| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006815122757398668, | |
| "eval_steps": 2, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "grad_norm": 2.638183116912842, | |
| "learning_rate": 1e-05, | |
| "loss": 44.3756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.407561378699334e-05, | |
| "eval_loss": 11.093536376953125, | |
| "eval_runtime": 113.9897, | |
| "eval_samples_per_second": 108.405, | |
| "eval_steps_per_second": 54.207, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.815122757398668e-05, | |
| "grad_norm": 2.178905963897705, | |
| "learning_rate": 2e-05, | |
| "loss": 44.2993, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.815122757398668e-05, | |
| "eval_loss": 11.093539237976074, | |
| "eval_runtime": 114.5009, | |
| "eval_samples_per_second": 107.921, | |
| "eval_steps_per_second": 53.965, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00010222684136098001, | |
| "grad_norm": 2.257598876953125, | |
| "learning_rate": 3e-05, | |
| "loss": 44.3175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013630245514797336, | |
| "grad_norm": 3.2154581546783447, | |
| "learning_rate": 4e-05, | |
| "loss": 44.4066, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013630245514797336, | |
| "eval_loss": 11.092741012573242, | |
| "eval_runtime": 114.161, | |
| "eval_samples_per_second": 108.242, | |
| "eval_steps_per_second": 54.125, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001703780689349667, | |
| "grad_norm": 2.7002158164978027, | |
| "learning_rate": 5e-05, | |
| "loss": 44.4089, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020445368272196002, | |
| "grad_norm": 2.5694777965545654, | |
| "learning_rate": 6e-05, | |
| "loss": 44.3066, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020445368272196002, | |
| "eval_loss": 11.091360092163086, | |
| "eval_runtime": 114.2137, | |
| "eval_samples_per_second": 108.192, | |
| "eval_steps_per_second": 54.1, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023852929650895337, | |
| "grad_norm": 2.498781442642212, | |
| "learning_rate": 7e-05, | |
| "loss": 44.3137, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002726049102959467, | |
| "grad_norm": 2.4782936573028564, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3997, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002726049102959467, | |
| "eval_loss": 11.08991527557373, | |
| "eval_runtime": 114.0478, | |
| "eval_samples_per_second": 108.349, | |
| "eval_steps_per_second": 54.179, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00030668052408294006, | |
| "grad_norm": 2.774634599685669, | |
| "learning_rate": 9e-05, | |
| "loss": 44.3353, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003407561378699334, | |
| "grad_norm": 2.3270585536956787, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4153, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003407561378699334, | |
| "eval_loss": 11.087890625, | |
| "eval_runtime": 114.1863, | |
| "eval_samples_per_second": 108.218, | |
| "eval_steps_per_second": 54.113, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003748317516569267, | |
| "grad_norm": 2.2423906326293945, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 44.3149, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00040890736544392005, | |
| "grad_norm": 2.1097352504730225, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 44.4146, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00040890736544392005, | |
| "eval_loss": 11.085128784179688, | |
| "eval_runtime": 114.1984, | |
| "eval_samples_per_second": 108.206, | |
| "eval_steps_per_second": 54.108, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0004429829792309134, | |
| "grad_norm": 2.6091725826263428, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 44.3838, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00047705859301790674, | |
| "grad_norm": 2.9170174598693848, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 44.4147, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00047705859301790674, | |
| "eval_loss": 11.082711219787598, | |
| "eval_runtime": 114.2172, | |
| "eval_samples_per_second": 108.189, | |
| "eval_steps_per_second": 54.099, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0005111342068049, | |
| "grad_norm": 2.4831223487854004, | |
| "learning_rate": 5e-05, | |
| "loss": 44.2988, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005452098205918934, | |
| "grad_norm": 2.7560153007507324, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 44.2967, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005452098205918934, | |
| "eval_loss": 11.08093547821045, | |
| "eval_runtime": 114.1435, | |
| "eval_samples_per_second": 108.258, | |
| "eval_steps_per_second": 54.134, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005792854343788867, | |
| "grad_norm": 2.718780040740967, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 44.2053, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0006133610481658801, | |
| "grad_norm": 2.361675262451172, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 44.2844, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006133610481658801, | |
| "eval_loss": 11.079801559448242, | |
| "eval_runtime": 114.2329, | |
| "eval_samples_per_second": 108.174, | |
| "eval_steps_per_second": 54.091, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006474366619528734, | |
| "grad_norm": 2.549006938934326, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 44.2642, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006815122757398668, | |
| "grad_norm": 2.272350549697876, | |
| "learning_rate": 0.0, | |
| "loss": 44.2192, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006815122757398668, | |
| "eval_loss": 11.079532623291016, | |
| "eval_runtime": 114.2157, | |
| "eval_samples_per_second": 108.19, | |
| "eval_steps_per_second": 54.099, | |
| "step": 20 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 55215390720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |