| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009730781706130393, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003243593902043464, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003243593902043464, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.428, | |
| "eval_samples_per_second": 3.037, | |
| "eval_steps_per_second": 0.76, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006487187804086928, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009730781706130393, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012974375608173856, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012974375608173856, | |
| "eval_loss": NaN, | |
| "eval_runtime": 426.8831, | |
| "eval_samples_per_second": 3.041, | |
| "eval_steps_per_second": 0.761, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001621796951021732, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019461563412260785, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0022705157314304248, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0025948751216347712, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025948751216347712, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.2329, | |
| "eval_samples_per_second": 3.038, | |
| "eval_steps_per_second": 0.761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0029192345118391177, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003243593902043464, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0035679532922478106, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003892312682452157, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003892312682452157, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.1271, | |
| "eval_samples_per_second": 3.039, | |
| "eval_steps_per_second": 0.761, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0042166720726565035, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0045410314628608495, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004865390853065196, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0051897502432695424, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0051897502432695424, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.0135, | |
| "eval_samples_per_second": 3.04, | |
| "eval_steps_per_second": 0.761, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005514109633473889, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005838469023678235, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.006162828413882582, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.006487187804086928, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006487187804086928, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.2112, | |
| "eval_samples_per_second": 3.038, | |
| "eval_steps_per_second": 0.761, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006811547194291274, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007135906584495621, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.007460265974699967, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007784625364904314, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007784625364904314, | |
| "eval_loss": NaN, | |
| "eval_runtime": 426.942, | |
| "eval_samples_per_second": 3.04, | |
| "eval_steps_per_second": 0.761, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008108984755108661, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008433344145313007, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.008757703535517353, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.009082062925721699, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009082062925721699, | |
| "eval_loss": NaN, | |
| "eval_runtime": 426.982, | |
| "eval_samples_per_second": 3.04, | |
| "eval_steps_per_second": 0.761, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.009406422315926047, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.009730781706130393, | |
| "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": 3.1185484973604864e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |