| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013748657357679914, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0034371643394199786, | |
| "grad_norm": 8.735864639282227, | |
| "learning_rate": 1e-05, | |
| "loss": 12.067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0034371643394199786, | |
| "eval_loss": 11.081414222717285, | |
| "eval_runtime": 122.4794, | |
| "eval_samples_per_second": 4.001, | |
| "eval_steps_per_second": 2.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "grad_norm": 7.742408752441406, | |
| "learning_rate": 2e-05, | |
| "loss": 10.7824, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "eval_loss": 10.88512134552002, | |
| "eval_runtime": 33.1253, | |
| "eval_samples_per_second": 14.792, | |
| "eval_steps_per_second": 7.396, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010311493018259935, | |
| "grad_norm": 7.876696586608887, | |
| "learning_rate": 3e-05, | |
| "loss": 10.7218, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013748657357679914, | |
| "grad_norm": 8.09037971496582, | |
| "learning_rate": 4e-05, | |
| "loss": 10.9274, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013748657357679914, | |
| "eval_loss": 10.605326652526855, | |
| "eval_runtime": 26.0997, | |
| "eval_samples_per_second": 18.774, | |
| "eval_steps_per_second": 9.387, | |
| "step": 4 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4762627938975744.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |