| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5763688760806917, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005763688760806916, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.7478, | |
| "eval_samples_per_second": 9.529, | |
| "eval_steps_per_second": 1.203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01729106628242075, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0345821325648415, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.05187319884726225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05187319884726225, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.7379, | |
| "eval_samples_per_second": 9.532, | |
| "eval_steps_per_second": 1.204, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.069164265129683, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08645533141210375, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1037463976945245, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1037463976945245, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8365, | |
| "eval_samples_per_second": 9.502, | |
| "eval_steps_per_second": 1.2, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.12103746397694524, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.138328530259366, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15561959654178675, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15561959654178675, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8287, | |
| "eval_samples_per_second": 9.504, | |
| "eval_steps_per_second": 1.2, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1729106628242075, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19020172910662825, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.207492795389049, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.207492795389049, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.797, | |
| "eval_samples_per_second": 9.514, | |
| "eval_steps_per_second": 1.201, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22478386167146974, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2420749279538905, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.25936599423631124, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.25936599423631124, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.846, | |
| "eval_samples_per_second": 9.499, | |
| "eval_steps_per_second": 1.2, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.276657060518732, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29394812680115273, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.3112391930835735, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3112391930835735, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.7943, | |
| "eval_samples_per_second": 9.515, | |
| "eval_steps_per_second": 1.202, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3285302593659942, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.345821325648415, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3631123919308357, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3631123919308357, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8588, | |
| "eval_samples_per_second": 9.495, | |
| "eval_steps_per_second": 1.199, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.3804034582132565, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3976945244956772, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.414985590778098, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.414985590778098, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.9168, | |
| "eval_samples_per_second": 9.477, | |
| "eval_steps_per_second": 1.197, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.4322766570605187, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4495677233429395, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.4668587896253602, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.4668587896253602, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8942, | |
| "eval_samples_per_second": 9.484, | |
| "eval_steps_per_second": 1.198, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.484149855907781, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5014409221902018, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.5187319884726225, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5187319884726225, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8746, | |
| "eval_samples_per_second": 9.49, | |
| "eval_steps_per_second": 1.198, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5360230547550432, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.553314121037464, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.5706051873198847, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.5706051873198847, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.8968, | |
| "eval_samples_per_second": 9.483, | |
| "eval_steps_per_second": 1.198, | |
| "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": 2.349921441153024e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |