|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.0, |
|
"eval_steps": 500, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0001996, |
|
"loss": 2.4683, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019920000000000002, |
|
"loss": 2.2023, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.0001988, |
|
"loss": 2.3039, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.0001984, |
|
"loss": 2.1855, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00019800000000000002, |
|
"loss": 2.328, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.0001976, |
|
"loss": 2.3407, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.0001972, |
|
"loss": 2.3432, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.0001968, |
|
"loss": 2.2333, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0001964, |
|
"loss": 2.1761, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.000196, |
|
"loss": 2.1473, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.44, |
|
"learning_rate": 0.0001956, |
|
"loss": 2.2076, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 0.0001952, |
|
"loss": 2.1925, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.52, |
|
"learning_rate": 0.0001948, |
|
"loss": 2.1694, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 0.0001944, |
|
"loss": 2.1056, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 0.000194, |
|
"loss": 2.2426, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 0.00019360000000000002, |
|
"loss": 2.2635, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 0.0001932, |
|
"loss": 2.251, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 0.0001928, |
|
"loss": 2.224, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 0.00019240000000000001, |
|
"loss": 2.1848, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.000192, |
|
"loss": 2.1341, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 0.0001916, |
|
"loss": 2.126, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.0001912, |
|
"loss": 2.0959, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 0.0001908, |
|
"loss": 2.2446, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 0.0001904, |
|
"loss": 1.9448, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00019, |
|
"loss": 2.0939, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 0.0001896, |
|
"loss": 2.1247, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 1.08, |
|
"learning_rate": 0.0001892, |
|
"loss": 1.9417, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 0.0001888, |
|
"loss": 2.105, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 1.16, |
|
"learning_rate": 0.0001884, |
|
"loss": 2.1595, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.000188, |
|
"loss": 2.2009, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 0.0001876, |
|
"loss": 2.0784, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 0.00018720000000000002, |
|
"loss": 2.2173, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 1.32, |
|
"learning_rate": 0.00018680000000000001, |
|
"loss": 2.1185, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 0.00018640000000000003, |
|
"loss": 1.988, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 1.4, |
|
"learning_rate": 0.00018600000000000002, |
|
"loss": 1.9493, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 0.0001856, |
|
"loss": 1.9947, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 1.48, |
|
"learning_rate": 0.00018520000000000003, |
|
"loss": 2.0506, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 0.00018480000000000002, |
|
"loss": 2.0829, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 0.0001844, |
|
"loss": 2.1455, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.00018400000000000003, |
|
"loss": 2.0304, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 0.00018360000000000002, |
|
"loss": 2.006, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 0.0001832, |
|
"loss": 2.1759, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 1.72, |
|
"learning_rate": 0.00018280000000000003, |
|
"loss": 2.0093, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00018240000000000002, |
|
"loss": 2.0683, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 1.8, |
|
"learning_rate": 0.000182, |
|
"loss": 2.1352, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 0.00018160000000000002, |
|
"loss": 1.9736, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.0001812, |
|
"loss": 1.9631, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 0.0001808, |
|
"loss": 2.1024, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 1.96, |
|
"learning_rate": 0.00018040000000000002, |
|
"loss": 1.9895, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00018, |
|
"loss": 2.0067, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 0.0001796, |
|
"loss": 2.0509, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 0.00017920000000000002, |
|
"loss": 1.8795, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 0.0001788, |
|
"loss": 2.0633, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 0.0001784, |
|
"loss": 1.9998, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 2.2, |
|
"learning_rate": 0.00017800000000000002, |
|
"loss": 2.0675, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 0.0001776, |
|
"loss": 2.0129, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 2.28, |
|
"learning_rate": 0.0001772, |
|
"loss": 1.9302, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 0.00017680000000000001, |
|
"loss": 2.0472, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 2.36, |
|
"learning_rate": 0.0001764, |
|
"loss": 2.0031, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 0.00017600000000000002, |
|
"loss": 2.0231, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 0.0001756, |
|
"loss": 2.0192, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 0.0001752, |
|
"loss": 2.1336, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 2.52, |
|
"learning_rate": 0.00017480000000000002, |
|
"loss": 1.7753, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 0.0001744, |
|
"loss": 2.0274, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 2.6, |
|
"learning_rate": 0.000174, |
|
"loss": 1.8893, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 0.00017360000000000002, |
|
"loss": 2.0341, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 0.0001732, |
|
"loss": 2.1081, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 0.0001728, |
|
"loss": 1.9463, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 2.76, |
|
"learning_rate": 0.00017240000000000002, |
|
"loss": 2.0607, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 0.000172, |
|
"loss": 1.9803, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.84, |
|
"learning_rate": 0.0001716, |
|
"loss": 1.7663, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 0.00017120000000000001, |
|
"loss": 2.1116, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 0.0001708, |
|
"loss": 1.9039, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 0.0001704, |
|
"loss": 2.049, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.00017, |
|
"loss": 1.991, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 0.0001696, |
|
"loss": 1.8755, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 0.0001692, |
|
"loss": 2.0367, |
|
"step": 77 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 0.0001688, |
|
"loss": 1.9959, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 0.0001684, |
|
"loss": 1.8051, |
|
"step": 79 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 0.000168, |
|
"loss": 2.0446, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 0.0001676, |
|
"loss": 1.7873, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 0.0001672, |
|
"loss": 1.9264, |
|
"step": 82 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 0.0001668, |
|
"loss": 1.8595, |
|
"step": 83 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 0.0001664, |
|
"loss": 1.9992, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 0.000166, |
|
"loss": 1.8783, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 0.0001656, |
|
"loss": 2.0216, |
|
"step": 86 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 0.0001652, |
|
"loss": 1.947, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 0.0001648, |
|
"loss": 1.9554, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 0.0001644, |
|
"loss": 1.8563, |
|
"step": 89 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 0.000164, |
|
"loss": 1.7795, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 0.0001636, |
|
"loss": 1.9347, |
|
"step": 91 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 0.0001632, |
|
"loss": 2.0078, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 3.72, |
|
"learning_rate": 0.0001628, |
|
"loss": 1.9964, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 3.76, |
|
"learning_rate": 0.00016240000000000002, |
|
"loss": 1.9004, |
|
"step": 94 |
|
}, |
|
{ |
|
"epoch": 3.8, |
|
"learning_rate": 0.000162, |
|
"loss": 1.9446, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 3.84, |
|
"learning_rate": 0.00016160000000000002, |
|
"loss": 1.8857, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 3.88, |
|
"learning_rate": 0.00016120000000000002, |
|
"loss": 1.8797, |
|
"step": 97 |
|
}, |
|
{ |
|
"epoch": 3.92, |
|
"learning_rate": 0.0001608, |
|
"loss": 1.7643, |
|
"step": 98 |
|
}, |
|
{ |
|
"epoch": 3.96, |
|
"learning_rate": 0.00016040000000000002, |
|
"loss": 1.9724, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 0.00016, |
|
"loss": 1.9058, |
|
"step": 100 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 500, |
|
"num_train_epochs": 20, |
|
"save_steps": 100, |
|
"total_flos": 3.406529677264896e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|