| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03041131300843914, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003041131300843914, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.8114, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.526, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009123393902531741, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018246787805063483, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0027370181707595228, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027370181707595228, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.3548, | |
| "eval_samples_per_second": 4.204, | |
| "eval_steps_per_second": 0.526, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0036493575610126966, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004561696951265871, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0054740363415190455, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0054740363415190455, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.7402, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.526, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006386375731772219, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007298715122025393, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008211054512278567, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008211054512278567, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.7909, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.526, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009123393902531743, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010035733292784916, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.010948072683038091, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010948072683038091, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.6648, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.526, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.011860412073291264, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.012772751463544438, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.013685090853797613, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013685090853797613, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1318.2747, | |
| "eval_samples_per_second": 4.201, | |
| "eval_steps_per_second": 0.526, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.014597430244050786, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.015509769634303961, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.016422109024557135, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.016422109024557135, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1318.2078, | |
| "eval_samples_per_second": 4.201, | |
| "eval_steps_per_second": 0.526, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.01733444841481031, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.018246787805063485, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.019159127195316657, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.019159127195316657, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1318.5348, | |
| "eval_samples_per_second": 4.2, | |
| "eval_steps_per_second": 0.526, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.020071466585569832, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.020983805975823007, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.021896145366076182, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.021896145366076182, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1319.2601, | |
| "eval_samples_per_second": 4.198, | |
| "eval_steps_per_second": 0.525, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.022808484756329354, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.02372082414658253, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.024633163536835704, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.024633163536835704, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1318.9732, | |
| "eval_samples_per_second": 4.199, | |
| "eval_steps_per_second": 0.525, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.025545502927088876, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02645784231734205, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.027370181707595226, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.027370181707595226, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1318.0656, | |
| "eval_samples_per_second": 4.202, | |
| "eval_steps_per_second": 0.526, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0282825210978484, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.029194860488101573, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.030107199878354748, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.030107199878354748, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1317.6542, | |
| "eval_samples_per_second": 4.203, | |
| "eval_steps_per_second": 0.526, | |
| "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": 5.16340095909888e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |