| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06042296072507553, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002014098690835851, | |
| "grad_norm": 0.07153145968914032, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 10.3873, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002014098690835851, | |
| "eval_loss": 10.376280784606934, | |
| "eval_runtime": 1.3195, | |
| "eval_samples_per_second": 159.148, | |
| "eval_steps_per_second": 40.166, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004028197381671702, | |
| "grad_norm": 0.06775236129760742, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 10.3785, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006042296072507553, | |
| "grad_norm": 0.08857472985982895, | |
| "learning_rate": 6e-06, | |
| "loss": 10.3979, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008056394763343404, | |
| "grad_norm": 0.07686039060354233, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 10.3753, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008056394763343404, | |
| "eval_loss": 10.376274108886719, | |
| "eval_runtime": 1.3333, | |
| "eval_samples_per_second": 157.504, | |
| "eval_steps_per_second": 39.751, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010070493454179255, | |
| "grad_norm": 0.07507610321044922, | |
| "learning_rate": 1e-05, | |
| "loss": 10.3641, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012084592145015106, | |
| "grad_norm": 0.06724587082862854, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 10.381, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014098690835850957, | |
| "grad_norm": 0.08287353068590164, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 10.3681, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016112789526686808, | |
| "grad_norm": 0.0772046148777008, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 10.3759, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016112789526686808, | |
| "eval_loss": 10.376235008239746, | |
| "eval_runtime": 1.3303, | |
| "eval_samples_per_second": 157.863, | |
| "eval_steps_per_second": 39.842, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01812688821752266, | |
| "grad_norm": 0.08999884128570557, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 10.3635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02014098690835851, | |
| "grad_norm": 0.0935807079076767, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 10.3863, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022155085599194362, | |
| "grad_norm": 0.060600243508815765, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 10.3691, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "grad_norm": 0.0810532197356224, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 10.3711, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "eval_loss": 10.376185417175293, | |
| "eval_runtime": 1.3069, | |
| "eval_samples_per_second": 160.688, | |
| "eval_steps_per_second": 40.555, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.026183282980866064, | |
| "grad_norm": 0.06339351087808609, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 10.3754, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.028197381671701913, | |
| "grad_norm": 0.07340232282876968, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 10.384, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.030211480362537766, | |
| "grad_norm": 0.07252522557973862, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 10.3791, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.032225579053373615, | |
| "grad_norm": 0.11222871392965317, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 10.3713, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.032225579053373615, | |
| "eval_loss": 10.376160621643066, | |
| "eval_runtime": 1.3263, | |
| "eval_samples_per_second": 158.336, | |
| "eval_steps_per_second": 39.961, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03423967774420947, | |
| "grad_norm": 0.09647917747497559, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 10.3705, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03625377643504532, | |
| "grad_norm": 0.05165452882647514, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 10.3825, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.038267875125881166, | |
| "grad_norm": 0.09363428503274918, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 10.3865, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04028197381671702, | |
| "grad_norm": 0.08932711184024811, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 10.3844, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04028197381671702, | |
| "eval_loss": 10.376140594482422, | |
| "eval_runtime": 1.3254, | |
| "eval_samples_per_second": 158.447, | |
| "eval_steps_per_second": 39.989, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04229607250755287, | |
| "grad_norm": 0.06776072829961777, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 10.3778, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.044310171198388724, | |
| "grad_norm": 0.10044359415769577, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 10.3809, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04632426988922457, | |
| "grad_norm": 0.05310438573360443, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 10.384, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04833836858006042, | |
| "grad_norm": 0.07263986021280289, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 10.3776, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04833836858006042, | |
| "eval_loss": 10.376131057739258, | |
| "eval_runtime": 1.3848, | |
| "eval_samples_per_second": 151.648, | |
| "eval_steps_per_second": 38.273, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.050352467270896276, | |
| "grad_norm": 0.06635206937789917, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 10.3833, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05236656596173213, | |
| "grad_norm": 0.07960743457078934, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 10.3775, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.054380664652567974, | |
| "grad_norm": 0.08524226397275925, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 10.3724, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05639476334340383, | |
| "grad_norm": 0.07138201594352722, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 10.3583, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05639476334340383, | |
| "eval_loss": 10.37612533569336, | |
| "eval_runtime": 1.3276, | |
| "eval_samples_per_second": 158.18, | |
| "eval_steps_per_second": 39.922, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05840886203423968, | |
| "grad_norm": 0.06965550780296326, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 10.3757, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06042296072507553, | |
| "grad_norm": 0.09820755571126938, | |
| "learning_rate": 0.0, | |
| "loss": 10.3674, | |
| "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": 836839145472.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |