| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 48.888888888888886, | |
| "eval_steps": 500, | |
| "global_step": 2200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 3663.33642578125, | |
| "learning_rate": 3.6750000000000003e-07, | |
| "loss": 1356.1239, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 3973.032470703125, | |
| "learning_rate": 7.425000000000001e-07, | |
| "loss": 1275.5178, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 2667.0068359375, | |
| "learning_rate": 1.1174999999999999e-06, | |
| "loss": 1123.6059, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 2320.48486328125, | |
| "learning_rate": 1.4925000000000001e-06, | |
| "loss": 922.8917, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 1611.3345947265625, | |
| "learning_rate": 1.8675000000000001e-06, | |
| "loss": 714.5638, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1395.7064208984375, | |
| "learning_rate": 2.2425e-06, | |
| "loss": 542.1251, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 1019.4860229492188, | |
| "learning_rate": 2.6175e-06, | |
| "loss": 411.1387, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 888.315185546875, | |
| "learning_rate": 2.9925e-06, | |
| "loss": 318.4567, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 2590.113525390625, | |
| "learning_rate": 3.3675000000000004e-06, | |
| "loss": 261.6995, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 711.677734375, | |
| "learning_rate": 3.7425e-06, | |
| "loss": 220.2936, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 12.222222222222221, | |
| "grad_norm": 548.9371948242188, | |
| "learning_rate": 4.117500000000001e-06, | |
| "loss": 187.9833, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 1127.1611328125, | |
| "learning_rate": 4.4925e-06, | |
| "loss": 159.1351, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 14.444444444444445, | |
| "grad_norm": 426.074951171875, | |
| "learning_rate": 4.8675e-06, | |
| "loss": 137.1092, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 15.555555555555555, | |
| "grad_norm": 348.842529296875, | |
| "learning_rate": 5.2425e-06, | |
| "loss": 119.822, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 373.2169189453125, | |
| "learning_rate": 5.6175e-06, | |
| "loss": 104.3366, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 324.51702880859375, | |
| "learning_rate": 5.992500000000001e-06, | |
| "loss": 90.8788, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 18.88888888888889, | |
| "grad_norm": 269.91827392578125, | |
| "learning_rate": 6.3675e-06, | |
| "loss": 78.4644, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1744.54052734375, | |
| "learning_rate": 6.7425e-06, | |
| "loss": 70.3526, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 21.11111111111111, | |
| "grad_norm": 369.39837646484375, | |
| "learning_rate": 7.1175e-06, | |
| "loss": 63.9417, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 303.95977783203125, | |
| "learning_rate": 7.4925e-06, | |
| "loss": 63.4575, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 23.333333333333332, | |
| "grad_norm": 187.462890625, | |
| "learning_rate": 7.8675e-06, | |
| "loss": 54.7417, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 24.444444444444443, | |
| "grad_norm": 165.56666564941406, | |
| "learning_rate": 8.2425e-06, | |
| "loss": 49.6842, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 25.555555555555557, | |
| "grad_norm": 147.3148193359375, | |
| "learning_rate": 8.6175e-06, | |
| "loss": 43.027, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 125.53775024414062, | |
| "learning_rate": 8.9925e-06, | |
| "loss": 38.2579, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 27.77777777777778, | |
| "grad_norm": 109.85810089111328, | |
| "learning_rate": 9.367500000000001e-06, | |
| "loss": 34.3957, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 28.88888888888889, | |
| "grad_norm": 98.328369140625, | |
| "learning_rate": 9.7425e-06, | |
| "loss": 31.4378, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 109.77750396728516, | |
| "learning_rate": 1.01175e-05, | |
| "loss": 28.5084, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 31.11111111111111, | |
| "grad_norm": 112.47483825683594, | |
| "learning_rate": 1.04925e-05, | |
| "loss": 26.1671, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 32.22222222222222, | |
| "grad_norm": 85.60242462158203, | |
| "learning_rate": 1.08675e-05, | |
| "loss": 24.2309, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 33.333333333333336, | |
| "grad_norm": 73.19799041748047, | |
| "learning_rate": 1.1242500000000001e-05, | |
| "loss": 22.6248, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 34.44444444444444, | |
| "grad_norm": 80.70884704589844, | |
| "learning_rate": 1.16175e-05, | |
| "loss": 21.1187, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 35.55555555555556, | |
| "grad_norm": 110.98326110839844, | |
| "learning_rate": 1.19925e-05, | |
| "loss": 20.4828, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 36.666666666666664, | |
| "grad_norm": 113.65286254882812, | |
| "learning_rate": 1.23675e-05, | |
| "loss": 19.7366, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 37.77777777777778, | |
| "grad_norm": 77.65855407714844, | |
| "learning_rate": 1.27425e-05, | |
| "loss": 18.6632, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 38.888888888888886, | |
| "grad_norm": 88.96723175048828, | |
| "learning_rate": 1.3117500000000001e-05, | |
| "loss": 18.0793, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "grad_norm": 79.1690902709961, | |
| "learning_rate": 1.34925e-05, | |
| "loss": 17.0667, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 41.111111111111114, | |
| "grad_norm": 93.60108184814453, | |
| "learning_rate": 1.38675e-05, | |
| "loss": 16.6106, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 42.22222222222222, | |
| "grad_norm": 66.16129302978516, | |
| "learning_rate": 1.4242500000000001e-05, | |
| "loss": 16.4905, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 43.333333333333336, | |
| "grad_norm": 62.41362380981445, | |
| "learning_rate": 1.46175e-05, | |
| "loss": 15.6427, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 44.44444444444444, | |
| "grad_norm": 107.30168151855469, | |
| "learning_rate": 1.4992500000000001e-05, | |
| "loss": 15.0731, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 45.55555555555556, | |
| "grad_norm": 100.18666076660156, | |
| "learning_rate": 1.2060000000000001e-05, | |
| "loss": 14.6973, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 46.666666666666664, | |
| "grad_norm": 68.78209686279297, | |
| "learning_rate": 9.06e-06, | |
| "loss": 13.8928, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 47.77777777777778, | |
| "grad_norm": 65.85958099365234, | |
| "learning_rate": 6.0600000000000004e-06, | |
| "loss": 13.4318, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 48.888888888888886, | |
| "grad_norm": 72.31432342529297, | |
| "learning_rate": 3.06e-06, | |
| "loss": 12.6856, | |
| "step": 2200 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 2250, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.926395026677432e+19, | |
| "train_batch_size": 24, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |