| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3373534620899047, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-05, | |
| "loss": 0.676, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6731, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6757, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6726, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6734, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6718, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6678, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6683, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6735, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6669, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6719, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6684, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6675, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6806, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6743, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6735, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6739, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6739, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6761, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6714, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6707, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6651, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6757, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6759, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6698, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6687, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6697, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6678, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6604, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6669, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6655, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6569, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6666, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6647, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6612, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6616, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6607, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6596, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6542, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6606, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5e-05, | |
| "loss": 0.654, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6631, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6558, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6498, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6728, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6649, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6569, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6582, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6484, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6476, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6505, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6523, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6521, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6467, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6628, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6523, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 5e-05, | |
| "loss": 0.655, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6496, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6498, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6498, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6542, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6445, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6511, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6482, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6462, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6623, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6473, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5e-05, | |
| "loss": 0.651, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6453, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6508, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6541, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6526, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6391, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6467, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6505, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6405, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6533, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6432, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6448, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6361, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6416, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6381, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6461, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6439, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6433, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6468, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6507, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6481, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6442, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6384, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6418, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6505, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 0.637, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6381, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6377, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6737, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5e-05, | |
| "loss": 0.64, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5e-05, | |
| "loss": 0.641, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 8892, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |