File size: 3,807 Bytes
c15d061 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.4,
"eval_steps": 1,
"global_step": 9,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.26666666666666666,
"grad_norm": 0.1357570467836887,
"learning_rate": 1.0000000000000001e-07,
"loss": 1.7723,
"step": 1
},
{
"epoch": 0.26666666666666666,
"eval_loss": 2.088420867919922,
"eval_runtime": 6.4988,
"eval_samples_per_second": 2.308,
"eval_steps_per_second": 0.154,
"step": 1
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.12515875774524352,
"learning_rate": 2.0000000000000002e-07,
"loss": 1.8176,
"step": 2
},
{
"epoch": 0.5333333333333333,
"eval_loss": 2.0871875286102295,
"eval_runtime": 6.4536,
"eval_samples_per_second": 2.324,
"eval_steps_per_second": 0.155,
"step": 2
},
{
"epoch": 0.8,
"grad_norm": 0.126303798585066,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.8499,
"step": 3
},
{
"epoch": 0.8,
"eval_loss": 2.087430000305176,
"eval_runtime": 6.4444,
"eval_samples_per_second": 2.328,
"eval_steps_per_second": 0.155,
"step": 3
},
{
"epoch": 1.0666666666666667,
"grad_norm": 0.3606214748278613,
"learning_rate": 4.0000000000000003e-07,
"loss": 1.7963,
"step": 4
},
{
"epoch": 1.0666666666666667,
"eval_loss": 2.0864670276641846,
"eval_runtime": 3.8555,
"eval_samples_per_second": 3.891,
"eval_steps_per_second": 0.259,
"step": 4
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.13158662209460245,
"learning_rate": 5.000000000000001e-07,
"loss": 1.8762,
"step": 5
},
{
"epoch": 1.3333333333333333,
"eval_loss": 2.0866217613220215,
"eval_runtime": 6.4449,
"eval_samples_per_second": 2.327,
"eval_steps_per_second": 0.155,
"step": 5
},
{
"epoch": 1.6,
"grad_norm": 0.12861366776262778,
"learning_rate": 6.000000000000001e-07,
"loss": 1.7795,
"step": 6
},
{
"epoch": 1.6,
"eval_loss": 2.0874640941619873,
"eval_runtime": 6.43,
"eval_samples_per_second": 2.333,
"eval_steps_per_second": 0.156,
"step": 6
},
{
"epoch": 1.8666666666666667,
"grad_norm": 0.1328896386162935,
"learning_rate": 7.000000000000001e-07,
"loss": 1.8179,
"step": 7
},
{
"epoch": 1.8666666666666667,
"eval_loss": 2.088042736053467,
"eval_runtime": 3.8515,
"eval_samples_per_second": 3.895,
"eval_steps_per_second": 0.26,
"step": 7
},
{
"epoch": 2.1333333333333333,
"grad_norm": 0.14871283917025502,
"learning_rate": 8.000000000000001e-07,
"loss": 1.8353,
"step": 8
},
{
"epoch": 2.1333333333333333,
"eval_loss": 2.087448835372925,
"eval_runtime": 6.431,
"eval_samples_per_second": 2.332,
"eval_steps_per_second": 0.155,
"step": 8
},
{
"epoch": 2.4,
"grad_norm": 0.12616378257742752,
"learning_rate": 9.000000000000001e-07,
"loss": 1.8009,
"step": 9
},
{
"epoch": 2.4,
"eval_loss": 2.0864264965057373,
"eval_runtime": 6.4396,
"eval_samples_per_second": 2.329,
"eval_steps_per_second": 0.155,
"step": 9
}
],
"logging_steps": 1,
"max_steps": 12,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 3,
"total_flos": 14110477516800.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|