End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.96,
|
| 3 |
+
"eval_accuracy": 0.9765227021040974,
|
| 4 |
+
"eval_loss": 0.060047686100006104,
|
| 5 |
+
"eval_runtime": 172.8069,
|
| 6 |
+
"eval_samples_per_second": 26.127,
|
| 7 |
+
"eval_steps_per_second": 1.638,
|
| 8 |
+
"total_flos": 8.138660625246413e+18,
|
| 9 |
+
"train_loss": 0.22687274961061374,
|
| 10 |
+
"train_runtime": 10415.6562,
|
| 11 |
+
"train_samples_per_second": 2.873,
|
| 12 |
+
"train_steps_per_second": 0.045
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.96,
|
| 3 |
+
"eval_accuracy": 0.9765227021040974,
|
| 4 |
+
"eval_loss": 0.060047686100006104,
|
| 5 |
+
"eval_runtime": 172.8069,
|
| 6 |
+
"eval_samples_per_second": 26.127,
|
| 7 |
+
"eval_steps_per_second": 1.638
|
| 8 |
+
}
|
runs/Jul22_17-36-37_6a016831cfe9/events.out.tfevents.1690058137.6a016831cfe9.2994.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb645b9a1d36e79bc9d546e33e6957aca25e2641a8ad07b410ac1947c3b3e1a4
|
| 3 |
+
size 1147
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.96,
|
| 3 |
+
"total_flos": 8.138660625246413e+18,
|
| 4 |
+
"train_loss": 0.22687274961061374,
|
| 5 |
+
"train_runtime": 10415.6562,
|
| 6 |
+
"train_samples_per_second": 2.873,
|
| 7 |
+
"train_steps_per_second": 0.045
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9765227021040974,
|
| 3 |
+
"best_model_checkpoint": "beit-large-patch16-224-finetuned-LungCancer-Classification-LC25000-AH-40-30-30-Shuffled/checkpoint-465",
|
| 4 |
+
"epoch": 4.96,
|
| 5 |
+
"global_step": 465,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 1.072961373390558e-05,
|
| 13 |
+
"loss": 1.0622,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 2.145922746781116e-05,
|
| 19 |
+
"loss": 0.392,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 3.2188841201716734e-05,
|
| 25 |
+
"loss": 0.1492,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 4.291845493562232e-05,
|
| 31 |
+
"loss": 0.3119,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 5.36480686695279e-05,
|
| 37 |
+
"loss": 0.3857,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.32,
|
| 42 |
+
"learning_rate": 6.437768240343347e-05,
|
| 43 |
+
"loss": 0.3276,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.37,
|
| 48 |
+
"learning_rate": 7.510729613733907e-05,
|
| 49 |
+
"loss": 0.1959,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.43,
|
| 54 |
+
"learning_rate": 8.583690987124464e-05,
|
| 55 |
+
"loss": 0.2293,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"learning_rate": 9.656652360515021e-05,
|
| 61 |
+
"loss": 0.2327,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.53,
|
| 66 |
+
"learning_rate": 0.0001072961373390558,
|
| 67 |
+
"loss": 0.1448,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.59,
|
| 72 |
+
"learning_rate": 0.00011802575107296138,
|
| 73 |
+
"loss": 0.4546,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.64,
|
| 78 |
+
"learning_rate": 0.00012875536480686693,
|
| 79 |
+
"loss": 0.4873,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.69,
|
| 84 |
+
"learning_rate": 0.00013948497854077252,
|
| 85 |
+
"loss": 0.2304,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.75,
|
| 90 |
+
"learning_rate": 0.00015021459227467814,
|
| 91 |
+
"loss": 0.2108,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 0.0001609442060085837,
|
| 97 |
+
"loss": 0.1728,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"learning_rate": 0.00017167381974248928,
|
| 103 |
+
"loss": 0.2435,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.91,
|
| 108 |
+
"learning_rate": 0.00018240343347639484,
|
| 109 |
+
"loss": 0.1867,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.96,
|
| 114 |
+
"learning_rate": 0.00019313304721030043,
|
| 115 |
+
"loss": 0.1531,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.99,
|
| 120 |
+
"eval_accuracy": 0.950609080841639,
|
| 121 |
+
"eval_loss": 0.13507413864135742,
|
| 122 |
+
"eval_runtime": 2782.0005,
|
| 123 |
+
"eval_samples_per_second": 1.623,
|
| 124 |
+
"eval_steps_per_second": 0.102,
|
| 125 |
+
"step": 93
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.01,
|
| 129 |
+
"learning_rate": 0.00020386266094420602,
|
| 130 |
+
"loss": 0.1951,
|
| 131 |
+
"step": 95
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.07,
|
| 135 |
+
"learning_rate": 0.0002145922746781116,
|
| 136 |
+
"loss": 0.2277,
|
| 137 |
+
"step": 100
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.12,
|
| 141 |
+
"learning_rate": 0.00022532188841201716,
|
| 142 |
+
"loss": 0.5258,
|
| 143 |
+
"step": 105
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.17,
|
| 147 |
+
"learning_rate": 0.00023605150214592275,
|
| 148 |
+
"loss": 0.2515,
|
| 149 |
+
"step": 110
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.23,
|
| 153 |
+
"learning_rate": 0.0002467811158798283,
|
| 154 |
+
"loss": 0.2739,
|
| 155 |
+
"step": 115
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.28,
|
| 159 |
+
"learning_rate": 0.00025751072961373387,
|
| 160 |
+
"loss": 0.2044,
|
| 161 |
+
"step": 120
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.33,
|
| 165 |
+
"learning_rate": 0.0002682403433476395,
|
| 166 |
+
"loss": 0.1319,
|
| 167 |
+
"step": 125
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.39,
|
| 171 |
+
"learning_rate": 0.00027896995708154504,
|
| 172 |
+
"loss": 0.222,
|
| 173 |
+
"step": 130
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.44,
|
| 177 |
+
"learning_rate": 0.00028969957081545066,
|
| 178 |
+
"loss": 0.1768,
|
| 179 |
+
"step": 135
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.49,
|
| 183 |
+
"learning_rate": 0.00030042918454935627,
|
| 184 |
+
"loss": 0.3206,
|
| 185 |
+
"step": 140
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.55,
|
| 189 |
+
"learning_rate": 0.00031115879828326183,
|
| 190 |
+
"loss": 0.2142,
|
| 191 |
+
"step": 145
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.6,
|
| 195 |
+
"learning_rate": 0.0003218884120171674,
|
| 196 |
+
"loss": 0.3406,
|
| 197 |
+
"step": 150
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.65,
|
| 201 |
+
"learning_rate": 0.00033261802575107295,
|
| 202 |
+
"loss": 0.2023,
|
| 203 |
+
"step": 155
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.71,
|
| 207 |
+
"learning_rate": 0.00034334763948497857,
|
| 208 |
+
"loss": 0.2542,
|
| 209 |
+
"step": 160
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.76,
|
| 213 |
+
"learning_rate": 0.0003540772532188841,
|
| 214 |
+
"loss": 0.2525,
|
| 215 |
+
"step": 165
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.81,
|
| 219 |
+
"learning_rate": 0.0003648068669527897,
|
| 220 |
+
"loss": 0.1976,
|
| 221 |
+
"step": 170
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.87,
|
| 225 |
+
"learning_rate": 0.00037553648068669525,
|
| 226 |
+
"loss": 0.3107,
|
| 227 |
+
"step": 175
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.92,
|
| 231 |
+
"learning_rate": 0.00038626609442060086,
|
| 232 |
+
"loss": 0.2429,
|
| 233 |
+
"step": 180
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.97,
|
| 237 |
+
"learning_rate": 0.0003969957081545064,
|
| 238 |
+
"loss": 0.2389,
|
| 239 |
+
"step": 185
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.99,
|
| 243 |
+
"eval_accuracy": 0.9344407530454042,
|
| 244 |
+
"eval_loss": 0.1534101516008377,
|
| 245 |
+
"eval_runtime": 174.101,
|
| 246 |
+
"eval_samples_per_second": 25.933,
|
| 247 |
+
"eval_steps_per_second": 1.625,
|
| 248 |
+
"step": 187
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.03,
|
| 252 |
+
"learning_rate": 0.00040772532188841203,
|
| 253 |
+
"loss": 0.3097,
|
| 254 |
+
"step": 190
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.08,
|
| 258 |
+
"learning_rate": 0.00041845493562231765,
|
| 259 |
+
"loss": 0.3555,
|
| 260 |
+
"step": 195
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.13,
|
| 264 |
+
"learning_rate": 0.0004291845493562232,
|
| 265 |
+
"loss": 0.236,
|
| 266 |
+
"step": 200
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.19,
|
| 270 |
+
"learning_rate": 0.00043991416309012877,
|
| 271 |
+
"loss": 0.4288,
|
| 272 |
+
"step": 205
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.24,
|
| 276 |
+
"learning_rate": 0.0004506437768240343,
|
| 277 |
+
"loss": 0.3266,
|
| 278 |
+
"step": 210
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.29,
|
| 282 |
+
"learning_rate": 0.00046137339055793994,
|
| 283 |
+
"loss": 0.3499,
|
| 284 |
+
"step": 215
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.35,
|
| 288 |
+
"learning_rate": 0.0004721030042918455,
|
| 289 |
+
"loss": 0.1853,
|
| 290 |
+
"step": 220
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.4,
|
| 294 |
+
"learning_rate": 0.00048283261802575106,
|
| 295 |
+
"loss": 0.2131,
|
| 296 |
+
"step": 225
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.45,
|
| 300 |
+
"learning_rate": 0.0004935622317596566,
|
| 301 |
+
"loss": 0.3181,
|
| 302 |
+
"step": 230
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.51,
|
| 306 |
+
"learning_rate": 0.0004956896551724138,
|
| 307 |
+
"loss": 0.2982,
|
| 308 |
+
"step": 235
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.56,
|
| 312 |
+
"learning_rate": 0.0004849137931034483,
|
| 313 |
+
"loss": 0.204,
|
| 314 |
+
"step": 240
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.61,
|
| 318 |
+
"learning_rate": 0.00047413793103448276,
|
| 319 |
+
"loss": 0.2397,
|
| 320 |
+
"step": 245
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.67,
|
| 324 |
+
"learning_rate": 0.00046336206896551726,
|
| 325 |
+
"loss": 0.2364,
|
| 326 |
+
"step": 250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.72,
|
| 330 |
+
"learning_rate": 0.0004525862068965517,
|
| 331 |
+
"loss": 0.386,
|
| 332 |
+
"step": 255
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.77,
|
| 336 |
+
"learning_rate": 0.0004418103448275862,
|
| 337 |
+
"loss": 0.2408,
|
| 338 |
+
"step": 260
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.83,
|
| 342 |
+
"learning_rate": 0.0004310344827586207,
|
| 343 |
+
"loss": 0.2186,
|
| 344 |
+
"step": 265
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.88,
|
| 348 |
+
"learning_rate": 0.0004202586206896552,
|
| 349 |
+
"loss": 0.1758,
|
| 350 |
+
"step": 270
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.93,
|
| 354 |
+
"learning_rate": 0.00040948275862068967,
|
| 355 |
+
"loss": 0.1743,
|
| 356 |
+
"step": 275
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.99,
|
| 360 |
+
"learning_rate": 0.00039870689655172416,
|
| 361 |
+
"loss": 0.2517,
|
| 362 |
+
"step": 280
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.0,
|
| 366 |
+
"eval_accuracy": 0.9401993355481728,
|
| 367 |
+
"eval_loss": 0.14838582277297974,
|
| 368 |
+
"eval_runtime": 173.6514,
|
| 369 |
+
"eval_samples_per_second": 26.0,
|
| 370 |
+
"eval_steps_per_second": 1.63,
|
| 371 |
+
"step": 281
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.04,
|
| 375 |
+
"learning_rate": 0.0003879310344827586,
|
| 376 |
+
"loss": 0.1926,
|
| 377 |
+
"step": 285
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.09,
|
| 381 |
+
"learning_rate": 0.0003771551724137931,
|
| 382 |
+
"loss": 0.2566,
|
| 383 |
+
"step": 290
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.15,
|
| 387 |
+
"learning_rate": 0.0003663793103448276,
|
| 388 |
+
"loss": 0.2189,
|
| 389 |
+
"step": 295
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.2,
|
| 393 |
+
"learning_rate": 0.00035560344827586203,
|
| 394 |
+
"loss": 0.17,
|
| 395 |
+
"step": 300
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.25,
|
| 399 |
+
"learning_rate": 0.0003448275862068966,
|
| 400 |
+
"loss": 0.2557,
|
| 401 |
+
"step": 305
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.31,
|
| 405 |
+
"learning_rate": 0.0003340517241379311,
|
| 406 |
+
"loss": 0.2607,
|
| 407 |
+
"step": 310
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.36,
|
| 411 |
+
"learning_rate": 0.0003232758620689655,
|
| 412 |
+
"loss": 0.1703,
|
| 413 |
+
"step": 315
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.41,
|
| 417 |
+
"learning_rate": 0.0003125,
|
| 418 |
+
"loss": 0.1908,
|
| 419 |
+
"step": 320
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.47,
|
| 423 |
+
"learning_rate": 0.0003017241379310345,
|
| 424 |
+
"loss": 0.1231,
|
| 425 |
+
"step": 325
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.52,
|
| 429 |
+
"learning_rate": 0.00029094827586206894,
|
| 430 |
+
"loss": 0.1843,
|
| 431 |
+
"step": 330
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.57,
|
| 435 |
+
"learning_rate": 0.00028017241379310343,
|
| 436 |
+
"loss": 0.2714,
|
| 437 |
+
"step": 335
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.63,
|
| 441 |
+
"learning_rate": 0.000269396551724138,
|
| 442 |
+
"loss": 0.1593,
|
| 443 |
+
"step": 340
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.68,
|
| 447 |
+
"learning_rate": 0.0002586206896551724,
|
| 448 |
+
"loss": 0.1333,
|
| 449 |
+
"step": 345
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.73,
|
| 453 |
+
"learning_rate": 0.0002478448275862069,
|
| 454 |
+
"loss": 0.1681,
|
| 455 |
+
"step": 350
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.79,
|
| 459 |
+
"learning_rate": 0.00023706896551724138,
|
| 460 |
+
"loss": 0.1455,
|
| 461 |
+
"step": 355
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.84,
|
| 465 |
+
"learning_rate": 0.00022629310344827585,
|
| 466 |
+
"loss": 0.1066,
|
| 467 |
+
"step": 360
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.89,
|
| 471 |
+
"learning_rate": 0.00021551724137931034,
|
| 472 |
+
"loss": 0.0931,
|
| 473 |
+
"step": 365
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 3.95,
|
| 477 |
+
"learning_rate": 0.00020474137931034484,
|
| 478 |
+
"loss": 0.1979,
|
| 479 |
+
"step": 370
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.0,
|
| 483 |
+
"learning_rate": 0.0001939655172413793,
|
| 484 |
+
"loss": 0.1769,
|
| 485 |
+
"step": 375
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.0,
|
| 489 |
+
"eval_accuracy": 0.9570321151716501,
|
| 490 |
+
"eval_loss": 0.11080712080001831,
|
| 491 |
+
"eval_runtime": 173.6912,
|
| 492 |
+
"eval_samples_per_second": 25.994,
|
| 493 |
+
"eval_steps_per_second": 1.629,
|
| 494 |
+
"step": 375
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.05,
|
| 498 |
+
"learning_rate": 0.0001831896551724138,
|
| 499 |
+
"loss": 0.1417,
|
| 500 |
+
"step": 380
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.11,
|
| 504 |
+
"learning_rate": 0.0001724137931034483,
|
| 505 |
+
"loss": 0.198,
|
| 506 |
+
"step": 385
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.16,
|
| 510 |
+
"learning_rate": 0.00016163793103448276,
|
| 511 |
+
"loss": 0.164,
|
| 512 |
+
"step": 390
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.21,
|
| 516 |
+
"learning_rate": 0.00015086206896551725,
|
| 517 |
+
"loss": 0.1534,
|
| 518 |
+
"step": 395
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.27,
|
| 522 |
+
"learning_rate": 0.00014008620689655172,
|
| 523 |
+
"loss": 0.1645,
|
| 524 |
+
"step": 400
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.32,
|
| 528 |
+
"learning_rate": 0.0001293103448275862,
|
| 529 |
+
"loss": 0.1008,
|
| 530 |
+
"step": 405
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.37,
|
| 534 |
+
"learning_rate": 0.00011853448275862069,
|
| 535 |
+
"loss": 0.1344,
|
| 536 |
+
"step": 410
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.43,
|
| 540 |
+
"learning_rate": 0.00010775862068965517,
|
| 541 |
+
"loss": 0.0964,
|
| 542 |
+
"step": 415
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.48,
|
| 546 |
+
"learning_rate": 9.698275862068965e-05,
|
| 547 |
+
"loss": 0.0954,
|
| 548 |
+
"step": 420
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.53,
|
| 552 |
+
"learning_rate": 8.620689655172414e-05,
|
| 553 |
+
"loss": 0.1101,
|
| 554 |
+
"step": 425
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.59,
|
| 558 |
+
"learning_rate": 7.543103448275863e-05,
|
| 559 |
+
"loss": 0.0681,
|
| 560 |
+
"step": 430
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.64,
|
| 564 |
+
"learning_rate": 6.46551724137931e-05,
|
| 565 |
+
"loss": 0.1394,
|
| 566 |
+
"step": 435
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.69,
|
| 570 |
+
"learning_rate": 5.3879310344827585e-05,
|
| 571 |
+
"loss": 0.1221,
|
| 572 |
+
"step": 440
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.75,
|
| 576 |
+
"learning_rate": 4.310344827586207e-05,
|
| 577 |
+
"loss": 0.1046,
|
| 578 |
+
"step": 445
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.8,
|
| 582 |
+
"learning_rate": 3.232758620689655e-05,
|
| 583 |
+
"loss": 0.0807,
|
| 584 |
+
"step": 450
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.85,
|
| 588 |
+
"learning_rate": 2.1551724137931036e-05,
|
| 589 |
+
"loss": 0.069,
|
| 590 |
+
"step": 455
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 4.91,
|
| 594 |
+
"learning_rate": 1.0775862068965518e-05,
|
| 595 |
+
"loss": 0.1025,
|
| 596 |
+
"step": 460
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.96,
|
| 600 |
+
"learning_rate": 0.0,
|
| 601 |
+
"loss": 0.0764,
|
| 602 |
+
"step": 465
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 4.96,
|
| 606 |
+
"eval_accuracy": 0.9765227021040974,
|
| 607 |
+
"eval_loss": 0.060047686100006104,
|
| 608 |
+
"eval_runtime": 173.6863,
|
| 609 |
+
"eval_samples_per_second": 25.995,
|
| 610 |
+
"eval_steps_per_second": 1.629,
|
| 611 |
+
"step": 465
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 4.96,
|
| 615 |
+
"step": 465,
|
| 616 |
+
"total_flos": 8.138660625246413e+18,
|
| 617 |
+
"train_loss": 0.22687274961061374,
|
| 618 |
+
"train_runtime": 10415.6562,
|
| 619 |
+
"train_samples_per_second": 2.873,
|
| 620 |
+
"train_steps_per_second": 0.045
|
| 621 |
+
}
|
| 622 |
+
],
|
| 623 |
+
"max_steps": 465,
|
| 624 |
+
"num_train_epochs": 5,
|
| 625 |
+
"total_flos": 8.138660625246413e+18,
|
| 626 |
+
"trial_name": null,
|
| 627 |
+
"trial_params": null
|
| 628 |
+
}
|