| { | |
| "best_metric": 0.9637255072593689, | |
| "best_model_checkpoint": "./outputs/checkpoint-2200", | |
| "epoch": 2.9333333333333336, | |
| "eval_steps": 100, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0609, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.075240969657898, | |
| "eval_runtime": 354.5496, | |
| "eval_samples_per_second": 5.444, | |
| "eval_steps_per_second": 0.683, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.0535345077514648, | |
| "eval_runtime": 353.5007, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 0.685, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9039, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": 1.0421228408813477, | |
| "eval_runtime": 353.3408, | |
| "eval_samples_per_second": 5.462, | |
| "eval_steps_per_second": 0.685, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8945, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": 1.033984661102295, | |
| "eval_runtime": 353.6405, | |
| "eval_samples_per_second": 5.458, | |
| "eval_steps_per_second": 0.684, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8815, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.0270758867263794, | |
| "eval_runtime": 353.4888, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 0.685, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8818, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": 1.0182862281799316, | |
| "eval_runtime": 353.8429, | |
| "eval_samples_per_second": 5.454, | |
| "eval_steps_per_second": 0.684, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8787, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.0158191919326782, | |
| "eval_runtime": 354.0822, | |
| "eval_samples_per_second": 5.451, | |
| "eval_steps_per_second": 0.683, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8685, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_loss": 1.0099796056747437, | |
| "eval_runtime": 354.7588, | |
| "eval_samples_per_second": 5.44, | |
| "eval_steps_per_second": 0.682, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8637, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_loss": 1.006648063659668, | |
| "eval_runtime": 354.057, | |
| "eval_samples_per_second": 5.451, | |
| "eval_steps_per_second": 0.684, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8554, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_loss": 1.0002124309539795, | |
| "eval_runtime": 354.0353, | |
| "eval_samples_per_second": 5.451, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 0.0002, | |
| "loss": 0.859, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_loss": 0.9991586804389954, | |
| "eval_runtime": 354.265, | |
| "eval_samples_per_second": 5.448, | |
| "eval_steps_per_second": 0.683, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8584, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_loss": 0.9944009184837341, | |
| "eval_runtime": 353.9279, | |
| "eval_samples_per_second": 5.453, | |
| "eval_steps_per_second": 0.684, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0002, | |
| "loss": 0.852, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_loss": 0.989990234375, | |
| "eval_runtime": 354.4704, | |
| "eval_samples_per_second": 5.445, | |
| "eval_steps_per_second": 0.683, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.0002, | |
| "loss": 0.846, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_loss": 0.9865836501121521, | |
| "eval_runtime": 358.9224, | |
| "eval_samples_per_second": 5.377, | |
| "eval_steps_per_second": 0.674, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0002, | |
| "loss": 0.847, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.9840803742408752, | |
| "eval_runtime": 354.4171, | |
| "eval_samples_per_second": 5.446, | |
| "eval_steps_per_second": 0.683, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8378, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_loss": 0.9801441431045532, | |
| "eval_runtime": 355.2231, | |
| "eval_samples_per_second": 5.433, | |
| "eval_steps_per_second": 0.681, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8418, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "eval_loss": 0.9762414693832397, | |
| "eval_runtime": 354.5929, | |
| "eval_samples_per_second": 5.443, | |
| "eval_steps_per_second": 0.682, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 0.0002, | |
| "loss": 0.831, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "eval_loss": 0.975382924079895, | |
| "eval_runtime": 378.7821, | |
| "eval_samples_per_second": 5.095, | |
| "eval_steps_per_second": 0.639, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8297, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "eval_loss": 0.9727230072021484, | |
| "eval_runtime": 366.7965, | |
| "eval_samples_per_second": 5.262, | |
| "eval_steps_per_second": 0.66, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8283, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_loss": 0.9686517715454102, | |
| "eval_runtime": 366.7742, | |
| "eval_samples_per_second": 5.262, | |
| "eval_steps_per_second": 0.66, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8303, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "eval_loss": 0.9657241106033325, | |
| "eval_runtime": 368.2461, | |
| "eval_samples_per_second": 5.241, | |
| "eval_steps_per_second": 0.657, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8358, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "eval_loss": 0.9637255072593689, | |
| "eval_runtime": 365.4459, | |
| "eval_samples_per_second": 5.281, | |
| "eval_steps_per_second": 0.662, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "total_flos": 6.220289728654295e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |