| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 16.0, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.978494623655914e-05, | |
| "loss": 2.3806, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.956989247311828e-05, | |
| "loss": 2.2445, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.935483870967742e-05, | |
| "loss": 1.9394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 1.9150537634408603e-05, | |
| "loss": 1.7953, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 1.8935483870967742e-05, | |
| "loss": 1.6449, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.8720430107526882e-05, | |
| "loss": 1.4618, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.8505376344086025e-05, | |
| "loss": 1.2538, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 1.8290322580645165e-05, | |
| "loss": 1.0844, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.8075268817204305e-05, | |
| "loss": 0.9909, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 1.7860215053763444e-05, | |
| "loss": 0.9419, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 1.764516129032258e-05, | |
| "loss": 0.8202, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 1.743010752688172e-05, | |
| "loss": 0.7706, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 1.721505376344086e-05, | |
| "loss": 0.7102, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 1.7e-05, | |
| "loss": 0.6723, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 1.678494623655914e-05, | |
| "loss": 0.6262, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 1.656989247311828e-05, | |
| "loss": 0.5895, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 1.6354838709677422e-05, | |
| "loss": 0.5636, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 1.6139784946236562e-05, | |
| "loss": 0.5095, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 1.5924731182795702e-05, | |
| "loss": 0.5093, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 1.570967741935484e-05, | |
| "loss": 0.4729, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 1.549462365591398e-05, | |
| "loss": 0.4805, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 1.527956989247312e-05, | |
| "loss": 0.4508, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 1.5064516129032259e-05, | |
| "loss": 0.4254, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 1.4849462365591399e-05, | |
| "loss": 0.4104, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 1.4634408602150539e-05, | |
| "loss": 0.4135, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 1.4419354838709678e-05, | |
| "loss": 0.3828, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 1.4204301075268818e-05, | |
| "loss": 0.3924, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 1.3989247311827958e-05, | |
| "loss": 0.3782, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 1.3774193548387098e-05, | |
| "loss": 0.3569, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 1.3559139784946237e-05, | |
| "loss": 0.3609, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 1.3344086021505379e-05, | |
| "loss": 0.3385, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 1.3129032258064518e-05, | |
| "loss": 0.3246, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 1.2913978494623658e-05, | |
| "loss": 0.3229, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 1.2698924731182796e-05, | |
| "loss": 0.3051, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 1.2483870967741936e-05, | |
| "loss": 0.3159, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 1.2268817204301076e-05, | |
| "loss": 0.2884, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 1.2053763440860215e-05, | |
| "loss": 0.2976, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 1.1838709677419355e-05, | |
| "loss": 0.2934, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 1.1623655913978495e-05, | |
| "loss": 0.2739, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 1.1408602150537636e-05, | |
| "loss": 0.2807, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 1.1193548387096776e-05, | |
| "loss": 0.2593, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 1.0978494623655916e-05, | |
| "loss": 0.2589, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 1.0763440860215055e-05, | |
| "loss": 0.2679, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 1.0548387096774195e-05, | |
| "loss": 0.2463, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 1.0333333333333335e-05, | |
| "loss": 0.2435, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 1.0118279569892473e-05, | |
| "loss": 0.2469, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 9.903225806451614e-06, | |
| "loss": 0.2406, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 9.688172043010754e-06, | |
| "loss": 0.2231, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 9.473118279569892e-06, | |
| "loss": 0.2317, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 9.258064516129034e-06, | |
| "loss": 0.2305, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 1860, | |
| "num_train_epochs": 30, | |
| "total_flos": 5.1982555742208e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |