| { | |
| "best_metric": 1.8858510255813599, | |
| "best_model_checkpoint": "./lora-redpajama/checkpoint-600", | |
| "epoch": 2.745995423340961, | |
| "global_step": 600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 5.6682, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 5.1317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.1627, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 3.1593, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00015, | |
| "loss": 2.6813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 2.4024, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00020999999999999998, | |
| "loss": 2.3087, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 2.2026, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00027, | |
| "loss": 2.1257, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.0003, | |
| "loss": 2.118, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002945848375451263, | |
| "loss": 2.076, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00028916967509025267, | |
| "loss": 2.0684, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.000283754512635379, | |
| "loss": 2.0212, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00027833935018050537, | |
| "loss": 2.0192, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.00027292418772563177, | |
| "loss": 1.9991, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 0.0002675090252707581, | |
| "loss": 2.0075, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00026209386281588447, | |
| "loss": 2.0414, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 0.0002566787003610108, | |
| "loss": 2.0048, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.00025126353790613716, | |
| "loss": 1.9604, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 0.0002458483754512635, | |
| "loss": 1.9739, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": 2.0006659030914307, | |
| "eval_runtime": 83.0225, | |
| "eval_samples_per_second": 24.09, | |
| "eval_steps_per_second": 0.602, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.00024043321299638986, | |
| "loss": 1.9856, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.00023501805054151624, | |
| "loss": 1.9604, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00022960288808664258, | |
| "loss": 1.9357, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.00022418772563176893, | |
| "loss": 1.9783, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0002187725631768953, | |
| "loss": 1.9581, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.00021335740072202166, | |
| "loss": 1.9507, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.00020794223826714798, | |
| "loss": 1.9258, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.00020252707581227435, | |
| "loss": 1.912, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 0.0001971119133574007, | |
| "loss": 1.9246, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 0.00019169675090252705, | |
| "loss": 1.9106, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 0.00018628158844765343, | |
| "loss": 1.8997, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00018086642599277977, | |
| "loss": 1.8958, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.00017545126353790612, | |
| "loss": 1.8874, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 0.00017003610108303247, | |
| "loss": 1.8956, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 0.00016462093862815885, | |
| "loss": 1.8743, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0001592057761732852, | |
| "loss": 1.875, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00015379061371841152, | |
| "loss": 1.914, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.0001483754512635379, | |
| "loss": 1.8679, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00014296028880866424, | |
| "loss": 1.8845, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 0.00013754512635379062, | |
| "loss": 1.8715, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_loss": 1.9187651872634888, | |
| "eval_runtime": 83.4457, | |
| "eval_samples_per_second": 23.968, | |
| "eval_steps_per_second": 0.599, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.00013212996389891696, | |
| "loss": 1.8722, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.0001267148014440433, | |
| "loss": 1.8782, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.00012129963898916966, | |
| "loss": 1.8651, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 0.00011588447653429602, | |
| "loss": 1.8639, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "learning_rate": 0.00011046931407942237, | |
| "loss": 1.8544, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.00010505415162454872, | |
| "loss": 1.8086, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 9.963898916967508e-05, | |
| "loss": 1.8364, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 9.422382671480144e-05, | |
| "loss": 1.8745, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 8.880866425992779e-05, | |
| "loss": 1.8652, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 8.339350180505415e-05, | |
| "loss": 1.8381, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 7.797833935018049e-05, | |
| "loss": 1.8419, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 7.256317689530685e-05, | |
| "loss": 1.8665, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 6.71480144404332e-05, | |
| "loss": 1.8074, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 6.173285198555956e-05, | |
| "loss": 1.8404, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "learning_rate": 5.6317689530685916e-05, | |
| "loss": 1.8357, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 5.090252707581227e-05, | |
| "loss": 1.8223, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 4.548736462093862e-05, | |
| "loss": 1.8599, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 4.007220216606498e-05, | |
| "loss": 1.8284, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.7, | |
| "learning_rate": 3.4657039711191336e-05, | |
| "loss": 1.871, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.9241877256317685e-05, | |
| "loss": 1.8523, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 1.8858510255813599, | |
| "eval_runtime": 83.601, | |
| "eval_samples_per_second": 23.923, | |
| "eval_steps_per_second": 0.598, | |
| "step": 600 | |
| } | |
| ], | |
| "max_steps": 654, | |
| "num_train_epochs": 3, | |
| "total_flos": 6.234403544225546e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |