| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 5000, | |
| "global_step": 504, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01984126984126984, | |
| "grad_norm": 2912.028564453125, | |
| "learning_rate": 2e-08, | |
| "loss": 14.5926, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03968253968253968, | |
| "grad_norm": 6037.033203125, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 14.6525, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05952380952380952, | |
| "grad_norm": 7095.4931640625, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 13.8958, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 3047.11572265625, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 13.0648, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0992063492063492, | |
| "grad_norm": 20132.697265625, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 11.7415, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11904761904761904, | |
| "grad_norm": 65280.9921875, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 10.186, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1388888888888889, | |
| "grad_norm": 18013.744140625, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 8.9537, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 12039.76171875, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 8.8499, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 4152.63037109375, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 8.1076, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1984126984126984, | |
| "grad_norm": 112633.828125, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 7.3218, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21825396825396826, | |
| "grad_norm": 12219.0498046875, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 6.8102, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 5337.48681640625, | |
| "learning_rate": 2.2e-06, | |
| "loss": 6.4298, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25793650793650796, | |
| "grad_norm": 66286.9609375, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 6.1412, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 22970.162109375, | |
| "learning_rate": 2.6e-06, | |
| "loss": 6.1932, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2976190476190476, | |
| "grad_norm": 1229.7572021484375, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 5.807, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 4040.58544921875, | |
| "learning_rate": 3e-06, | |
| "loss": 5.3959, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3373015873015873, | |
| "grad_norm": 79031.90625, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 5.1443, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 2377.986328125, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 5.1, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.376984126984127, | |
| "grad_norm": 6816.78173828125, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 5.0767, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 329.9869384765625, | |
| "learning_rate": 3.8000000000000005e-06, | |
| "loss": 4.7978, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 551.7224731445312, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 4.3107, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.4365079365079365, | |
| "grad_norm": 306.0798645019531, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 4.126, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.45634920634920634, | |
| "grad_norm": 259.38702392578125, | |
| "learning_rate": 4.4e-06, | |
| "loss": 3.3982, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 152.5589141845703, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 2.9569, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.49603174603174605, | |
| "grad_norm": 188.98681640625, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 2.3802, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5158730158730159, | |
| "grad_norm": 214.31179809570312, | |
| "learning_rate": 5e-06, | |
| "loss": 2.0057, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 184.34437561035156, | |
| "learning_rate": 5.2e-06, | |
| "loss": 1.6501, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 119.70015716552734, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 1.4393, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5753968253968254, | |
| "grad_norm": 172.4916534423828, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 1.2536, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.5952380952380952, | |
| "grad_norm": 152.96202087402344, | |
| "learning_rate": 5.8e-06, | |
| "loss": 1.1011, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6150793650793651, | |
| "grad_norm": 229.5851593017578, | |
| "learning_rate": 6e-06, | |
| "loss": 0.9963, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 192.8756103515625, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 0.893, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6547619047619048, | |
| "grad_norm": 285.22601318359375, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 0.7744, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.6746031746031746, | |
| "grad_norm": 121.977783203125, | |
| "learning_rate": 6.600000000000001e-06, | |
| "loss": 0.6989, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6944444444444444, | |
| "grad_norm": 135.0439453125, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 0.559, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 157.01791381835938, | |
| "learning_rate": 7e-06, | |
| "loss": 0.5721, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.7341269841269841, | |
| "grad_norm": 139.25894165039062, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 0.5385, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.753968253968254, | |
| "grad_norm": 94.0282974243164, | |
| "learning_rate": 7.4e-06, | |
| "loss": 0.5169, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7738095238095238, | |
| "grad_norm": 64.70858764648438, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 0.4738, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 68.39224243164062, | |
| "learning_rate": 7.800000000000002e-06, | |
| "loss": 0.4533, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.8134920634920635, | |
| "grad_norm": 55.44282150268555, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.4296, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 66.44039154052734, | |
| "learning_rate": 8.2e-06, | |
| "loss": 0.3933, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.8531746031746031, | |
| "grad_norm": 64.27642822265625, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 0.4348, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.873015873015873, | |
| "grad_norm": 1226.5478515625, | |
| "learning_rate": 8.6e-06, | |
| "loss": 0.6043, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 94.26041412353516, | |
| "learning_rate": 8.8e-06, | |
| "loss": 0.3775, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9126984126984127, | |
| "grad_norm": 63.64945983886719, | |
| "learning_rate": 9e-06, | |
| "loss": 0.3306, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.9325396825396826, | |
| "grad_norm": 41.9366340637207, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 0.3727, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 36.641475677490234, | |
| "learning_rate": 9.4e-06, | |
| "loss": 0.3561, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.9722222222222222, | |
| "grad_norm": 30.62155532836914, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 0.3152, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.9920634920634921, | |
| "grad_norm": 36.66413497924805, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 0.3266, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 504, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.2449113063424e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |