| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019506485906563932, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007802594362625573, | |
| "grad_norm": 0.3376312553882599, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.4989, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007802594362625573, | |
| "eval_loss": 0.8446513414382935, | |
| "eval_runtime": 321.1678, | |
| "eval_samples_per_second": 3.363, | |
| "eval_steps_per_second": 1.681, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015605188725251145, | |
| "grad_norm": 0.4070318341255188, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.6737, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002340778308787672, | |
| "grad_norm": 0.4004059433937073, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5249, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003121037745050229, | |
| "grad_norm": 0.43589961528778076, | |
| "learning_rate": 9.99524110790929e-05, | |
| "loss": 0.6278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0039012971813127866, | |
| "grad_norm": 0.5050280690193176, | |
| "learning_rate": 9.980973490458728e-05, | |
| "loss": 0.6549, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004681556617575344, | |
| "grad_norm": 0.40668612718582153, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.5572, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005461816053837901, | |
| "grad_norm": 0.4934292733669281, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.6219, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006242075490100458, | |
| "grad_norm": 0.5753898620605469, | |
| "learning_rate": 9.881480035599667e-05, | |
| "loss": 0.5658, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007022334926363016, | |
| "grad_norm": 0.5027673840522766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.6963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007802594362625573, | |
| "grad_norm": 0.47841089963912964, | |
| "learning_rate": 9.768584753741134e-05, | |
| "loss": 0.6117, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00858285379888813, | |
| "grad_norm": 0.4685758948326111, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.561, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009363113235150688, | |
| "grad_norm": 0.5550876259803772, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7298, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010143372671413246, | |
| "grad_norm": 0.48063692450523376, | |
| "learning_rate": 9.53153893518325e-05, | |
| "loss": 0.7098, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010923632107675801, | |
| "grad_norm": 0.4520593583583832, | |
| "learning_rate": 9.435054165891109e-05, | |
| "loss": 0.6776, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011703891543938359, | |
| "grad_norm": 0.5039393305778503, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8103, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012484150980200916, | |
| "grad_norm": 0.4985882043838501, | |
| "learning_rate": 9.21695722906443e-05, | |
| "loss": 0.702, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013264410416463474, | |
| "grad_norm": 0.4833678603172302, | |
| "learning_rate": 9.09576022144496e-05, | |
| "loss": 0.7118, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.014044669852726031, | |
| "grad_norm": 0.45505037903785706, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6413, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.014824929288988589, | |
| "grad_norm": 0.5279719829559326, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.7873, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015605188725251146, | |
| "grad_norm": 0.5257707834243774, | |
| "learning_rate": 8.68638668405062e-05, | |
| "loss": 0.7481, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016385448161513702, | |
| "grad_norm": 0.5363844633102417, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7771, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01716570759777626, | |
| "grad_norm": 0.5524177551269531, | |
| "learning_rate": 8.377951038078302e-05, | |
| "loss": 0.8244, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.017945967034038817, | |
| "grad_norm": 0.5710583329200745, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 0.7883, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.018726226470301376, | |
| "grad_norm": 0.5935850739479065, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8224, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019506485906563932, | |
| "grad_norm": 0.6716726422309875, | |
| "learning_rate": 7.86788218175523e-05, | |
| "loss": 0.9925, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019506485906563932, | |
| "eval_loss": 0.7827931642532349, | |
| "eval_runtime": 323.3131, | |
| "eval_samples_per_second": 3.34, | |
| "eval_steps_per_second": 1.67, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.878345006854963e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |