| { |
| "best_metric": 0.33089256286621094, |
| "best_model_checkpoint": "/content/drive/My Drive/Colab Data/LLaMA-LoRA Tuner/lora_models/guitarGPT0/checkpoint-900", |
| "epoch": 1.9313304721030042, |
| "global_step": 900, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 0.7034, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 0.7056, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 8.999999999999999e-05, |
| "loss": 0.6413, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00011999999999999999, |
| "loss": 0.574, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00015, |
| "loss": 0.5307, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00017999999999999998, |
| "loss": 0.4797, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.00020999999999999998, |
| "loss": 0.4554, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.00023999999999999998, |
| "loss": 0.4219, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00027, |
| "loss": 0.4163, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0003, |
| "loss": 0.4183, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00029987068965517237, |
| "loss": 0.3947, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.0002997413793103448, |
| "loss": 0.413, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0002996120689655172, |
| "loss": 0.4028, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00029948275862068965, |
| "loss": 0.3807, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.00029935344827586205, |
| "loss": 0.3982, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00029922413793103444, |
| "loss": 0.3907, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0002990948275862069, |
| "loss": 0.391, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.0002989655172413793, |
| "loss": 0.3807, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0002988362068965517, |
| "loss": 0.3735, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.0002987068965517241, |
| "loss": 0.4056, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0002985775862068965, |
| "loss": 0.3732, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00029844827586206896, |
| "loss": 0.3873, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00029831896551724135, |
| "loss": 0.3421, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00029818965517241375, |
| "loss": 0.3708, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0002980603448275862, |
| "loss": 0.371, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.0002979310344827586, |
| "loss": 0.3747, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00029780172413793103, |
| "loss": 0.3608, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.0002976724137931034, |
| "loss": 0.3559, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.0002975431034482758, |
| "loss": 0.3838, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00029741379310344827, |
| "loss": 0.3587, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 0.36829814314842224, |
| "eval_runtime": 676.778, |
| "eval_samples_per_second": 3.398, |
| "eval_steps_per_second": 0.426, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00029728448275862066, |
| "loss": 0.3585, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00029715517241379305, |
| "loss": 0.3536, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.0002970258620689655, |
| "loss": 0.3721, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.0002968965517241379, |
| "loss": 0.37, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00029676724137931034, |
| "loss": 0.3738, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.00029663793103448273, |
| "loss": 0.3542, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0002965086206896552, |
| "loss": 0.378, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00029637931034482757, |
| "loss": 0.3443, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00029624999999999996, |
| "loss": 0.3484, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00029612068965517236, |
| "loss": 0.35, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0002959913793103448, |
| "loss": 0.3622, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.0002958620689655172, |
| "loss": 0.3479, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00029573275862068964, |
| "loss": 0.3535, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00029560344827586204, |
| "loss": 0.3547, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0002954741379310345, |
| "loss": 0.365, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.0002953448275862069, |
| "loss": 0.3292, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00029521551724137927, |
| "loss": 0.3377, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.0002950862068965517, |
| "loss": 0.349, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.0002949568965517241, |
| "loss": 0.3638, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.0002948275862068965, |
| "loss": 0.3488, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00029469827586206895, |
| "loss": 0.3438, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00029456896551724134, |
| "loss": 0.3367, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.0002944396551724138, |
| "loss": 0.364, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0002943103448275862, |
| "loss": 0.3557, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00029418103448275863, |
| "loss": 0.3513, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.000294051724137931, |
| "loss": 0.3519, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.0002939224137931034, |
| "loss": 0.341, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.0002937931034482758, |
| "loss": 0.3404, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00029366379310344826, |
| "loss": 0.3381, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00029353448275862065, |
| "loss": 0.347, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.29, |
| "eval_loss": 0.3440234959125519, |
| "eval_runtime": 676.8128, |
| "eval_samples_per_second": 3.398, |
| "eval_steps_per_second": 0.426, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.0002934051724137931, |
| "loss": 0.3377, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.0002932758620689655, |
| "loss": 0.3573, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00029314655172413794, |
| "loss": 0.3264, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.00029301724137931033, |
| "loss": 0.3458, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0002928879310344827, |
| "loss": 0.3432, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.0002927586206896551, |
| "loss": 0.3321, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.00029262931034482756, |
| "loss": 0.3396, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00029249999999999995, |
| "loss": 0.3314, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0002923706896551724, |
| "loss": 0.3389, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.0002922413793103448, |
| "loss": 0.3194, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00029211206896551724, |
| "loss": 0.3379, |
| "step": 710 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.00029198275862068963, |
| "loss": 0.3546, |
| "step": 720 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.0002918534482758621, |
| "loss": 0.3146, |
| "step": 730 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.0002917241379310344, |
| "loss": 0.3381, |
| "step": 740 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.00029159482758620687, |
| "loss": 0.3165, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00029146551724137926, |
| "loss": 0.3372, |
| "step": 760 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.0002913362068965517, |
| "loss": 0.3452, |
| "step": 770 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.0002912068965517241, |
| "loss": 0.3549, |
| "step": 780 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.00029107758620689655, |
| "loss": 0.3149, |
| "step": 790 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.00029094827586206894, |
| "loss": 0.3278, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.0002908189655172414, |
| "loss": 0.3432, |
| "step": 810 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.0002906896551724138, |
| "loss": 0.3475, |
| "step": 820 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.00029056034482758617, |
| "loss": 0.3271, |
| "step": 830 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.00029043103448275857, |
| "loss": 0.3298, |
| "step": 840 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.000290301724137931, |
| "loss": 0.3247, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.0002901724137931034, |
| "loss": 0.324, |
| "step": 860 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 0.00029004310344827585, |
| "loss": 0.3015, |
| "step": 870 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.00028991379310344825, |
| "loss": 0.322, |
| "step": 880 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.0002897844827586207, |
| "loss": 0.3127, |
| "step": 890 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.0002896551724137931, |
| "loss": 0.3205, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.93, |
| "eval_loss": 0.33089256286621094, |
| "eval_runtime": 676.8619, |
| "eval_samples_per_second": 3.398, |
| "eval_steps_per_second": 0.425, |
| "step": 900 |
| } |
| ], |
| "max_steps": 23300, |
| "num_train_epochs": 50, |
| "total_flos": 1.1550358861932134e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
