| { | |
| "best_metric": 1.1438716650009155, | |
| "best_model_checkpoint": "/data1/attanasiog/safetune/models/checkpoint-750", | |
| "epoch": 0.9996955859969558, | |
| "global_step": 821, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 2e-05, | |
| "loss": 2.1055, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": 1.762616515159607, | |
| "eval_mse": 1.7626165039521147, | |
| "eval_runtime": 183.7464, | |
| "eval_samples_per_second": 15.891, | |
| "eval_steps_per_second": 3.973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7607, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 2e-05, | |
| "loss": 1.6818, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": 1.4659080505371094, | |
| "eval_mse": 1.4659080196895005, | |
| "eval_runtime": 183.1621, | |
| "eval_samples_per_second": 15.942, | |
| "eval_steps_per_second": 3.986, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5873, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4062, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": 1.6322834491729736, | |
| "eval_mse": 1.632283383560956, | |
| "eval_runtime": 183.308, | |
| "eval_samples_per_second": 15.929, | |
| "eval_steps_per_second": 3.982, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5638, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4777, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": 1.3775594234466553, | |
| "eval_mse": 1.3775594118336603, | |
| "eval_runtime": 183.7408, | |
| "eval_samples_per_second": 15.892, | |
| "eval_steps_per_second": 3.973, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4016, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4106, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": 1.304379940032959, | |
| "eval_mse": 1.3043799442360644, | |
| "eval_runtime": 183.2767, | |
| "eval_samples_per_second": 15.932, | |
| "eval_steps_per_second": 3.983, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3077, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2702, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": 1.3791648149490356, | |
| "eval_mse": 1.3791648080316543, | |
| "eval_runtime": 183.7482, | |
| "eval_samples_per_second": 15.891, | |
| "eval_steps_per_second": 3.973, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3216, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4448, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": 1.3047657012939453, | |
| "eval_mse": 1.3047656766562488, | |
| "eval_runtime": 183.5141, | |
| "eval_samples_per_second": 15.912, | |
| "eval_steps_per_second": 3.978, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3344, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3582, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.248475432395935, | |
| "eval_mse": 1.248475439073647, | |
| "eval_runtime": 183.4404, | |
| "eval_samples_per_second": 15.918, | |
| "eval_steps_per_second": 3.979, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1767, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2357, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.3708600997924805, | |
| "eval_mse": 1.3708599920592506, | |
| "eval_runtime": 183.3578, | |
| "eval_samples_per_second": 15.925, | |
| "eval_steps_per_second": 3.981, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2e-05, | |
| "loss": 1.3204, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1075, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": 1.2537685632705688, | |
| "eval_mse": 1.2537685594483436, | |
| "eval_runtime": 183.4476, | |
| "eval_samples_per_second": 15.917, | |
| "eval_steps_per_second": 3.979, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4399, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2406, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.19956636428833, | |
| "eval_mse": 1.1995664079472905, | |
| "eval_runtime": 183.4122, | |
| "eval_samples_per_second": 15.92, | |
| "eval_steps_per_second": 3.98, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1667, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2309, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": 1.2671302556991577, | |
| "eval_mse": 1.2671302648346725, | |
| "eval_runtime": 183.2517, | |
| "eval_samples_per_second": 15.934, | |
| "eval_steps_per_second": 3.984, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1541, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 2e-05, | |
| "loss": 1.194, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": 1.4325885772705078, | |
| "eval_mse": 1.4325886574488846, | |
| "eval_runtime": 183.2552, | |
| "eval_samples_per_second": 15.934, | |
| "eval_steps_per_second": 3.984, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1926, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2135, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": 1.176251769065857, | |
| "eval_mse": 1.1762518139201403, | |
| "eval_runtime": 183.5032, | |
| "eval_samples_per_second": 15.913, | |
| "eval_steps_per_second": 3.978, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2e-05, | |
| "loss": 1.111, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2196, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": 1.1438716650009155, | |
| "eval_mse": 1.1438715909390142, | |
| "eval_runtime": 183.3716, | |
| "eval_samples_per_second": 15.924, | |
| "eval_steps_per_second": 3.981, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1891, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1983, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": 1.1710615158081055, | |
| "eval_mse": 1.1710615362599224, | |
| "eval_runtime": 183.5541, | |
| "eval_samples_per_second": 15.908, | |
| "eval_steps_per_second": 3.977, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 821, | |
| "total_flos": 2.448378334121165e+16, | |
| "train_loss": 1.4025647422428107, | |
| "train_runtime": 6674.4502, | |
| "train_samples_per_second": 3.937, | |
| "train_steps_per_second": 0.123 | |
| } | |
| ], | |
| "max_steps": 821, | |
| "num_train_epochs": 1, | |
| "total_flos": 2.448378334121165e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |