| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8450704225352113, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.028169014084507043, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.028169014084507043, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4451, | |
| "eval_samples_per_second": 4.354, | |
| "eval_steps_per_second": 1.161, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.08450704225352113, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11267605633802817, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9398, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 1.361, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.16901408450704225, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19718309859154928, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22535211267605634, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9416, | |
| "eval_samples_per_second": 5.099, | |
| "eval_steps_per_second": 1.36, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2535211267605634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.30985915492957744, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3380281690140845, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9608, | |
| "eval_samples_per_second": 5.066, | |
| "eval_steps_per_second": 1.351, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.36619718309859156, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.39436619718309857, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4507042253521127, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9402, | |
| "eval_samples_per_second": 5.102, | |
| "eval_steps_per_second": 1.36, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4788732394366197, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5070422535211268, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5352112676056338, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9509, | |
| "eval_samples_per_second": 5.083, | |
| "eval_steps_per_second": 1.356, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5915492957746479, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6197183098591549, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.647887323943662, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.676056338028169, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9454, | |
| "eval_samples_per_second": 5.093, | |
| "eval_steps_per_second": 1.358, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7323943661971831, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7605633802816901, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7887323943661971, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.9601, | |
| "eval_samples_per_second": 5.067, | |
| "eval_steps_per_second": 1.351, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8169014084507042, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.073272468373504e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |