| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 82, | |
| "global_step": 82, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012195121951219513, | |
| "grad_norm": 0.6484375, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3233, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.024390243902439025, | |
| "grad_norm": 0.62109375, | |
| "learning_rate": 9.878048780487805e-06, | |
| "loss": 2.4552, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.036585365853658534, | |
| "grad_norm": 0.640625, | |
| "learning_rate": 9.756097560975611e-06, | |
| "loss": 2.4145, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.04878048780487805, | |
| "grad_norm": 0.59765625, | |
| "learning_rate": 9.634146341463415e-06, | |
| "loss": 2.3799, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06097560975609756, | |
| "grad_norm": 0.5625, | |
| "learning_rate": 9.51219512195122e-06, | |
| "loss": 2.3369, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07317073170731707, | |
| "grad_norm": 0.54296875, | |
| "learning_rate": 9.390243902439025e-06, | |
| "loss": 2.3515, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08536585365853659, | |
| "grad_norm": 0.498046875, | |
| "learning_rate": 9.268292682926831e-06, | |
| "loss": 2.177, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 9.146341463414635e-06, | |
| "loss": 2.2079, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.10975609756097561, | |
| "grad_norm": 0.4921875, | |
| "learning_rate": 9.02439024390244e-06, | |
| "loss": 2.2779, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12195121951219512, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 8.902439024390244e-06, | |
| "loss": 2.1717, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13414634146341464, | |
| "grad_norm": 0.48828125, | |
| "learning_rate": 8.78048780487805e-06, | |
| "loss": 2.2514, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.14634146341463414, | |
| "grad_norm": 0.4609375, | |
| "learning_rate": 8.658536585365854e-06, | |
| "loss": 2.2022, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.15853658536585366, | |
| "grad_norm": 0.431640625, | |
| "learning_rate": 8.536585365853658e-06, | |
| "loss": 2.0803, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17073170731707318, | |
| "grad_norm": 0.4453125, | |
| "learning_rate": 8.414634146341464e-06, | |
| "loss": 2.1038, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.18292682926829268, | |
| "grad_norm": 0.451171875, | |
| "learning_rate": 8.292682926829268e-06, | |
| "loss": 2.0937, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 0.44921875, | |
| "learning_rate": 8.170731707317073e-06, | |
| "loss": 2.0558, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2073170731707317, | |
| "grad_norm": 0.431640625, | |
| "learning_rate": 8.048780487804879e-06, | |
| "loss": 2.0218, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.21951219512195122, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 7.926829268292685e-06, | |
| "loss": 2.0406, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.23170731707317074, | |
| "grad_norm": 0.416015625, | |
| "learning_rate": 7.804878048780489e-06, | |
| "loss": 1.9861, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.439453125, | |
| "learning_rate": 7.682926829268293e-06, | |
| "loss": 2.0237, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25609756097560976, | |
| "grad_norm": 0.3984375, | |
| "learning_rate": 7.560975609756098e-06, | |
| "loss": 1.9977, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.2682926829268293, | |
| "grad_norm": 0.3828125, | |
| "learning_rate": 7.439024390243903e-06, | |
| "loss": 1.972, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2804878048780488, | |
| "grad_norm": 0.375, | |
| "learning_rate": 7.317073170731707e-06, | |
| "loss": 1.9552, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 0.384765625, | |
| "learning_rate": 7.1951219512195125e-06, | |
| "loss": 1.9581, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3048780487804878, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 7.0731707317073175e-06, | |
| "loss": 1.9023, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3170731707317073, | |
| "grad_norm": 0.400390625, | |
| "learning_rate": 6.951219512195122e-06, | |
| "loss": 1.9077, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.32926829268292684, | |
| "grad_norm": 0.353515625, | |
| "learning_rate": 6.829268292682928e-06, | |
| "loss": 1.8831, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.34146341463414637, | |
| "grad_norm": 0.361328125, | |
| "learning_rate": 6.707317073170733e-06, | |
| "loss": 1.8655, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.35365853658536583, | |
| "grad_norm": 0.345703125, | |
| "learning_rate": 6.585365853658538e-06, | |
| "loss": 1.796, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.36585365853658536, | |
| "grad_norm": 0.328125, | |
| "learning_rate": 6.463414634146342e-06, | |
| "loss": 1.8275, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3780487804878049, | |
| "grad_norm": 0.3203125, | |
| "learning_rate": 6.341463414634147e-06, | |
| "loss": 1.7658, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 6.219512195121951e-06, | |
| "loss": 1.8462, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4024390243902439, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 6.0975609756097564e-06, | |
| "loss": 1.7359, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4146341463414634, | |
| "grad_norm": 0.326171875, | |
| "learning_rate": 5.9756097560975615e-06, | |
| "loss": 1.7696, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4268292682926829, | |
| "grad_norm": 0.3125, | |
| "learning_rate": 5.853658536585366e-06, | |
| "loss": 1.7683, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43902439024390244, | |
| "grad_norm": 0.33203125, | |
| "learning_rate": 5.731707317073171e-06, | |
| "loss": 1.8454, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.45121951219512196, | |
| "grad_norm": 0.318359375, | |
| "learning_rate": 5.609756097560977e-06, | |
| "loss": 1.7914, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4634146341463415, | |
| "grad_norm": 0.29296875, | |
| "learning_rate": 5.487804878048781e-06, | |
| "loss": 1.7627, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.47560975609756095, | |
| "grad_norm": 0.30078125, | |
| "learning_rate": 5.365853658536586e-06, | |
| "loss": 1.7751, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 5.243902439024391e-06, | |
| "loss": 1.7449, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.3046875, | |
| "learning_rate": 5.121951219512195e-06, | |
| "loss": 1.7489, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.5121951219512195, | |
| "grad_norm": 0.298828125, | |
| "learning_rate": 5e-06, | |
| "loss": 1.7532, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.524390243902439, | |
| "grad_norm": 0.271484375, | |
| "learning_rate": 4.8780487804878055e-06, | |
| "loss": 1.7089, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5365853658536586, | |
| "grad_norm": 0.296875, | |
| "learning_rate": 4.75609756097561e-06, | |
| "loss": 1.784, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5487804878048781, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 4.634146341463416e-06, | |
| "loss": 1.6915, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5609756097560976, | |
| "grad_norm": 0.283203125, | |
| "learning_rate": 4.51219512195122e-06, | |
| "loss": 1.6932, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.573170731707317, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 4.390243902439025e-06, | |
| "loss": 1.6824, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 0.28125, | |
| "learning_rate": 4.268292682926829e-06, | |
| "loss": 1.7119, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5975609756097561, | |
| "grad_norm": 0.2890625, | |
| "learning_rate": 4.146341463414634e-06, | |
| "loss": 1.7439, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6097560975609756, | |
| "grad_norm": 0.265625, | |
| "learning_rate": 4.024390243902439e-06, | |
| "loss": 1.6766, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6219512195121951, | |
| "grad_norm": 0.28515625, | |
| "learning_rate": 3.902439024390244e-06, | |
| "loss": 1.7051, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.6341463414634146, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 3.780487804878049e-06, | |
| "loss": 1.6532, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.6463414634146342, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 3.6585365853658537e-06, | |
| "loss": 1.6673, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6585365853658537, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 3.5365853658536588e-06, | |
| "loss": 1.6357, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6707317073170732, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 3.414634146341464e-06, | |
| "loss": 1.6375, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 0.248046875, | |
| "learning_rate": 3.292682926829269e-06, | |
| "loss": 1.5942, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6951219512195121, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 3.1707317073170736e-06, | |
| "loss": 1.6206, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.7073170731707317, | |
| "grad_norm": 0.25, | |
| "learning_rate": 3.0487804878048782e-06, | |
| "loss": 1.6198, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.7195121951219512, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 2.926829268292683e-06, | |
| "loss": 1.6647, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.25, | |
| "learning_rate": 2.8048780487804884e-06, | |
| "loss": 1.6164, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.7439024390243902, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 2.682926829268293e-06, | |
| "loss": 1.6352, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.7560975609756098, | |
| "grad_norm": 0.2490234375, | |
| "learning_rate": 2.5609756097560977e-06, | |
| "loss": 1.6524, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7682926829268293, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 2.4390243902439027e-06, | |
| "loss": 1.6427, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 2.317073170731708e-06, | |
| "loss": 1.6446, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7926829268292683, | |
| "grad_norm": 0.25, | |
| "learning_rate": 2.1951219512195125e-06, | |
| "loss": 1.62, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.8048780487804879, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 2.073170731707317e-06, | |
| "loss": 1.6486, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.8170731707317073, | |
| "grad_norm": 0.26171875, | |
| "learning_rate": 1.951219512195122e-06, | |
| "loss": 1.6394, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.8292682926829268, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 1.8292682926829268e-06, | |
| "loss": 1.6132, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.8414634146341463, | |
| "grad_norm": 0.2578125, | |
| "learning_rate": 1.707317073170732e-06, | |
| "loss": 1.665, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.8536585365853658, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 1.5853658536585368e-06, | |
| "loss": 1.6227, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.8658536585365854, | |
| "grad_norm": 0.23828125, | |
| "learning_rate": 1.4634146341463414e-06, | |
| "loss": 1.6064, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 1.3414634146341465e-06, | |
| "loss": 1.6649, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8902439024390244, | |
| "grad_norm": 0.2412109375, | |
| "learning_rate": 1.2195121951219514e-06, | |
| "loss": 1.5657, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.9024390243902439, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 1.0975609756097562e-06, | |
| "loss": 1.6191, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.9146341463414634, | |
| "grad_norm": 0.24609375, | |
| "learning_rate": 9.75609756097561e-07, | |
| "loss": 1.618, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.926829268292683, | |
| "grad_norm": 0.2470703125, | |
| "learning_rate": 8.53658536585366e-07, | |
| "loss": 1.593, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.9390243902439024, | |
| "grad_norm": 0.255859375, | |
| "learning_rate": 7.317073170731707e-07, | |
| "loss": 1.6636, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.9512195121951219, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 6.097560975609757e-07, | |
| "loss": 1.6529, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.9634146341463414, | |
| "grad_norm": 0.259765625, | |
| "learning_rate": 4.878048780487805e-07, | |
| "loss": 1.6672, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.25390625, | |
| "learning_rate": 3.6585365853658536e-07, | |
| "loss": 1.6409, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9878048780487805, | |
| "grad_norm": 0.267578125, | |
| "learning_rate": 2.439024390243903e-07, | |
| "loss": 1.6251, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2421875, | |
| "learning_rate": 1.2195121951219514e-07, | |
| "loss": 1.5768, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.609056830406189, | |
| "eval_runtime": 12.2057, | |
| "eval_samples_per_second": 2.868, | |
| "eval_steps_per_second": 0.41, | |
| "step": 82 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 82, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.805261781696512e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |