| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9395874623797988, | |
| "global_step": 3200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0004831670371886689, | |
| "loss": 1.6245, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.1368376016616821, | |
| "eval_runtime": 66.9577, | |
| "eval_samples_per_second": 19.565, | |
| "eval_steps_per_second": 0.612, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0004349349378507369, | |
| "loss": 1.0244, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": 0.934100866317749, | |
| "eval_runtime": 37.9955, | |
| "eval_samples_per_second": 34.478, | |
| "eval_steps_per_second": 1.079, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0003617988150619466, | |
| "loss": 0.9268, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": 0.8836056590080261, | |
| "eval_runtime": 40.0826, | |
| "eval_samples_per_second": 32.683, | |
| "eval_steps_per_second": 1.023, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002736074499028474, | |
| "loss": 0.8801, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": 0.8513150215148926, | |
| "eval_runtime": 33.9441, | |
| "eval_samples_per_second": 38.593, | |
| "eval_steps_per_second": 1.208, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00018223701813346817, | |
| "loss": 0.8534, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": 0.8301102519035339, | |
| "eval_runtime": 31.7757, | |
| "eval_samples_per_second": 41.226, | |
| "eval_steps_per_second": 1.29, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 9.999180039404274e-05, | |
| "loss": 0.8339, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": 0.8126574158668518, | |
| "eval_runtime": 33.2058, | |
| "eval_samples_per_second": 39.451, | |
| "eval_steps_per_second": 1.235, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 3.794724221751192e-05, | |
| "loss": 0.8214, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 0.8048203587532043, | |
| "eval_runtime": 33.377, | |
| "eval_samples_per_second": 39.249, | |
| "eval_steps_per_second": 1.228, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.4584935273235815e-06, | |
| "loss": 0.8142, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": 0.8004471659660339, | |
| "eval_runtime": 27.0937, | |
| "eval_samples_per_second": 48.351, | |
| "eval_steps_per_second": 1.513, | |
| "step": 3200 | |
| } | |
| ], | |
| "max_steps": 3405, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.217540294084133e+20, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |