| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06289308176100629, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020964360587002098, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020964360587002098, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.604, | |
| "eval_samples_per_second": 5.981, | |
| "eval_steps_per_second": 1.518, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0041928721174004195, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006289308176100629, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008385744234800839, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008385744234800839, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.4772, | |
| "eval_samples_per_second": 6.004, | |
| "eval_steps_per_second": 1.523, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.010482180293501049, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.012578616352201259, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014675052410901468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.016771488469601678, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016771488469601678, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.4928, | |
| "eval_samples_per_second": 6.001, | |
| "eval_steps_per_second": 1.523, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018867924528301886, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023060796645702306, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.025157232704402517, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025157232704402517, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.4963, | |
| "eval_samples_per_second": 6.001, | |
| "eval_steps_per_second": 1.523, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.027253668763102725, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.029350104821802937, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.031446540880503145, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.033542976939203356, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.033542976939203356, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.5245, | |
| "eval_samples_per_second": 5.996, | |
| "eval_steps_per_second": 1.521, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03563941299790356, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.039832285115303984, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.5119, | |
| "eval_samples_per_second": 5.998, | |
| "eval_steps_per_second": 1.522, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0440251572327044, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04612159329140461, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04821802935010482, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.050314465408805034, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.050314465408805034, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.448, | |
| "eval_samples_per_second": 6.009, | |
| "eval_steps_per_second": 1.525, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05241090146750524, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05450733752620545, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05660377358490566, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05870020964360587, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05870020964360587, | |
| "eval_loss": NaN, | |
| "eval_runtime": 33.4496, | |
| "eval_samples_per_second": 6.009, | |
| "eval_steps_per_second": 1.525, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06079664570230608, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "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": 1.5950576596549632e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |