| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06060606060606061, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006060606060606061, | |
| "grad_norm": 0.16079512238502502, | |
| "learning_rate": 2e-05, | |
| "loss": 6.9379, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006060606060606061, | |
| "eval_loss": 6.929784297943115, | |
| "eval_runtime": 1.5281, | |
| "eval_samples_per_second": 45.808, | |
| "eval_steps_per_second": 22.904, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012121212121212121, | |
| "grad_norm": 0.25343838334083557, | |
| "learning_rate": 4e-05, | |
| "loss": 6.9225, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "grad_norm": 0.15911762416362762, | |
| "learning_rate": 6e-05, | |
| "loss": 6.9307, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01818181818181818, | |
| "eval_loss": 6.92959451675415, | |
| "eval_runtime": 0.2332, | |
| "eval_samples_per_second": 300.135, | |
| "eval_steps_per_second": 150.068, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.024242424242424242, | |
| "grad_norm": 0.18496407568454742, | |
| "learning_rate": 8e-05, | |
| "loss": 6.9229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030303030303030304, | |
| "grad_norm": 0.2999425530433655, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9288, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "grad_norm": 0.5491859912872314, | |
| "learning_rate": 0.00012, | |
| "loss": 6.9041, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03636363636363636, | |
| "eval_loss": 6.928725719451904, | |
| "eval_runtime": 0.2363, | |
| "eval_samples_per_second": 296.194, | |
| "eval_steps_per_second": 148.097, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04242424242424243, | |
| "grad_norm": 0.30270734429359436, | |
| "learning_rate": 0.00014, | |
| "loss": 6.9248, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 0.24012736976146698, | |
| "learning_rate": 0.00016, | |
| "loss": 6.9257, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "grad_norm": 0.2366066873073578, | |
| "learning_rate": 0.00018, | |
| "loss": 6.928, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05454545454545454, | |
| "eval_loss": 6.927116870880127, | |
| "eval_runtime": 0.2482, | |
| "eval_samples_per_second": 282.009, | |
| "eval_steps_per_second": 141.005, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06060606060606061, | |
| "grad_norm": 0.21642495691776276, | |
| "learning_rate": 0.0002, | |
| "loss": 6.9218, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 26366607360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |