|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 74, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 6.666666666666667e-05, |
|
"loss": 1.7195, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 0.00013333333333333334, |
|
"loss": 1.7455, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6774, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 0.00019990212265199738, |
|
"loss": 1.5637, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.00019960868220749448, |
|
"loss": 1.5396, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 0.00019912025308994148, |
|
"loss": 1.4398, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 0.00019843779142227256, |
|
"loss": 1.4331, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 0.0001975626331552507, |
|
"loss": 1.3507, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 0.00019649649145228102, |
|
"loss": 1.3126, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 0.00019524145333581317, |
|
"loss": 1.2983, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.00019379997560189675, |
|
"loss": 1.3245, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 0.00019217488001088784, |
|
"loss": 1.2862, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 0.0001903693477637204, |
|
"loss": 1.3176, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 0.0001883869132745561, |
|
"loss": 1.2571, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.00018623145725200278, |
|
"loss": 1.2672, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.00018390719910244487, |
|
"loss": 1.2419, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 0.00018141868867035745, |
|
"loss": 1.1957, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 0.00017877079733177184, |
|
"loss": 1.2108, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 0.0001759687084583285, |
|
"loss": 1.2339, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.00017301790727058345, |
|
"loss": 1.1814, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 0.00016992417010043142, |
|
"loss": 1.2099, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.0001666935530836651, |
|
"loss": 1.1888, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.0001633323803048047, |
|
"loss": 1.1456, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 0.00015984723141740576, |
|
"loss": 1.1857, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.34, |
|
"learning_rate": 0.0001562449287640781, |
|
"loss": 1.1673, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 0.00015253252402142988, |
|
"loss": 1.1486, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.00014871728439607966, |
|
"loss": 1.1618, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 0.00014480667839875786, |
|
"loss": 1.1615, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 0.0001408083612243465, |
|
"loss": 1.1551, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.41, |
|
"learning_rate": 0.00013673015976647568, |
|
"loss": 1.1877, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.42, |
|
"learning_rate": 0.00013258005729601177, |
|
"loss": 1.1489, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 0.0001283661778334297, |
|
"loss": 1.1398, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 0.00012409677024566144, |
|
"loss": 1.1161, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 0.00011978019209855174, |
|
"loss": 1.1278, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 0.00011542489329653024, |
|
"loss": 1.1385, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.49, |
|
"learning_rate": 0.000111039399541527, |
|
"loss": 1.1242, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 0.00010663229564351041, |
|
"loss": 1.0724, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 0.00010221220871531869, |
|
"loss": 1.1417, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 9.778779128468132e-05, |
|
"loss": 1.1003, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.54, |
|
"learning_rate": 9.336770435648964e-05, |
|
"loss": 1.1438, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 8.896060045847304e-05, |
|
"loss": 1.1069, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.57, |
|
"learning_rate": 8.457510670346976e-05, |
|
"loss": 1.122, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 8.021980790144827e-05, |
|
"loss": 1.1105, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 7.590322975433857e-05, |
|
"loss": 1.1796, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.61, |
|
"learning_rate": 7.163382216657034e-05, |
|
"loss": 1.1247, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 6.741994270398826e-05, |
|
"loss": 1.1206, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 6.326984023352435e-05, |
|
"loss": 1.1108, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 5.91916387756535e-05, |
|
"loss": 1.0583, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 5.5193321601242156e-05, |
|
"loss": 1.0866, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.68, |
|
"learning_rate": 5.1282715603920374e-05, |
|
"loss": 1.1098, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.69, |
|
"learning_rate": 4.746747597857014e-05, |
|
"loss": 1.1054, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.375507123592194e-05, |
|
"loss": 1.1232, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.015276858259427e-05, |
|
"loss": 1.0834, |
|
"step": 53 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 3.6667619695195285e-05, |
|
"loss": 1.1167, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.74, |
|
"learning_rate": 3.330644691633492e-05, |
|
"loss": 1.1175, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 3.0075829899568597e-05, |
|
"loss": 1.0868, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 2.6982092729416587e-05, |
|
"loss": 1.0981, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.78, |
|
"learning_rate": 2.403129154167153e-05, |
|
"loss": 1.0785, |
|
"step": 58 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 2.1229202668228197e-05, |
|
"loss": 1.0842, |
|
"step": 59 |
|
}, |
|
{ |
|
"epoch": 0.81, |
|
"learning_rate": 1.858131132964259e-05, |
|
"loss": 1.098, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.82, |
|
"learning_rate": 1.609280089755515e-05, |
|
"loss": 1.0851, |
|
"step": 61 |
|
}, |
|
{ |
|
"epoch": 0.84, |
|
"learning_rate": 1.3768542747997215e-05, |
|
"loss": 1.087, |
|
"step": 62 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 1.161308672544389e-05, |
|
"loss": 1.0674, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 9.630652236279625e-06, |
|
"loss": 1.134, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 7.825119989112173e-06, |
|
"loss": 1.0663, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 6.200024398103255e-06, |
|
"loss": 1.0968, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 4.758546664186869e-06, |
|
"loss": 1.1045, |
|
"step": 67 |
|
}, |
|
{ |
|
"epoch": 0.92, |
|
"learning_rate": 3.5035085477190143e-06, |
|
"loss": 1.0606, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 2.4373668447493224e-06, |
|
"loss": 1.061, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 1.562208577727442e-06, |
|
"loss": 1.068, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 8.797469100585431e-07, |
|
"loss": 1.066, |
|
"step": 71 |
|
}, |
|
{ |
|
"epoch": 0.97, |
|
"learning_rate": 3.913177925055189e-07, |
|
"loss": 1.0895, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 9.78773480026396e-08, |
|
"loss": 1.0862, |
|
"step": 73 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.9774, |
|
"step": 74 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 74, |
|
"total_flos": 43635507462144.0, |
|
"train_loss": 1.1855848898758758, |
|
"train_runtime": 1454.9887, |
|
"train_samples_per_second": 6.428, |
|
"train_steps_per_second": 0.051 |
|
} |
|
], |
|
"logging_steps": 1.0, |
|
"max_steps": 74, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50000, |
|
"total_flos": 43635507462144.0, |
|
"train_batch_size": 16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|