| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.136986301369863, | |
| "global_step": 390, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 1.3901418447494507, | |
| "eval_runtime": 108.6518, | |
| "eval_samples_per_second": 1.555, | |
| "eval_steps_per_second": 0.396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3304, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": 1.3154278993606567, | |
| "eval_runtime": 108.7121, | |
| "eval_samples_per_second": 1.555, | |
| "eval_steps_per_second": 0.396, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2138, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.2570539712905884, | |
| "eval_runtime": 108.5686, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2281, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": 1.237758994102478, | |
| "eval_runtime": 108.8506, | |
| "eval_samples_per_second": 1.553, | |
| "eval_steps_per_second": 0.395, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2155, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": 1.2247029542922974, | |
| "eval_runtime": 108.5608, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 1.1823, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": 1.2180429697036743, | |
| "eval_runtime": 108.7983, | |
| "eval_samples_per_second": 1.553, | |
| "eval_steps_per_second": 0.395, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 1.2289, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": 1.2121814489364624, | |
| "eval_runtime": 108.4495, | |
| "eval_samples_per_second": 1.558, | |
| "eval_steps_per_second": 0.396, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 1.1623, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": 1.2073330879211426, | |
| "eval_runtime": 108.7996, | |
| "eval_samples_per_second": 1.553, | |
| "eval_steps_per_second": 0.395, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 1.2067, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": 1.204315423965454, | |
| "eval_runtime": 108.8942, | |
| "eval_samples_per_second": 1.552, | |
| "eval_steps_per_second": 0.395, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 1.1499, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": 1.2012346982955933, | |
| "eval_runtime": 108.7573, | |
| "eval_samples_per_second": 1.554, | |
| "eval_steps_per_second": 0.395, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 1.2184, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": 1.200089454650879, | |
| "eval_runtime": 108.5135, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.1758, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": 1.1969162225723267, | |
| "eval_runtime": 108.562, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.1931, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": 1.1960800886154175, | |
| "eval_runtime": 108.6308, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 1.1334, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": 1.1931264400482178, | |
| "eval_runtime": 108.6207, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 1.1321, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": 1.1918461322784424, | |
| "eval_runtime": 108.4723, | |
| "eval_samples_per_second": 1.558, | |
| "eval_steps_per_second": 0.396, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 1.181, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": 1.1898659467697144, | |
| "eval_runtime": 108.5621, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 1.2347, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": 1.1882331371307373, | |
| "eval_runtime": 108.6542, | |
| "eval_samples_per_second": 1.555, | |
| "eval_steps_per_second": 0.396, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 1.0926, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": 1.1871733665466309, | |
| "eval_runtime": 108.5395, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 1.1425, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.4877, | |
| "eval_samples_per_second": 1.558, | |
| "eval_steps_per_second": 0.396, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 1.128, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.7001, | |
| "eval_samples_per_second": 1.555, | |
| "eval_steps_per_second": 0.396, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 1.1237, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.5929, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 1.0939, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.8988, | |
| "eval_samples_per_second": 1.552, | |
| "eval_steps_per_second": 0.395, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 1.093, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.817, | |
| "eval_samples_per_second": 1.553, | |
| "eval_steps_per_second": 0.395, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.0988, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.6088, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 1.1054, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.4026, | |
| "eval_samples_per_second": 1.559, | |
| "eval_steps_per_second": 0.397, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 1.1051, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.6345, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 1.1373, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.873, | |
| "eval_samples_per_second": 1.552, | |
| "eval_steps_per_second": 0.395, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 1.119, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.5863, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 1.1399, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.7422, | |
| "eval_samples_per_second": 1.554, | |
| "eval_steps_per_second": 0.395, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 1.0744, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.7961, | |
| "eval_samples_per_second": 1.553, | |
| "eval_steps_per_second": 0.395, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 1.0797, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.4529, | |
| "eval_samples_per_second": 1.558, | |
| "eval_steps_per_second": 0.396, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 1.1281, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.354, | |
| "eval_samples_per_second": 1.56, | |
| "eval_steps_per_second": 0.397, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 1.073, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.3772, | |
| "eval_samples_per_second": 1.559, | |
| "eval_steps_per_second": 0.397, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 1.1053, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.3166, | |
| "eval_samples_per_second": 1.56, | |
| "eval_steps_per_second": 0.397, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 1.1402, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.4029, | |
| "eval_samples_per_second": 1.559, | |
| "eval_steps_per_second": 0.397, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 1.1627, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_loss": 1.1867098808288574, | |
| "eval_runtime": 108.4859, | |
| "eval_samples_per_second": 1.558, | |
| "eval_steps_per_second": 0.396, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 1.1064, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "eval_loss": 1.1901580095291138, | |
| "eval_runtime": 108.5309, | |
| "eval_samples_per_second": 1.557, | |
| "eval_steps_per_second": 0.396, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 1.0264, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "eval_loss": 1.187896966934204, | |
| "eval_runtime": 108.3764, | |
| "eval_samples_per_second": 1.559, | |
| "eval_steps_per_second": 0.397, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 1.1384, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_loss": 1.1920827627182007, | |
| "eval_runtime": 108.625, | |
| "eval_samples_per_second": 1.556, | |
| "eval_steps_per_second": 0.396, | |
| "step": 390 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 6, | |
| "total_flos": 6.601561671204864e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |