| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0445103857566767, | |
| "eval_steps": 6, | |
| "global_step": 22, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04747774480712166, | |
| "grad_norm": 0.10393894463777542, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3853, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04747774480712166, | |
| "eval_loss": 10.38197135925293, | |
| "eval_runtime": 10.9858, | |
| "eval_samples_per_second": 3.277, | |
| "eval_steps_per_second": 1.638, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09495548961424333, | |
| "grad_norm": 0.10695062577724457, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3893, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.142433234421365, | |
| "grad_norm": 0.10071176290512085, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3815, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.18991097922848665, | |
| "grad_norm": 0.104220911860466, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3825, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.23738872403560832, | |
| "grad_norm": 0.11204732209444046, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3846, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "grad_norm": 0.11993242055177689, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3843, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.28486646884273, | |
| "eval_loss": 10.381671905517578, | |
| "eval_runtime": 0.075, | |
| "eval_samples_per_second": 480.233, | |
| "eval_steps_per_second": 240.117, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3323442136498516, | |
| "grad_norm": 0.10505552589893341, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3793, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3798219584569733, | |
| "grad_norm": 0.10710933804512024, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3793, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.42729970326409494, | |
| "grad_norm": 0.104378342628479, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3886, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.47477744807121663, | |
| "grad_norm": 0.1055062860250473, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5222551928783383, | |
| "grad_norm": 0.11344417184591293, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3823, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.56973293768546, | |
| "grad_norm": 0.10140898078680038, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3856, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.56973293768546, | |
| "eval_loss": 10.380664825439453, | |
| "eval_runtime": 0.0723, | |
| "eval_samples_per_second": 497.765, | |
| "eval_steps_per_second": 248.882, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6172106824925816, | |
| "grad_norm": 0.10060179978609085, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3803, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6646884272997032, | |
| "grad_norm": 0.11765701323747635, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3862, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.712166172106825, | |
| "grad_norm": 0.12245073914527893, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3825, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.7596439169139466, | |
| "grad_norm": 0.10479110479354858, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3832, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8071216617210683, | |
| "grad_norm": 0.09735947102308273, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3786, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8545994065281899, | |
| "grad_norm": 0.11688768118619919, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3835, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8545994065281899, | |
| "eval_loss": 10.379833221435547, | |
| "eval_runtime": 0.0775, | |
| "eval_samples_per_second": 464.759, | |
| "eval_steps_per_second": 232.379, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.9020771513353115, | |
| "grad_norm": 0.10974813997745514, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3813, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.9495548961424333, | |
| "grad_norm": 0.11267790198326111, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3783, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9970326409495549, | |
| "grad_norm": 0.10685980319976807, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.3776, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.0445103857566767, | |
| "grad_norm": 0.26596400141716003, | |
| "learning_rate": 0.0, | |
| "loss": 20.1393, | |
| "step": 22 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 22, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 6, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1765068963840.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |