Instructions to use bboeun/sft2-Delayed2-ref-mistral-fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bboeun/sft2-Delayed2-ref-mistral-fix with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model = PeftModel.from_pretrained(base_model, "bboeun/sft2-Delayed2-ref-mistral-fix") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4.9840000000000004e-05, | |
| "loss": 4.7991, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9640000000000006e-05, | |
| "loss": 4.4063, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.944e-05, | |
| "loss": 3.8331, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.924e-05, | |
| "loss": 2.8485, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.9040000000000005e-05, | |
| "loss": 2.5842, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.884e-05, | |
| "loss": 2.3857, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.864e-05, | |
| "loss": 2.2079, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.8440000000000004e-05, | |
| "loss": 2.2818, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.824e-05, | |
| "loss": 2.1391, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.804e-05, | |
| "loss": 2.1858, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.784e-05, | |
| "loss": 2.1695, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.7640000000000005e-05, | |
| "loss": 2.0576, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.744e-05, | |
| "loss": 2.0989, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.724e-05, | |
| "loss": 2.0584, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.7040000000000004e-05, | |
| "loss": 2.0516, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.684e-05, | |
| "loss": 2.0031, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.664e-05, | |
| "loss": 2.0133, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.644e-05, | |
| "loss": 2.027, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.624e-05, | |
| "loss": 2.0238, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.606e-05, | |
| "loss": 2.0607, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.5860000000000005e-05, | |
| "loss": 2.1364, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.566e-05, | |
| "loss": 2.0829, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.546e-05, | |
| "loss": 2.2079, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.5260000000000004e-05, | |
| "loss": 1.9552, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.506e-05, | |
| "loss": 2.0141, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.486e-05, | |
| "loss": 1.9904, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.466e-05, | |
| "loss": 1.9627, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.4460000000000005e-05, | |
| "loss": 2.0108, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.426e-05, | |
| "loss": 1.9851, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.406e-05, | |
| "loss": 2.1354, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.3860000000000004e-05, | |
| "loss": 2.0532, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.366e-05, | |
| "loss": 2.0449, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.346e-05, | |
| "loss": 1.9925, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.326e-05, | |
| "loss": 2.0868, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.306e-05, | |
| "loss": 2.0281, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.286e-05, | |
| "loss": 1.9509, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.266e-05, | |
| "loss": 2.0431, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.246e-05, | |
| "loss": 1.917, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.226e-05, | |
| "loss": 2.0301, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.206e-05, | |
| "loss": 1.8611, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.186e-05, | |
| "loss": 1.8227, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1660000000000004e-05, | |
| "loss": 1.9631, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.1460000000000006e-05, | |
| "loss": 1.954, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.126e-05, | |
| "loss": 1.9286, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.106e-05, | |
| "loss": 2.0062, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.0860000000000005e-05, | |
| "loss": 2.0218, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.066e-05, | |
| "loss": 2.0331, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.046e-05, | |
| "loss": 1.8572, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0260000000000004e-05, | |
| "loss": 2.0023, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.0060000000000006e-05, | |
| "loss": 2.1018, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 3.986e-05, | |
| "loss": 1.8793, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.966e-05, | |
| "loss": 1.9712, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 3.9460000000000005e-05, | |
| "loss": 1.9055, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.926e-05, | |
| "loss": 1.9317, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.906e-05, | |
| "loss": 2.0175, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.8860000000000004e-05, | |
| "loss": 1.9598, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.866e-05, | |
| "loss": 1.9828, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.846e-05, | |
| "loss": 1.9153, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.826e-05, | |
| "loss": 1.8578, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.806e-05, | |
| "loss": 1.9993, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.786e-05, | |
| "loss": 1.8577, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.766e-05, | |
| "loss": 1.9251, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 3.7460000000000004e-05, | |
| "loss": 1.8683, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.726e-05, | |
| "loss": 1.9517, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.706e-05, | |
| "loss": 1.8613, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 3.686e-05, | |
| "loss": 1.8133, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.666e-05, | |
| "loss": 1.8165, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 3.646e-05, | |
| "loss": 1.7916, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.626e-05, | |
| "loss": 1.7016, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.606e-05, | |
| "loss": 1.7513, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 3.586e-05, | |
| "loss": 1.7839, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.566e-05, | |
| "loss": 1.8013, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 3.546e-05, | |
| "loss": 1.7298, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.5260000000000005e-05, | |
| "loss": 1.7424, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.5060000000000007e-05, | |
| "loss": 1.6861, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 3.486e-05, | |
| "loss": 1.7022, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4660000000000004e-05, | |
| "loss": 1.7965, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 3.4460000000000005e-05, | |
| "loss": 1.7315, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.426e-05, | |
| "loss": 1.7057, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.406e-05, | |
| "loss": 1.8009, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 3.3860000000000004e-05, | |
| "loss": 1.7931, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.366e-05, | |
| "loss": 1.664, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.346e-05, | |
| "loss": 1.7098, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3260000000000003e-05, | |
| "loss": 1.7413, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.3060000000000005e-05, | |
| "loss": 1.7604, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 3.286e-05, | |
| "loss": 1.7232, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.266e-05, | |
| "loss": 1.7531, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 3.2460000000000004e-05, | |
| "loss": 1.7535, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.226e-05, | |
| "loss": 1.7284, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.206e-05, | |
| "loss": 1.7321, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 3.186e-05, | |
| "loss": 1.7222, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.166e-05, | |
| "loss": 1.7226, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 3.146e-05, | |
| "loss": 1.7156, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.126e-05, | |
| "loss": 1.7291, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.106e-05, | |
| "loss": 1.7604, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.086e-05, | |
| "loss": 1.6752, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.066e-05, | |
| "loss": 1.6983, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 3.046e-05, | |
| "loss": 1.6599, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.0259999999999998e-05, | |
| "loss": 1.7848, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 3.006e-05, | |
| "loss": 1.7583, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 2.986e-05, | |
| "loss": 1.6887, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.9659999999999997e-05, | |
| "loss": 1.6829, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 2.946e-05, | |
| "loss": 1.5917, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9260000000000004e-05, | |
| "loss": 1.6951, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.9060000000000003e-05, | |
| "loss": 1.7579, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 2.8860000000000005e-05, | |
| "loss": 1.7073, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8660000000000003e-05, | |
| "loss": 1.6211, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.8460000000000002e-05, | |
| "loss": 1.6521, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8260000000000004e-05, | |
| "loss": 1.758, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.8060000000000002e-05, | |
| "loss": 1.7321, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 2.7860000000000004e-05, | |
| "loss": 1.7187, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.7660000000000003e-05, | |
| "loss": 1.7101, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 2.746e-05, | |
| "loss": 1.6314, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7260000000000003e-05, | |
| "loss": 1.794, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.7060000000000002e-05, | |
| "loss": 1.7144, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.686e-05, | |
| "loss": 1.7711, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.6660000000000002e-05, | |
| "loss": 1.7436, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.646e-05, | |
| "loss": 1.6836, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.6260000000000003e-05, | |
| "loss": 1.7399, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.606e-05, | |
| "loss": 1.7628, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.586e-05, | |
| "loss": 1.7708, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.566e-05, | |
| "loss": 1.7114, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.546e-05, | |
| "loss": 1.5984, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.526e-05, | |
| "loss": 1.7057, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.506e-05, | |
| "loss": 1.7779, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 2.486e-05, | |
| "loss": 1.6984, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.466e-05, | |
| "loss": 1.7017, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 2.4460000000000003e-05, | |
| "loss": 1.7408, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.426e-05, | |
| "loss": 1.7441, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.4060000000000003e-05, | |
| "loss": 1.6177, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 2.3860000000000002e-05, | |
| "loss": 1.7621, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.366e-05, | |
| "loss": 1.6717, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 2.3460000000000002e-05, | |
| "loss": 1.6861, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.326e-05, | |
| "loss": 1.707, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.306e-05, | |
| "loss": 1.7853, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 2.286e-05, | |
| "loss": 1.744, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.266e-05, | |
| "loss": 1.7309, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 2.2460000000000002e-05, | |
| "loss": 1.6741, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.226e-05, | |
| "loss": 1.6597, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.206e-05, | |
| "loss": 1.7398, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 2.186e-05, | |
| "loss": 1.7266, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.166e-05, | |
| "loss": 1.667, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 2.146e-05, | |
| "loss": 1.7571, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1260000000000003e-05, | |
| "loss": 1.7637, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.106e-05, | |
| "loss": 1.6878, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.086e-05, | |
| "loss": 1.694, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.0660000000000002e-05, | |
| "loss": 1.6909, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 2.046e-05, | |
| "loss": 1.7218, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.0260000000000003e-05, | |
| "loss": 1.6519, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.006e-05, | |
| "loss": 1.5711, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.986e-05, | |
| "loss": 1.7072, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.966e-05, | |
| "loss": 1.6743, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.946e-05, | |
| "loss": 1.8284, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.9260000000000002e-05, | |
| "loss": 1.7596, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.906e-05, | |
| "loss": 1.6365, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.886e-05, | |
| "loss": 1.6961, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.866e-05, | |
| "loss": 1.7091, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.846e-05, | |
| "loss": 1.6835, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.826e-05, | |
| "loss": 1.7597, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.8060000000000003e-05, | |
| "loss": 1.7119, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.7860000000000002e-05, | |
| "loss": 1.6979, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.766e-05, | |
| "loss": 1.6685, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.7460000000000002e-05, | |
| "loss": 1.6231, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.726e-05, | |
| "loss": 1.6583, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.706e-05, | |
| "loss": 1.7673, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.686e-05, | |
| "loss": 1.7094, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.666e-05, | |
| "loss": 1.7663, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.646e-05, | |
| "loss": 1.6688, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.626e-05, | |
| "loss": 1.7058, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.606e-05, | |
| "loss": 1.705, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.586e-05, | |
| "loss": 1.7562, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.566e-05, | |
| "loss": 1.7273, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.546e-05, | |
| "loss": 1.7069, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5260000000000003e-05, | |
| "loss": 1.6405, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.5060000000000001e-05, | |
| "loss": 1.6771, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 1.4860000000000002e-05, | |
| "loss": 1.7157, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4660000000000002e-05, | |
| "loss": 1.6899, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.4460000000000002e-05, | |
| "loss": 1.7271, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.426e-05, | |
| "loss": 1.7838, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.4060000000000001e-05, | |
| "loss": 1.802, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 1.3860000000000001e-05, | |
| "loss": 1.7144, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.3660000000000001e-05, | |
| "loss": 1.7215, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.346e-05, | |
| "loss": 1.6961, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.326e-05, | |
| "loss": 1.6575, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.306e-05, | |
| "loss": 1.697, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 1.286e-05, | |
| "loss": 1.6385, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2659999999999999e-05, | |
| "loss": 1.7265, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2460000000000001e-05, | |
| "loss": 1.7385, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2260000000000001e-05, | |
| "loss": 1.6288, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.206e-05, | |
| "loss": 1.7478, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.186e-05, | |
| "loss": 1.6661, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.166e-05, | |
| "loss": 1.6749, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 1.146e-05, | |
| "loss": 1.6919, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.126e-05, | |
| "loss": 1.7477, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.106e-05, | |
| "loss": 1.7278, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.0860000000000001e-05, | |
| "loss": 1.7192, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.0660000000000001e-05, | |
| "loss": 1.6794, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.046e-05, | |
| "loss": 1.7545, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.026e-05, | |
| "loss": 1.7377, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.006e-05, | |
| "loss": 1.663, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 3.632950229815296e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |