| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 113, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 4.13215970993042, | |
| "learning_rate": 0.000184070796460177, | |
| "loss": 4.2493, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 3.08798885345459, | |
| "learning_rate": 0.0001663716814159292, | |
| "loss": 2.3753, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 2.5904085636138916, | |
| "learning_rate": 0.00014867256637168144, | |
| "loss": 1.5071, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.754753828048706, | |
| "learning_rate": 0.00013097345132743365, | |
| "loss": 1.1523, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.8605502843856812, | |
| "learning_rate": 0.00011327433628318584, | |
| "loss": 1.1626, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.8758076429367065, | |
| "learning_rate": 9.557522123893806e-05, | |
| "loss": 1.0921, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.6590514183044434, | |
| "learning_rate": 7.787610619469027e-05, | |
| "loss": 1.1019, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 1.5678151845932007, | |
| "learning_rate": 6.017699115044248e-05, | |
| "loss": 1.0947, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.8976061344146729, | |
| "learning_rate": 4.247787610619469e-05, | |
| "loss": 1.0576, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.6436711549758911, | |
| "learning_rate": 2.4778761061946905e-05, | |
| "loss": 1.0157, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.874859094619751, | |
| "learning_rate": 7.079646017699115e-06, | |
| "loss": 1.0479, | |
| "step": 110 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 113, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 225739973468160.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |