| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000444122044737894, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.48040681579298e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.48040681579298e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 188.0117, | |
| "eval_samples_per_second": 151.278, | |
| "eval_steps_per_second": 37.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.96081363158596e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.4412204473789396e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-06, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.92162726317192e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.92162726317192e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 188.5033, | |
| "eval_samples_per_second": 150.883, | |
| "eval_steps_per_second": 37.723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 7.4020340789649e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 8.882440894757879e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00010362847710550859, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001184325452634384, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001184325452634384, | |
| "eval_loss": NaN, | |
| "eval_runtime": 189.0065, | |
| "eval_samples_per_second": 150.482, | |
| "eval_steps_per_second": 37.623, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00013323661342136818, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000148040681579298, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001628447497372278, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00017764881789515758, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00017764881789515758, | |
| "eval_loss": NaN, | |
| "eval_runtime": 189.3091, | |
| "eval_samples_per_second": 150.241, | |
| "eval_steps_per_second": 37.563, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0001924528860530874, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00020725695421101718, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.000222061022368947, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002368650905268768, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002368650905268768, | |
| "eval_loss": NaN, | |
| "eval_runtime": 189.2595, | |
| "eval_samples_per_second": 150.28, | |
| "eval_steps_per_second": 37.573, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002516691586848066, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00026647322684273636, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00028127729500066617, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.000296081363158596, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000296081363158596, | |
| "eval_loss": NaN, | |
| "eval_runtime": 189.0574, | |
| "eval_samples_per_second": 150.441, | |
| "eval_steps_per_second": 37.613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003108854313165258, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0003256894994744556, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00034049356763238536, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00035529763579031517, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00035529763579031517, | |
| "eval_loss": NaN, | |
| "eval_runtime": 188.8151, | |
| "eval_samples_per_second": 150.634, | |
| "eval_steps_per_second": 37.661, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.000370101703948245, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0003849057721061748, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0003997098402641046, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00041451390842203435, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00041451390842203435, | |
| "eval_loss": NaN, | |
| "eval_runtime": 189.0757, | |
| "eval_samples_per_second": 150.427, | |
| "eval_steps_per_second": 37.609, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.00042931797657996416, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.000444122044737894, | |
| "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": 64909329039360.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |