| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 665, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0009849624060150376, | |
| "loss": 1.0885, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0009699248120300752, | |
| "loss": 1.028, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0009548872180451129, | |
| "loss": 0.97, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0009398496240601504, | |
| "loss": 0.8525, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.000924812030075188, | |
| "loss": 0.8267, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.0009097744360902256, | |
| "loss": 0.7703, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0008947368421052632, | |
| "loss": 0.7238, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0008796992481203007, | |
| "loss": 0.7592, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 0.0008646616541353384, | |
| "loss": 0.7658, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.000849624060150376, | |
| "loss": 0.7197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0008345864661654136, | |
| "loss": 0.7101, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.0008195488721804511, | |
| "loss": 0.7549, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0008045112781954887, | |
| "loss": 0.6945, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0007894736842105263, | |
| "loss": 0.6607, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 0.000774436090225564, | |
| "loss": 0.6256, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0007593984962406016, | |
| "loss": 0.5617, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0007443609022556391, | |
| "loss": 0.5822, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 0.0007293233082706767, | |
| "loss": 0.6355, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 0.0007142857142857143, | |
| "loss": 0.6236, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.0006992481203007519, | |
| "loss": 0.6361, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.0006842105263157895, | |
| "loss": 0.6258, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 0.0006691729323308271, | |
| "loss": 0.6211, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.0006541353383458647, | |
| "loss": 0.5467, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0006390977443609023, | |
| "loss": 0.5651, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 0.0006240601503759398, | |
| "loss": 0.5344, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0006090225563909775, | |
| "loss": 0.4808, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0005939849624060151, | |
| "loss": 0.4835, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 0.0005789473684210527, | |
| "loss": 0.3901, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.18, | |
| "learning_rate": 0.0005639097744360903, | |
| "loss": 0.4705, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.26, | |
| "learning_rate": 0.0005488721804511278, | |
| "loss": 0.4504, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 0.0005338345864661654, | |
| "loss": 0.4119, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 0.0005187969924812031, | |
| "loss": 0.4303, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 0.0005037593984962407, | |
| "loss": 0.4437, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 0.0004887218045112781, | |
| "loss": 0.4096, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 0.00047368421052631577, | |
| "loss": 0.381, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 0.00045864661654135334, | |
| "loss": 0.3711, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 0.000443609022556391, | |
| "loss": 0.3948, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.00042857142857142855, | |
| "loss": 0.3547, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.93, | |
| "learning_rate": 0.0004135338345864661, | |
| "loss": 0.3901, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 0.00039849624060150376, | |
| "loss": 0.4044, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "learning_rate": 0.00038345864661654133, | |
| "loss": 0.3684, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "learning_rate": 0.00036842105263157896, | |
| "loss": 0.2573, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 3.23, | |
| "learning_rate": 0.00035338345864661654, | |
| "loss": 0.2689, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 3.31, | |
| "learning_rate": 0.0003383458646616541, | |
| "loss": 0.3602, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 3.38, | |
| "learning_rate": 0.00032330827067669174, | |
| "loss": 0.3268, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.46, | |
| "learning_rate": 0.0003082706766917293, | |
| "loss": 0.3209, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 0.0002932330827067669, | |
| "loss": 0.3209, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 3.61, | |
| "learning_rate": 0.0002781954887218045, | |
| "loss": 0.3551, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 0.3508, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "learning_rate": 0.0002481203007518797, | |
| "loss": 0.3245, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.83, | |
| "learning_rate": 0.00023308270676691728, | |
| "loss": 0.3305, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 3.91, | |
| "learning_rate": 0.00021804511278195488, | |
| "loss": 0.2589, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 3.98, | |
| "learning_rate": 0.00020300751879699248, | |
| "loss": 0.28, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 0.00018796992481203006, | |
| "loss": 0.2616, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "learning_rate": 0.00017293233082706766, | |
| "loss": 0.2456, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.21, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 0.2407, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 4.29, | |
| "learning_rate": 0.00014285714285714284, | |
| "loss": 0.3143, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "learning_rate": 0.00012781954887218044, | |
| "loss": 0.204, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 0.00011278195488721805, | |
| "loss": 0.2682, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 4.51, | |
| "learning_rate": 9.774436090225564e-05, | |
| "loss": 0.2864, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "learning_rate": 8.270676691729323e-05, | |
| "loss": 0.208, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 4.66, | |
| "learning_rate": 6.766917293233083e-05, | |
| "loss": 0.2753, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 4.74, | |
| "learning_rate": 5.263157894736842e-05, | |
| "loss": 0.2745, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 3.759398496240601e-05, | |
| "loss": 0.2303, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 2.255639097744361e-05, | |
| "loss": 0.279, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 7.518796992481203e-06, | |
| "loss": 0.2759, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 665, | |
| "total_flos": 24952435630080.0, | |
| "train_loss": 0.47780078264107384, | |
| "train_runtime": 10.6583, | |
| "train_samples_per_second": 1983.424, | |
| "train_steps_per_second": 62.392 | |
| } | |
| ], | |
| "max_steps": 665, | |
| "num_train_epochs": 5, | |
| "total_flos": 24952435630080.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |