| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09339248190520663, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009339248190520663, | |
| "grad_norm": 6.638877692627699, | |
| "learning_rate": 9.345794392523364e-07, | |
| "loss": 9.2917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009339248190520663, | |
| "grad_norm": 1.1560921335705272, | |
| "learning_rate": 9.345794392523365e-06, | |
| "loss": 9.0876, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018678496381041326, | |
| "grad_norm": 0.8415132296956432, | |
| "learning_rate": 1.869158878504673e-05, | |
| "loss": 8.2164, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02801774457156199, | |
| "grad_norm": 0.45381630992958155, | |
| "learning_rate": 2.8037383177570094e-05, | |
| "loss": 7.5184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03735699276208265, | |
| "grad_norm": 0.8400636107958425, | |
| "learning_rate": 3.738317757009346e-05, | |
| "loss": 6.6507, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.046696240952603316, | |
| "grad_norm": 0.557696240829066, | |
| "learning_rate": 4.672897196261683e-05, | |
| "loss": 5.8909, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05603548914312398, | |
| "grad_norm": 0.3971996057467842, | |
| "learning_rate": 5.607476635514019e-05, | |
| "loss": 5.4127, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.06537473733364464, | |
| "grad_norm": 0.2932710540265688, | |
| "learning_rate": 6.542056074766355e-05, | |
| "loss": 5.0106, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0747139855241653, | |
| "grad_norm": 0.3682690443551033, | |
| "learning_rate": 7.476635514018692e-05, | |
| "loss": 4.6042, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08405323371468597, | |
| "grad_norm": 0.3132971920011515, | |
| "learning_rate": 8.411214953271028e-05, | |
| "loss": 4.2031, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09339248190520663, | |
| "grad_norm": 0.6731868159213446, | |
| "learning_rate": 9.345794392523365e-05, | |
| "loss": 3.9423, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4280, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.097013951490949e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |