061879080329266, | |
| "grad_norm": 0.23131313920021057, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0796, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.34061879080329266, | |
| "eval_loss": 0.09314567595720291, | |
| "eval_runtime": 243.4064, | |
| "eval_samples_per_second": 0.822, | |
| "eval_steps_per_second": 0.822, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3633267101901788, | |
| "grad_norm": 0.311929851770401, | |
| "learning_rate": 0.00012873563218390805, | |
| "loss": 0.0783, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.386034629577065, | |
| "grad_norm": 0.2242027074098587, | |
| "learning_rate": 0.00012413793103448277, | |
| "loss": 0.0818, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.4087425489639512, | |
| "grad_norm": 0.2559347450733185, | |
| "learning_rate": 0.00011954022988505748, | |
| "loss": 0.0789, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.43145046835083734, | |
| "grad_norm": 0.23956073820590973, | |
| "learning_rate": 0.00011494252873563218, | |
| "loss": 0.0734, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.45415838773772355, | |
| "grad_norm": 0.290977418422699, | |
| "learning_rate": 0.0001103448275862069, | |
| "loss": 0.0753, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.45415838773772355, | |
| "eval_loss": 0.09412585943937302, | |
| "eval_runtime": 243.3084, | |
| "eval_samples_per_second": 0.822, | |
| "eval_steps_per_second": 0.822, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4768663071246097, | |
| "grad_norm": 0.37943148612976074, | |
| "learning_rate": 0.00010574712643678162, | |
| "loss": 0.0742, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4995742265114959, | |
| "grad_norm": 0.25092101097106934, | |
| "learning_rate": 0.00010114942528735633, | |
| "loss": 0.0745, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5222821458983821, | |
| "grad_norm": 0.27841272950172424, | |
| "learning_rate": 9.655172413793105e-05, | |
| "loss": 0.0732, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5449900652852683, | |
| "grad_norm": 0.24122974276542664, | |
| "learning_rate": 9.195402298850575e-05, | |
| "loss": 0.0738, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5676979846721544, | |
| "grad_norm": 0.33553385734558105, | |
| "learning_rate": 8.735632183908047e-05, | |
| "loss": 0.075, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5676979846721544, | |
| "eval_loss": 0.08785887062549591, | |
| "eval_runtime": 243.3288, | |
| "eval_samples_per_second": 0.822, | |
| "eval_steps_per_second": 0.822, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5904059040590406, | |
| "grad_norm": 0.228590190410614, | |
| "learning_rate": 8.275862068965517e-05, | |
| "loss": 0.0743, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.6131138234459268, | |
| "grad_norm": 0.24921129643917084, | |
| "learning_rate": 7.81609195402299e-05, | |
| "loss": 0.075, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6358217428328129, | |
| "grad_norm": 0.27115267515182495, | |
| "learning_rate": 7.35632183908046e-05, | |
| "loss": 0.0749, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6585296622196991, | |
| "grad_norm": 0.1899242103099823, | |
| "learning_rate": 6.896551724137931e-05, | |
| "loss": 0.0705, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6812375816065853, | |
| "grad_norm": 0.2068161964416504, | |
| "learning_rate": 6.436781609195403e-05, | |
| "loss": 0.0726, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6812375816065853, | |
| "eval_loss": 0.08430539816617966, | |
| "eval_runtime": 243.0981, | |
| "eval_samples_per_second": 0.823, | |
| "eval_steps_per_second": 0.823, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.261504929129062e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |