| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07077140835102619, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014154281670205238, | |
| "eval_loss": 6.930484771728516, | |
| "eval_runtime": 1.7566, | |
| "eval_samples_per_second": 169.644, | |
| "eval_steps_per_second": 84.822, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007077140835102618, | |
| "grad_norm": 0.09372831881046295, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9285, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014154281670205236, | |
| "grad_norm": 0.09359531104564667, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9288, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014154281670205236, | |
| "eval_loss": 6.929349899291992, | |
| "eval_runtime": 1.3482, | |
| "eval_samples_per_second": 221.028, | |
| "eval_steps_per_second": 110.514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021231422505307854, | |
| "grad_norm": 0.0958743542432785, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.9268, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028308563340410473, | |
| "grad_norm": 0.10200145095586777, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.9273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028308563340410473, | |
| "eval_loss": 6.926776885986328, | |
| "eval_runtime": 1.3948, | |
| "eval_samples_per_second": 213.645, | |
| "eval_steps_per_second": 106.823, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.035385704175513094, | |
| "grad_norm": 0.09926024824380875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.9245, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04246284501061571, | |
| "grad_norm": 0.10141738504171371, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04246284501061571, | |
| "eval_loss": 6.924662113189697, | |
| "eval_runtime": 1.344, | |
| "eval_samples_per_second": 221.722, | |
| "eval_steps_per_second": 110.861, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04953998584571833, | |
| "grad_norm": 0.1036619171500206, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 6.9226, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.056617126680820945, | |
| "grad_norm": 0.10181432217359543, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 6.9217, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.056617126680820945, | |
| "eval_loss": 6.923534870147705, | |
| "eval_runtime": 1.3597, | |
| "eval_samples_per_second": 219.17, | |
| "eval_steps_per_second": 109.585, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06369426751592357, | |
| "grad_norm": 0.10488573461771011, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 6.9213, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07077140835102619, | |
| "grad_norm": 0.10614355653524399, | |
| "learning_rate": 0.0, | |
| "loss": 6.9204, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07077140835102619, | |
| "eval_loss": 6.923311233520508, | |
| "eval_runtime": 1.3429, | |
| "eval_samples_per_second": 221.909, | |
| "eval_steps_per_second": 110.955, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 131833036800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |