| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04, | |
| "eval_steps": 1000, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0499, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6769, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9706, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.707, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019789473684210526, | |
| "loss": 2.2169, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019578947368421054, | |
| "loss": 2.462, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001936842105263158, | |
| "loss": 1.4424, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019157894736842104, | |
| "loss": 1.9676, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018947368421052632, | |
| "loss": 1.9327, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001873684210526316, | |
| "loss": 1.7225, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018526315789473685, | |
| "loss": 1.9631, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001831578947368421, | |
| "loss": 1.7594, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00018105263157894739, | |
| "loss": 1.7592, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017894736842105264, | |
| "loss": 1.722, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001768421052631579, | |
| "loss": 1.5222, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017473684210526317, | |
| "loss": 1.7118, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00017263157894736842, | |
| "loss": 2.5015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001705263157894737, | |
| "loss": 1.5079, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016842105263157895, | |
| "loss": 1.9524, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016631578947368423, | |
| "loss": 1.8966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016421052631578948, | |
| "loss": 1.7529, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016210526315789473, | |
| "loss": 1.596, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9381, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 1.5751, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015578947368421052, | |
| "loss": 1.7917, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001536842105263158, | |
| "loss": 1.485, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00015157894736842108, | |
| "loss": 1.5073, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014947368421052633, | |
| "loss": 1.6471, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014736842105263158, | |
| "loss": 1.5818, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014526315789473686, | |
| "loss": 1.7394, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001431578947368421, | |
| "loss": 1.4422, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00014105263157894736, | |
| "loss": 2.2255, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013894736842105264, | |
| "loss": 1.6186, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0001368421052631579, | |
| "loss": 1.8378, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013473684210526317, | |
| "loss": 1.6349, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.00013263157894736842, | |
| "loss": 1.519, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001305263157894737, | |
| "loss": 1.5548, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012842105263157895, | |
| "loss": 2.2187, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001263157894736842, | |
| "loss": 1.4438, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012421052631578949, | |
| "loss": 1.4265, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012210526315789474, | |
| "loss": 1.6946, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9664, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011789473684210525, | |
| "loss": 1.7266, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011578947368421053, | |
| "loss": 1.8053, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001136842105263158, | |
| "loss": 1.3368, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00011157894736842105, | |
| "loss": 1.8476, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00010947368421052633, | |
| "loss": 1.5476, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00010736842105263158, | |
| "loss": 1.7867, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00010526315789473685, | |
| "loss": 1.4282, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00010315789473684211, | |
| "loss": 1.7713, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00010105263157894738, | |
| "loss": 1.6238, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.894736842105263e-05, | |
| "loss": 1.5243, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.68421052631579e-05, | |
| "loss": 1.4315, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.473684210526316e-05, | |
| "loss": 1.48, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.263157894736843e-05, | |
| "loss": 1.7109, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 9.052631578947369e-05, | |
| "loss": 1.6509, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.842105263157894e-05, | |
| "loss": 1.5552, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.631578947368421e-05, | |
| "loss": 1.8228, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.421052631578948e-05, | |
| "loss": 1.5684, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8.210526315789474e-05, | |
| "loss": 1.6735, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5827, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.789473684210526e-05, | |
| "loss": 1.5755, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.578947368421054e-05, | |
| "loss": 1.3339, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.368421052631579e-05, | |
| "loss": 1.4373, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 7.157894736842105e-05, | |
| "loss": 1.9484, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.947368421052632e-05, | |
| "loss": 1.5517, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.736842105263159e-05, | |
| "loss": 1.5427, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.526315789473685e-05, | |
| "loss": 1.689, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.31578947368421e-05, | |
| "loss": 1.5722, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 6.105263157894737e-05, | |
| "loss": 2.1363, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.894736842105263e-05, | |
| "loss": 1.8984, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.68421052631579e-05, | |
| "loss": 1.3357, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.4736842105263165e-05, | |
| "loss": 1.3596, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.2631578947368424e-05, | |
| "loss": 1.492, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 5.052631578947369e-05, | |
| "loss": 1.8862, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.842105263157895e-05, | |
| "loss": 1.721, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.6315789473684214e-05, | |
| "loss": 1.3932, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.421052631578947e-05, | |
| "loss": 1.4688, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.210526315789474e-05, | |
| "loss": 1.573, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4032, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.789473684210527e-05, | |
| "loss": 1.6532, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.578947368421053e-05, | |
| "loss": 1.3414, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.368421052631579e-05, | |
| "loss": 2.0307, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.157894736842105e-05, | |
| "loss": 1.6258, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.9473684210526314e-05, | |
| "loss": 1.5653, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.7368421052631583e-05, | |
| "loss": 1.3957, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.5263157894736845e-05, | |
| "loss": 1.7757, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.3157894736842107e-05, | |
| "loss": 1.7531, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.105263157894737e-05, | |
| "loss": 1.7966, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.8947368421052634e-05, | |
| "loss": 1.4885, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.6842105263157896e-05, | |
| "loss": 1.0934, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.4736842105263157e-05, | |
| "loss": 1.5674, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.2631578947368422e-05, | |
| "loss": 2.0261, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 1.5099, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 8.421052631578948e-06, | |
| "loss": 1.4694, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 6.315789473684211e-06, | |
| "loss": 1.675, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.210526315789474e-06, | |
| "loss": 1.6133, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 2.105263157894737e-06, | |
| "loss": 1.6722, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0, | |
| "loss": 1.4913, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "total_flos": 6616414021533696.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |