| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08481764206955046, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008481764206955047, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.4618, | |
| "eval_samples_per_second": 13.704, | |
| "eval_steps_per_second": 3.436, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002544529262086514, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005089058524173028, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007633587786259542, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.816, | |
| "eval_samples_per_second": 13.637, | |
| "eval_steps_per_second": 3.42, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010178117048346057, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01272264631043257, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015267175572519083, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9685, | |
| "eval_samples_per_second": 13.609, | |
| "eval_steps_per_second": 3.412, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017811704834605598, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.020356234096692113, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.022900763358778626, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9694, | |
| "eval_samples_per_second": 13.608, | |
| "eval_steps_per_second": 3.412, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02544529262086514, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027989821882951654, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.030534351145038167, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.929, | |
| "eval_samples_per_second": 13.616, | |
| "eval_steps_per_second": 3.414, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03307888040712468, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.035623409669211195, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03816793893129771, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9623, | |
| "eval_samples_per_second": 13.61, | |
| "eval_steps_per_second": 3.413, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04071246819338423, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.043256997455470736, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04580152671755725, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9424, | |
| "eval_samples_per_second": 13.613, | |
| "eval_steps_per_second": 3.414, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04834605597964377, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.05089058524173028, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05343511450381679, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05343511450381679, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9528, | |
| "eval_samples_per_second": 13.612, | |
| "eval_steps_per_second": 3.413, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05597964376590331, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.058524173027989825, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.061068702290076333, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9281, | |
| "eval_samples_per_second": 13.616, | |
| "eval_steps_per_second": 3.414, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06361323155216285, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06615776081424936, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.06870229007633588, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.06870229007633588, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9323, | |
| "eval_samples_per_second": 13.615, | |
| "eval_steps_per_second": 3.414, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07124681933842239, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.0737913486005089, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07633587786259542, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9706, | |
| "eval_samples_per_second": 13.608, | |
| "eval_steps_per_second": 3.412, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07888040712468193, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.08142493638676845, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.08396946564885496, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.08396946564885496, | |
| "eval_loss": NaN, | |
| "eval_runtime": 72.9717, | |
| "eval_samples_per_second": 13.608, | |
| "eval_steps_per_second": 3.412, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.65248289783808e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |