| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 20.0, | |
| "global_step": 7660, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.9878163251157847e-05, | |
| "loss": 2.5054, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3042960166931152, | |
| "eval_runtime": 6.5074, | |
| "eval_samples_per_second": 941.694, | |
| "eval_steps_per_second": 14.752, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.9513096703453338e-05, | |
| "loss": 2.3885, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.2446680068969727, | |
| "eval_runtime": 6.5762, | |
| "eval_samples_per_second": 931.841, | |
| "eval_steps_per_second": 14.598, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 1.8913786142751957e-05, | |
| "loss": 2.3418, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.231914758682251, | |
| "eval_runtime": 6.5679, | |
| "eval_samples_per_second": 933.023, | |
| "eval_steps_per_second": 14.617, | |
| "step": 1149 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.809498858405589e-05, | |
| "loss": 2.3045, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 2.188257932662964, | |
| "eval_runtime": 6.6128, | |
| "eval_samples_per_second": 926.691, | |
| "eval_steps_per_second": 14.517, | |
| "step": 1532 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 1.7076865540693534e-05, | |
| "loss": 2.2772, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 2.189318895339966, | |
| "eval_runtime": 6.8537, | |
| "eval_samples_per_second": 894.11, | |
| "eval_steps_per_second": 14.007, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 1.588448658094913e-05, | |
| "loss": 2.2543, | |
| "step": 2298 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 2.168344736099243, | |
| "eval_runtime": 6.7894, | |
| "eval_samples_per_second": 902.58, | |
| "eval_steps_per_second": 14.14, | |
| "step": 2298 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 1.4547212032090465e-05, | |
| "loss": 2.2308, | |
| "step": 2681 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 2.1453945636749268, | |
| "eval_runtime": 6.5512, | |
| "eval_samples_per_second": 935.407, | |
| "eval_steps_per_second": 14.654, | |
| "step": 2681 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.3097970031670223e-05, | |
| "loss": 2.2139, | |
| "step": 3064 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 2.1402783393859863, | |
| "eval_runtime": 6.5858, | |
| "eval_samples_per_second": 930.487, | |
| "eval_steps_per_second": 14.577, | |
| "step": 3064 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 1.1572445727497194e-05, | |
| "loss": 2.2008, | |
| "step": 3447 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 2.11649489402771, | |
| "eval_runtime": 6.5807, | |
| "eval_samples_per_second": 931.208, | |
| "eval_steps_per_second": 14.588, | |
| "step": 3447 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 1.0008202590865013e-05, | |
| "loss": 2.1937, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 2.1280927658081055, | |
| "eval_runtime": 6.6743, | |
| "eval_samples_per_second": 918.143, | |
| "eval_steps_per_second": 14.383, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 8.443757479222894e-06, | |
| "loss": 2.1778, | |
| "step": 4213 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 2.1188840866088867, | |
| "eval_runtime": 6.8275, | |
| "eval_samples_per_second": 897.543, | |
| "eval_steps_per_second": 14.061, | |
| "step": 4213 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 6.917632223315125e-06, | |
| "loss": 2.1742, | |
| "step": 4596 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.121837854385376, | |
| "eval_runtime": 6.6231, | |
| "eval_samples_per_second": 925.24, | |
| "eval_steps_per_second": 14.495, | |
| "step": 4596 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 5.467405091861484e-06, | |
| "loss": 2.1611, | |
| "step": 4979 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.099580764770508, | |
| "eval_runtime": 6.7959, | |
| "eval_samples_per_second": 901.723, | |
| "eval_steps_per_second": 14.126, | |
| "step": 4979 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "learning_rate": 4.12878548986627e-06, | |
| "loss": 2.1562, | |
| "step": 5362 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.099181890487671, | |
| "eval_runtime": 6.8991, | |
| "eval_samples_per_second": 888.236, | |
| "eval_steps_per_second": 13.915, | |
| "step": 5362 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 2.934734674554366e-06, | |
| "loss": 2.1508, | |
| "step": 5745 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 2.1012661457061768, | |
| "eval_runtime": 6.8384, | |
| "eval_samples_per_second": 896.11, | |
| "eval_steps_per_second": 14.038, | |
| "step": 5745 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 1.9146541398261966e-06, | |
| "loss": 2.1469, | |
| "step": 6128 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 2.094507932662964, | |
| "eval_runtime": 6.7332, | |
| "eval_samples_per_second": 910.114, | |
| "eval_steps_per_second": 14.258, | |
| "step": 6128 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "learning_rate": 1.0936616538999777e-06, | |
| "loss": 2.1437, | |
| "step": 6511 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_loss": 2.089902639389038, | |
| "eval_runtime": 6.6174, | |
| "eval_samples_per_second": 926.05, | |
| "eval_steps_per_second": 14.507, | |
| "step": 6511 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "learning_rate": 4.919727764970517e-07, | |
| "loss": 2.1436, | |
| "step": 6894 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_loss": 2.082735061645508, | |
| "eval_runtime": 6.5958, | |
| "eval_samples_per_second": 929.079, | |
| "eval_steps_per_second": 14.555, | |
| "step": 6894 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "learning_rate": 1.2440308466997952e-07, | |
| "loss": 2.1443, | |
| "step": 7277 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_loss": 2.0934832096099854, | |
| "eval_runtime": 6.5708, | |
| "eval_samples_per_second": 932.611, | |
| "eval_steps_per_second": 14.61, | |
| "step": 7277 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.3641254104654906e-12, | |
| "loss": 2.1389, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_loss": 2.0939252376556396, | |
| "eval_runtime": 6.5634, | |
| "eval_samples_per_second": 933.664, | |
| "eval_steps_per_second": 14.627, | |
| "step": 7660 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 7660, | |
| "total_flos": 3.24907393591296e+16, | |
| "train_loss": 2.2224227227990374, | |
| "train_runtime": 2024.9575, | |
| "train_samples_per_second": 242.079, | |
| "train_steps_per_second": 3.783 | |
| } | |
| ], | |
| "max_steps": 7660, | |
| "num_train_epochs": 20, | |
| "total_flos": 3.24907393591296e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |