| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0935672514619883, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "eval_loss": NaN, | |
| "eval_runtime": 85.7672, | |
| "eval_samples_per_second": 1.049, | |
| "eval_steps_per_second": 0.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.3777, | |
| "eval_samples_per_second": 37.852, | |
| "eval_steps_per_second": 18.926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07485380116959064, | |
| "eval_loss": NaN, | |
| "eval_runtime": 2.4337, | |
| "eval_samples_per_second": 36.98, | |
| "eval_steps_per_second": 18.49, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0935672514619883, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "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": 3987323763032064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |