| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01889466225791214, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003778932451582428, | |
| "grad_norm": 3.4327430725097656, | |
| "learning_rate": 1e-05, | |
| "loss": 19.7419, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003778932451582428, | |
| "eval_loss": 1.3291250467300415, | |
| "eval_runtime": 114.1364, | |
| "eval_samples_per_second": 3.908, | |
| "eval_steps_per_second": 1.954, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007557864903164856, | |
| "grad_norm": 3.4956791400909424, | |
| "learning_rate": 2e-05, | |
| "loss": 21.6864, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007557864903164856, | |
| "eval_loss": 1.3113912343978882, | |
| "eval_runtime": 87.3191, | |
| "eval_samples_per_second": 5.108, | |
| "eval_steps_per_second": 2.554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011336797354747285, | |
| "grad_norm": 3.430900812149048, | |
| "learning_rate": 3e-05, | |
| "loss": 21.1357, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015115729806329713, | |
| "grad_norm": 3.2519538402557373, | |
| "learning_rate": 4e-05, | |
| "loss": 18.0472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015115729806329713, | |
| "eval_loss": 1.3015305995941162, | |
| "eval_runtime": 160.4481, | |
| "eval_samples_per_second": 2.78, | |
| "eval_steps_per_second": 1.39, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01889466225791214, | |
| "grad_norm": 3.624499797821045, | |
| "learning_rate": 5e-05, | |
| "loss": 21.5395, | |
| "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": 6332448610713600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |