File size: 2,589 Bytes
d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 721d7d8 d91a210 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 14.4,
"eval_steps": 500,
"global_step": 180,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.2,
"grad_norm": 0.8679821491241455,
"learning_rate": 0.00019868265225415265,
"loss": 4.9095,
"step": 15
},
{
"epoch": 2.4,
"grad_norm": 1.064207911491394,
"learning_rate": 0.00019075754196709572,
"loss": 3.2019,
"step": 30
},
{
"epoch": 3.6,
"grad_norm": 0.6014457941055298,
"learning_rate": 0.00017621620551276366,
"loss": 1.7706,
"step": 45
},
{
"epoch": 4.8,
"grad_norm": 0.4954649806022644,
"learning_rate": 0.00015611870653623825,
"loss": 1.2936,
"step": 60
},
{
"epoch": 6.0,
"grad_norm": 0.418344110250473,
"learning_rate": 0.000131930153013598,
"loss": 1.0465,
"step": 75
},
{
"epoch": 7.2,
"grad_norm": 0.40778854489326477,
"learning_rate": 0.00010541389085854176,
"loss": 0.9186,
"step": 90
},
{
"epoch": 8.4,
"grad_norm": 0.3741260766983032,
"learning_rate": 7.85029559788976e-05,
"loss": 0.8364,
"step": 105
},
{
"epoch": 9.6,
"grad_norm": 0.4041515290737152,
"learning_rate": 5.3159155930021e-05,
"loss": 0.7861,
"step": 120
},
{
"epoch": 10.8,
"grad_norm": 0.3697131872177124,
"learning_rate": 3.123005411465766e-05,
"loss": 0.7488,
"step": 135
},
{
"epoch": 12.0,
"grad_norm": 0.4183999001979828,
"learning_rate": 1.4314282383241096e-05,
"loss": 0.7274,
"step": 150
},
{
"epoch": 13.2,
"grad_norm": 0.4263518154621124,
"learning_rate": 3.6450007480777093e-06,
"loss": 0.7245,
"step": 165
},
{
"epoch": 14.4,
"grad_norm": 0.3251570165157318,
"learning_rate": 0.0,
"loss": 0.7288,
"step": 180
},
{
"epoch": 14.4,
"step": 180,
"total_flos": 116292530995200.0,
"train_loss": 1.4744000752766928,
"train_runtime": 81.674,
"train_samples_per_second": 18.366,
"train_steps_per_second": 2.204
}
],
"logging_steps": 15,
"max_steps": 180,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"save_steps": 500,
"total_flos": 116292530995200.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|