| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12322858903265557, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024645717806531116, | |
| "eval_loss": NaN, | |
| "eval_runtime": 9.5964, | |
| "eval_samples_per_second": 17.819, | |
| "eval_steps_per_second": 8.962, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024645717806531114, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03203943314849045, | |
| "eval_loss": NaN, | |
| "eval_runtime": 7.9992, | |
| "eval_samples_per_second": 21.377, | |
| "eval_steps_per_second": 10.751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04929143561306223, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0640788662969809, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.0127, | |
| "eval_samples_per_second": 21.341, | |
| "eval_steps_per_second": 10.733, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07393715341959335, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09611829944547134, | |
| "eval_loss": NaN, | |
| "eval_runtime": 8.0048, | |
| "eval_samples_per_second": 21.362, | |
| "eval_steps_per_second": 10.744, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09858287122612445, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.12322858903265557, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3848370326011904e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |