| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.031658092599920855, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006331618519984171, | |
| "grad_norm": 2.2554357051849365, | |
| "learning_rate": 1e-05, | |
| "loss": 177.5625, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006331618519984171, | |
| "eval_loss": 11.099250793457031, | |
| "eval_runtime": 9.6811, | |
| "eval_samples_per_second": 27.58, | |
| "eval_steps_per_second": 13.841, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012663237039968342, | |
| "grad_norm": 2.3769423961639404, | |
| "learning_rate": 2e-05, | |
| "loss": 177.625, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012663237039968342, | |
| "eval_loss": 11.099250793457031, | |
| "eval_runtime": 0.3626, | |
| "eval_samples_per_second": 736.278, | |
| "eval_steps_per_second": 369.518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.018994855559952513, | |
| "grad_norm": 2.309274911880493, | |
| "learning_rate": 3e-05, | |
| "loss": 177.625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025326474079936684, | |
| "grad_norm": 2.5874454975128174, | |
| "learning_rate": 4e-05, | |
| "loss": 177.4375, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025326474079936684, | |
| "eval_loss": 11.09831428527832, | |
| "eval_runtime": 0.4363, | |
| "eval_samples_per_second": 611.905, | |
| "eval_steps_per_second": 307.099, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.031658092599920855, | |
| "grad_norm": 2.515315294265747, | |
| "learning_rate": 5e-05, | |
| "loss": 177.4375, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "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": 14942208000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |