Commit
·
55577f4
1
Parent(s):
c521604
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_f1": 0.9746835443037974,
|
| 4 |
+
"eval_loss": 0.09489229321479797,
|
| 5 |
+
"eval_runtime": 9.9057,
|
| 6 |
+
"eval_samples_per_second": 7.975,
|
| 7 |
+
"eval_steps_per_second": 0.101,
|
| 8 |
+
"train_loss": 0.17715629466942379,
|
| 9 |
+
"train_runtime": 2286.0002,
|
| 10 |
+
"train_samples_per_second": 7.804,
|
| 11 |
+
"train_steps_per_second": 0.122
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_f1": 0.9746835443037974,
|
| 4 |
+
"eval_loss": 0.09489229321479797,
|
| 5 |
+
"eval_runtime": 9.9057,
|
| 6 |
+
"eval_samples_per_second": 7.975,
|
| 7 |
+
"eval_steps_per_second": 0.101
|
| 8 |
+
}
|
runs/Dec06_20-52-20_49793c51f922/events.out.tfevents.1670362580.49793c51f922.5072.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01eef5558cd0e98c6c43403e4fdfd2fb9145fb54600e368e5933be3484ec3ce
|
| 3 |
+
size 357
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"train_loss": 0.17715629466942379,
|
| 4 |
+
"train_runtime": 2286.0002,
|
| 5 |
+
"train_samples_per_second": 7.804,
|
| 6 |
+
"train_steps_per_second": 0.122
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.09489229321479797,
|
| 3 |
+
"best_model_checkpoint": "/vit-base-patch32-224-in21k/checkpoint-273",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"global_step": 280,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_f1": 0.8607594936708861,
|
| 13 |
+
"eval_loss": 0.45760300755500793,
|
| 14 |
+
"eval_runtime": 9.802,
|
| 15 |
+
"eval_samples_per_second": 8.06,
|
| 16 |
+
"eval_steps_per_second": 0.102,
|
| 17 |
+
"step": 7
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.43,
|
| 21 |
+
"learning_rate": 1.928571428571429e-05,
|
| 22 |
+
"loss": 0.5021,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_f1": 0.8607594936708861,
|
| 28 |
+
"eval_loss": 0.39525437355041504,
|
| 29 |
+
"eval_runtime": 9.734,
|
| 30 |
+
"eval_samples_per_second": 8.116,
|
| 31 |
+
"eval_steps_per_second": 0.103,
|
| 32 |
+
"step": 14
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.86,
|
| 36 |
+
"learning_rate": 1.8571428571428575e-05,
|
| 37 |
+
"loss": 0.3595,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_f1": 0.8607594936708861,
|
| 43 |
+
"eval_loss": 0.38087165355682373,
|
| 44 |
+
"eval_runtime": 9.8033,
|
| 45 |
+
"eval_samples_per_second": 8.059,
|
| 46 |
+
"eval_steps_per_second": 0.102,
|
| 47 |
+
"step": 21
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.0,
|
| 51 |
+
"eval_f1": 0.8607594936708861,
|
| 52 |
+
"eval_loss": 0.32862257957458496,
|
| 53 |
+
"eval_runtime": 9.7791,
|
| 54 |
+
"eval_samples_per_second": 8.078,
|
| 55 |
+
"eval_steps_per_second": 0.102,
|
| 56 |
+
"step": 28
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.29,
|
| 60 |
+
"learning_rate": 1.785714285714286e-05,
|
| 61 |
+
"loss": 0.3009,
|
| 62 |
+
"step": 30
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"eval_f1": 0.8607594936708861,
|
| 67 |
+
"eval_loss": 0.29453742504119873,
|
| 68 |
+
"eval_runtime": 9.9491,
|
| 69 |
+
"eval_samples_per_second": 7.94,
|
| 70 |
+
"eval_steps_per_second": 0.101,
|
| 71 |
+
"step": 35
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.71,
|
| 75 |
+
"learning_rate": 1.7142857142857142e-05,
|
| 76 |
+
"loss": 0.2843,
|
| 77 |
+
"step": 40
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 6.0,
|
| 81 |
+
"eval_f1": 0.8607594936708861,
|
| 82 |
+
"eval_loss": 0.35278087854385376,
|
| 83 |
+
"eval_runtime": 9.8405,
|
| 84 |
+
"eval_samples_per_second": 8.028,
|
| 85 |
+
"eval_steps_per_second": 0.102,
|
| 86 |
+
"step": 42
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.0,
|
| 90 |
+
"eval_f1": 0.8607594936708861,
|
| 91 |
+
"eval_loss": 0.23452825844287872,
|
| 92 |
+
"eval_runtime": 9.7839,
|
| 93 |
+
"eval_samples_per_second": 8.074,
|
| 94 |
+
"eval_steps_per_second": 0.102,
|
| 95 |
+
"step": 49
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 7.14,
|
| 99 |
+
"learning_rate": 1.642857142857143e-05,
|
| 100 |
+
"loss": 0.266,
|
| 101 |
+
"step": 50
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 8.0,
|
| 105 |
+
"eval_f1": 0.8607594936708861,
|
| 106 |
+
"eval_loss": 0.24986670911312103,
|
| 107 |
+
"eval_runtime": 9.8907,
|
| 108 |
+
"eval_samples_per_second": 7.987,
|
| 109 |
+
"eval_steps_per_second": 0.101,
|
| 110 |
+
"step": 56
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 8.57,
|
| 114 |
+
"learning_rate": 1.5714285714285715e-05,
|
| 115 |
+
"loss": 0.222,
|
| 116 |
+
"step": 60
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.0,
|
| 120 |
+
"eval_f1": 0.8607594936708861,
|
| 121 |
+
"eval_loss": 0.25441065430641174,
|
| 122 |
+
"eval_runtime": 9.8794,
|
| 123 |
+
"eval_samples_per_second": 7.996,
|
| 124 |
+
"eval_steps_per_second": 0.101,
|
| 125 |
+
"step": 63
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 10.0,
|
| 129 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 130 |
+
"loss": 0.2018,
|
| 131 |
+
"step": 70
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 10.0,
|
| 135 |
+
"eval_f1": 0.8607594936708861,
|
| 136 |
+
"eval_loss": 0.19540712237358093,
|
| 137 |
+
"eval_runtime": 10.3358,
|
| 138 |
+
"eval_samples_per_second": 7.643,
|
| 139 |
+
"eval_steps_per_second": 0.097,
|
| 140 |
+
"step": 70
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 11.0,
|
| 144 |
+
"eval_f1": 0.8607594936708861,
|
| 145 |
+
"eval_loss": 0.23508581519126892,
|
| 146 |
+
"eval_runtime": 9.7761,
|
| 147 |
+
"eval_samples_per_second": 8.081,
|
| 148 |
+
"eval_steps_per_second": 0.102,
|
| 149 |
+
"step": 77
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 11.43,
|
| 153 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 154 |
+
"loss": 0.1948,
|
| 155 |
+
"step": 80
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 12.0,
|
| 159 |
+
"eval_f1": 0.8607594936708861,
|
| 160 |
+
"eval_loss": 0.17053687572479248,
|
| 161 |
+
"eval_runtime": 9.7433,
|
| 162 |
+
"eval_samples_per_second": 8.108,
|
| 163 |
+
"eval_steps_per_second": 0.103,
|
| 164 |
+
"step": 84
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 12.86,
|
| 168 |
+
"learning_rate": 1.3571428571428574e-05,
|
| 169 |
+
"loss": 0.2053,
|
| 170 |
+
"step": 90
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 13.0,
|
| 174 |
+
"eval_f1": 0.8734177215189873,
|
| 175 |
+
"eval_loss": 0.16247014701366425,
|
| 176 |
+
"eval_runtime": 9.7199,
|
| 177 |
+
"eval_samples_per_second": 8.128,
|
| 178 |
+
"eval_steps_per_second": 0.103,
|
| 179 |
+
"step": 91
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 14.0,
|
| 183 |
+
"eval_f1": 0.9367088607594937,
|
| 184 |
+
"eval_loss": 0.17189449071884155,
|
| 185 |
+
"eval_runtime": 9.7734,
|
| 186 |
+
"eval_samples_per_second": 8.083,
|
| 187 |
+
"eval_steps_per_second": 0.102,
|
| 188 |
+
"step": 98
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 14.29,
|
| 192 |
+
"learning_rate": 1.2857142857142859e-05,
|
| 193 |
+
"loss": 0.1729,
|
| 194 |
+
"step": 100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 15.0,
|
| 198 |
+
"eval_f1": 0.9367088607594937,
|
| 199 |
+
"eval_loss": 0.1488722860813141,
|
| 200 |
+
"eval_runtime": 9.7192,
|
| 201 |
+
"eval_samples_per_second": 8.128,
|
| 202 |
+
"eval_steps_per_second": 0.103,
|
| 203 |
+
"step": 105
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 15.71,
|
| 207 |
+
"learning_rate": 1.2142857142857142e-05,
|
| 208 |
+
"loss": 0.1535,
|
| 209 |
+
"step": 110
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 16.0,
|
| 213 |
+
"eval_f1": 0.9493670886075949,
|
| 214 |
+
"eval_loss": 0.14498455822467804,
|
| 215 |
+
"eval_runtime": 9.7322,
|
| 216 |
+
"eval_samples_per_second": 8.117,
|
| 217 |
+
"eval_steps_per_second": 0.103,
|
| 218 |
+
"step": 112
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 17.0,
|
| 222 |
+
"eval_f1": 0.9493670886075949,
|
| 223 |
+
"eval_loss": 0.1749649941921234,
|
| 224 |
+
"eval_runtime": 9.718,
|
| 225 |
+
"eval_samples_per_second": 8.129,
|
| 226 |
+
"eval_steps_per_second": 0.103,
|
| 227 |
+
"step": 119
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 17.14,
|
| 231 |
+
"learning_rate": 1.1428571428571429e-05,
|
| 232 |
+
"loss": 0.1492,
|
| 233 |
+
"step": 120
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 18.0,
|
| 237 |
+
"eval_f1": 0.9493670886075949,
|
| 238 |
+
"eval_loss": 0.15143541991710663,
|
| 239 |
+
"eval_runtime": 9.7273,
|
| 240 |
+
"eval_samples_per_second": 8.121,
|
| 241 |
+
"eval_steps_per_second": 0.103,
|
| 242 |
+
"step": 126
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 18.57,
|
| 246 |
+
"learning_rate": 1.0714285714285714e-05,
|
| 247 |
+
"loss": 0.1349,
|
| 248 |
+
"step": 130
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 19.0,
|
| 252 |
+
"eval_f1": 0.9620253164556962,
|
| 253 |
+
"eval_loss": 0.1304464191198349,
|
| 254 |
+
"eval_runtime": 9.7442,
|
| 255 |
+
"eval_samples_per_second": 8.107,
|
| 256 |
+
"eval_steps_per_second": 0.103,
|
| 257 |
+
"step": 133
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 20.0,
|
| 261 |
+
"learning_rate": 1e-05,
|
| 262 |
+
"loss": 0.1538,
|
| 263 |
+
"step": 140
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 20.0,
|
| 267 |
+
"eval_f1": 0.9620253164556962,
|
| 268 |
+
"eval_loss": 0.12909165024757385,
|
| 269 |
+
"eval_runtime": 9.7157,
|
| 270 |
+
"eval_samples_per_second": 8.131,
|
| 271 |
+
"eval_steps_per_second": 0.103,
|
| 272 |
+
"step": 140
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 21.0,
|
| 276 |
+
"eval_f1": 0.9620253164556962,
|
| 277 |
+
"eval_loss": 0.13061794638633728,
|
| 278 |
+
"eval_runtime": 9.7515,
|
| 279 |
+
"eval_samples_per_second": 8.101,
|
| 280 |
+
"eval_steps_per_second": 0.103,
|
| 281 |
+
"step": 147
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 21.43,
|
| 285 |
+
"learning_rate": 9.285714285714288e-06,
|
| 286 |
+
"loss": 0.1357,
|
| 287 |
+
"step": 150
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 22.0,
|
| 291 |
+
"eval_f1": 0.9620253164556962,
|
| 292 |
+
"eval_loss": 0.12830054759979248,
|
| 293 |
+
"eval_runtime": 9.7367,
|
| 294 |
+
"eval_samples_per_second": 8.114,
|
| 295 |
+
"eval_steps_per_second": 0.103,
|
| 296 |
+
"step": 154
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 22.86,
|
| 300 |
+
"learning_rate": 8.571428571428571e-06,
|
| 301 |
+
"loss": 0.147,
|
| 302 |
+
"step": 160
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 23.0,
|
| 306 |
+
"eval_f1": 0.9493670886075949,
|
| 307 |
+
"eval_loss": 0.12891362607479095,
|
| 308 |
+
"eval_runtime": 9.7565,
|
| 309 |
+
"eval_samples_per_second": 8.097,
|
| 310 |
+
"eval_steps_per_second": 0.102,
|
| 311 |
+
"step": 161
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 24.0,
|
| 315 |
+
"eval_f1": 0.9746835443037974,
|
| 316 |
+
"eval_loss": 0.1338558942079544,
|
| 317 |
+
"eval_runtime": 9.7379,
|
| 318 |
+
"eval_samples_per_second": 8.113,
|
| 319 |
+
"eval_steps_per_second": 0.103,
|
| 320 |
+
"step": 168
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 24.29,
|
| 324 |
+
"learning_rate": 7.857142857142858e-06,
|
| 325 |
+
"loss": 0.1388,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 25.0,
|
| 330 |
+
"eval_f1": 0.9493670886075949,
|
| 331 |
+
"eval_loss": 0.12436553090810776,
|
| 332 |
+
"eval_runtime": 9.7614,
|
| 333 |
+
"eval_samples_per_second": 8.093,
|
| 334 |
+
"eval_steps_per_second": 0.102,
|
| 335 |
+
"step": 175
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 25.71,
|
| 339 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 340 |
+
"loss": 0.1192,
|
| 341 |
+
"step": 180
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 26.0,
|
| 345 |
+
"eval_f1": 0.9746835443037974,
|
| 346 |
+
"eval_loss": 0.11165592074394226,
|
| 347 |
+
"eval_runtime": 9.7177,
|
| 348 |
+
"eval_samples_per_second": 8.129,
|
| 349 |
+
"eval_steps_per_second": 0.103,
|
| 350 |
+
"step": 182
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 27.0,
|
| 354 |
+
"eval_f1": 0.9873417721518988,
|
| 355 |
+
"eval_loss": 0.11046960204839706,
|
| 356 |
+
"eval_runtime": 9.7417,
|
| 357 |
+
"eval_samples_per_second": 8.109,
|
| 358 |
+
"eval_steps_per_second": 0.103,
|
| 359 |
+
"step": 189
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 27.14,
|
| 363 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 364 |
+
"loss": 0.112,
|
| 365 |
+
"step": 190
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 28.0,
|
| 369 |
+
"eval_f1": 0.9746835443037974,
|
| 370 |
+
"eval_loss": 0.1078834980726242,
|
| 371 |
+
"eval_runtime": 9.7562,
|
| 372 |
+
"eval_samples_per_second": 8.097,
|
| 373 |
+
"eval_steps_per_second": 0.102,
|
| 374 |
+
"step": 196
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 28.57,
|
| 378 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 379 |
+
"loss": 0.1215,
|
| 380 |
+
"step": 200
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 29.0,
|
| 384 |
+
"eval_f1": 0.9620253164556962,
|
| 385 |
+
"eval_loss": 0.11511888355016708,
|
| 386 |
+
"eval_runtime": 9.7361,
|
| 387 |
+
"eval_samples_per_second": 8.114,
|
| 388 |
+
"eval_steps_per_second": 0.103,
|
| 389 |
+
"step": 203
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 30.0,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.1139,
|
| 395 |
+
"step": 210
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 30.0,
|
| 399 |
+
"eval_f1": 0.9873417721518988,
|
| 400 |
+
"eval_loss": 0.10075395554304123,
|
| 401 |
+
"eval_runtime": 9.7351,
|
| 402 |
+
"eval_samples_per_second": 8.115,
|
| 403 |
+
"eval_steps_per_second": 0.103,
|
| 404 |
+
"step": 210
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 31.0,
|
| 408 |
+
"eval_f1": 0.9746835443037974,
|
| 409 |
+
"eval_loss": 0.10330603271722794,
|
| 410 |
+
"eval_runtime": 9.7699,
|
| 411 |
+
"eval_samples_per_second": 8.086,
|
| 412 |
+
"eval_steps_per_second": 0.102,
|
| 413 |
+
"step": 217
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 31.43,
|
| 417 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 418 |
+
"loss": 0.1164,
|
| 419 |
+
"step": 220
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 32.0,
|
| 423 |
+
"eval_f1": 0.9873417721518988,
|
| 424 |
+
"eval_loss": 0.0984945222735405,
|
| 425 |
+
"eval_runtime": 9.7232,
|
| 426 |
+
"eval_samples_per_second": 8.125,
|
| 427 |
+
"eval_steps_per_second": 0.103,
|
| 428 |
+
"step": 224
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 32.86,
|
| 432 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 433 |
+
"loss": 0.1192,
|
| 434 |
+
"step": 230
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 33.0,
|
| 438 |
+
"eval_f1": 0.9873417721518988,
|
| 439 |
+
"eval_loss": 0.09554588049650192,
|
| 440 |
+
"eval_runtime": 9.7164,
|
| 441 |
+
"eval_samples_per_second": 8.131,
|
| 442 |
+
"eval_steps_per_second": 0.103,
|
| 443 |
+
"step": 231
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 34.0,
|
| 447 |
+
"eval_f1": 0.9620253164556962,
|
| 448 |
+
"eval_loss": 0.10772588849067688,
|
| 449 |
+
"eval_runtime": 9.7297,
|
| 450 |
+
"eval_samples_per_second": 8.119,
|
| 451 |
+
"eval_steps_per_second": 0.103,
|
| 452 |
+
"step": 238
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 34.29,
|
| 456 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 457 |
+
"loss": 0.1132,
|
| 458 |
+
"step": 240
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 35.0,
|
| 462 |
+
"eval_f1": 0.9620253164556962,
|
| 463 |
+
"eval_loss": 0.11074268072843552,
|
| 464 |
+
"eval_runtime": 9.7358,
|
| 465 |
+
"eval_samples_per_second": 8.114,
|
| 466 |
+
"eval_steps_per_second": 0.103,
|
| 467 |
+
"step": 245
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 35.71,
|
| 471 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 472 |
+
"loss": 0.1021,
|
| 473 |
+
"step": 250
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 36.0,
|
| 477 |
+
"eval_f1": 0.9873417721518988,
|
| 478 |
+
"eval_loss": 0.09575933963060379,
|
| 479 |
+
"eval_runtime": 9.7306,
|
| 480 |
+
"eval_samples_per_second": 8.119,
|
| 481 |
+
"eval_steps_per_second": 0.103,
|
| 482 |
+
"step": 252
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 37.0,
|
| 486 |
+
"eval_f1": 0.9873417721518988,
|
| 487 |
+
"eval_loss": 0.09573517739772797,
|
| 488 |
+
"eval_runtime": 9.7256,
|
| 489 |
+
"eval_samples_per_second": 8.123,
|
| 490 |
+
"eval_steps_per_second": 0.103,
|
| 491 |
+
"step": 259
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 37.14,
|
| 495 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 496 |
+
"loss": 0.0945,
|
| 497 |
+
"step": 260
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 38.0,
|
| 501 |
+
"eval_f1": 0.9746835443037974,
|
| 502 |
+
"eval_loss": 0.09509044885635376,
|
| 503 |
+
"eval_runtime": 9.7255,
|
| 504 |
+
"eval_samples_per_second": 8.123,
|
| 505 |
+
"eval_steps_per_second": 0.103,
|
| 506 |
+
"step": 266
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 38.57,
|
| 510 |
+
"learning_rate": 7.142857142857143e-07,
|
| 511 |
+
"loss": 0.1244,
|
| 512 |
+
"step": 270
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 39.0,
|
| 516 |
+
"eval_f1": 0.9746835443037974,
|
| 517 |
+
"eval_loss": 0.09489229321479797,
|
| 518 |
+
"eval_runtime": 9.7321,
|
| 519 |
+
"eval_samples_per_second": 8.117,
|
| 520 |
+
"eval_steps_per_second": 0.103,
|
| 521 |
+
"step": 273
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 40.0,
|
| 525 |
+
"learning_rate": 0.0,
|
| 526 |
+
"loss": 0.1012,
|
| 527 |
+
"step": 280
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 40.0,
|
| 531 |
+
"eval_f1": 0.9873417721518988,
|
| 532 |
+
"eval_loss": 0.09554900228977203,
|
| 533 |
+
"eval_runtime": 9.7342,
|
| 534 |
+
"eval_samples_per_second": 8.116,
|
| 535 |
+
"eval_steps_per_second": 0.103,
|
| 536 |
+
"step": 280
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 40.0,
|
| 540 |
+
"step": 280,
|
| 541 |
+
"total_flos": 1.4091487038849024e+18,
|
| 542 |
+
"train_loss": 0.17715629466942379,
|
| 543 |
+
"train_runtime": 2286.0002,
|
| 544 |
+
"train_samples_per_second": 7.804,
|
| 545 |
+
"train_steps_per_second": 0.122
|
| 546 |
+
}
|
| 547 |
+
],
|
| 548 |
+
"max_steps": 280,
|
| 549 |
+
"num_train_epochs": 40,
|
| 550 |
+
"total_flos": 1.4091487038849024e+18,
|
| 551 |
+
"trial_name": null,
|
| 552 |
+
"trial_params": null
|
| 553 |
+
}
|