| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.976, | |
| "eval_steps": 500, | |
| "global_step": 186, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 2.315385580062866, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 1.1346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.9955989122390747, | |
| "learning_rate": 9.999115304121459e-06, | |
| "loss": 0.6167, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 2.6150994300842285, | |
| "learning_rate": 9.893330096656576e-06, | |
| "loss": 0.6992, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 1.5031245946884155, | |
| "learning_rate": 9.614885510995047e-06, | |
| "loss": 0.5127, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 2.037620782852173, | |
| "learning_rate": 9.173606363381218e-06, | |
| "loss": 0.6019, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.4414268732070923, | |
| "learning_rate": 8.585063028536015e-06, | |
| "loss": 0.5458, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "grad_norm": 1.4928420782089233, | |
| "learning_rate": 7.870022044630569e-06, | |
| "loss": 0.4214, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 3.09617280960083, | |
| "learning_rate": 7.053713373516538e-06, | |
| "loss": 0.3165, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "grad_norm": 0.9061471819877625, | |
| "learning_rate": 6.164940170670266e-06, | |
| "loss": 0.2753, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.7724579572677612, | |
| "learning_rate": 5.235062476295488e-06, | |
| "loss": 0.2277, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "grad_norm": 4.286865711212158, | |
| "learning_rate": 4.29689068767551e-06, | |
| "loss": 0.364, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "grad_norm": 2.2703816890716553, | |
| "learning_rate": 3.3835278562017405e-06, | |
| "loss": 0.2258, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "grad_norm": 3.2891488075256348, | |
| "learning_rate": 2.5272016582081236e-06, | |
| "loss": 0.3729, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "grad_norm": 1.9059756994247437, | |
| "learning_rate": 1.7581272530970666e-06, | |
| "loss": 0.2026, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.4624115228652954, | |
| "learning_rate": 1.103441152395588e-06, | |
| "loss": 0.1538, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "grad_norm": 1.4256014823913574, | |
| "learning_rate": 5.862437177854629e-07, | |
| "loss": 0.2309, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.7199999999999998, | |
| "grad_norm": 0.27677008509635925, | |
| "learning_rate": 2.2478407321721295e-07, | |
| "loss": 0.1604, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "grad_norm": 0.8201978206634521, | |
| "learning_rate": 3.181619118841517e-08, | |
| "loss": 0.1571, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.976, | |
| "step": 186, | |
| "total_flos": 4302697811263488.0, | |
| "train_loss": 0.3938655372588865, | |
| "train_runtime": 377.5359, | |
| "train_samples_per_second": 3.973, | |
| "train_steps_per_second": 0.493 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 186, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4302697811263488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |