End of training
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Sep23_12-56-30_Hang-Inspiron16/events.out.tfevents.1727111807.Hang-Inspiron16.18160.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +374 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
+
- vision
|
| 8 |
- generated_from_trainer
|
| 9 |
datasets:
|
| 10 |
- imagefolder
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.7739130434782608,
|
| 4 |
+
"eval_loss": 0.46259966492652893,
|
| 5 |
+
"eval_runtime": 12.6959,
|
| 6 |
+
"eval_samples_per_second": 9.058,
|
| 7 |
+
"eval_steps_per_second": 1.181,
|
| 8 |
+
"total_flos": 2.5223642619549696e+17,
|
| 9 |
+
"train_loss": 0.48874526954278713,
|
| 10 |
+
"train_runtime": 1194.2371,
|
| 11 |
+
"train_samples_per_second": 2.726,
|
| 12 |
+
"train_steps_per_second": 0.343
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.7739130434782608,
|
| 4 |
+
"eval_loss": 0.46259966492652893,
|
| 5 |
+
"eval_runtime": 12.6959,
|
| 6 |
+
"eval_samples_per_second": 9.058,
|
| 7 |
+
"eval_steps_per_second": 1.181
|
| 8 |
+
}
|
runs/Sep23_12-56-30_Hang-Inspiron16/events.out.tfevents.1727111807.Hang-Inspiron16.18160.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b04f0ac9276a080cd61e697176794507725322707b54523998412605b7ae02c
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 2.5223642619549696e+17,
|
| 4 |
+
"train_loss": 0.48874526954278713,
|
| 5 |
+
"train_runtime": 1194.2371,
|
| 6 |
+
"train_samples_per_second": 2.726,
|
| 7 |
+
"train_steps_per_second": 0.343
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.46259966492652893,
|
| 3 |
+
"best_model_checkpoint": "./TransparentBagClassifier/checkpoint-410",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 410,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12195121951219512,
|
| 13 |
+
"grad_norm": 1.9288002252578735,
|
| 14 |
+
"learning_rate": 1.9512195121951222e-05,
|
| 15 |
+
"loss": 0.639,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.24390243902439024,
|
| 20 |
+
"grad_norm": 1.795539379119873,
|
| 21 |
+
"learning_rate": 1.902439024390244e-05,
|
| 22 |
+
"loss": 0.6215,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.36585365853658536,
|
| 27 |
+
"grad_norm": 3.186365842819214,
|
| 28 |
+
"learning_rate": 1.8536585365853663e-05,
|
| 29 |
+
"loss": 0.5834,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4878048780487805,
|
| 34 |
+
"grad_norm": 2.8957085609436035,
|
| 35 |
+
"learning_rate": 1.804878048780488e-05,
|
| 36 |
+
"loss": 0.608,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.6097560975609756,
|
| 41 |
+
"grad_norm": 2.6288256645202637,
|
| 42 |
+
"learning_rate": 1.75609756097561e-05,
|
| 43 |
+
"loss": 0.6492,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.7317073170731707,
|
| 48 |
+
"grad_norm": 2.7670204639434814,
|
| 49 |
+
"learning_rate": 1.7073170731707317e-05,
|
| 50 |
+
"loss": 0.6062,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.8536585365853658,
|
| 55 |
+
"grad_norm": 2.380261182785034,
|
| 56 |
+
"learning_rate": 1.6585365853658537e-05,
|
| 57 |
+
"loss": 0.5372,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.975609756097561,
|
| 62 |
+
"grad_norm": 2.4240152835845947,
|
| 63 |
+
"learning_rate": 1.6097560975609757e-05,
|
| 64 |
+
"loss": 0.448,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"eval_accuracy": 0.7304347826086957,
|
| 70 |
+
"eval_loss": 0.5725326538085938,
|
| 71 |
+
"eval_runtime": 13.2774,
|
| 72 |
+
"eval_samples_per_second": 8.661,
|
| 73 |
+
"eval_steps_per_second": 1.13,
|
| 74 |
+
"step": 82
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0975609756097562,
|
| 78 |
+
"grad_norm": 1.8054224252700806,
|
| 79 |
+
"learning_rate": 1.5609756097560978e-05,
|
| 80 |
+
"loss": 0.5777,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.2195121951219512,
|
| 85 |
+
"grad_norm": 2.1294147968292236,
|
| 86 |
+
"learning_rate": 1.5121951219512196e-05,
|
| 87 |
+
"loss": 0.6131,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.3414634146341464,
|
| 92 |
+
"grad_norm": 2.426273822784424,
|
| 93 |
+
"learning_rate": 1.4634146341463415e-05,
|
| 94 |
+
"loss": 0.5493,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.4634146341463414,
|
| 99 |
+
"grad_norm": 2.6345632076263428,
|
| 100 |
+
"learning_rate": 1.4146341463414635e-05,
|
| 101 |
+
"loss": 0.5506,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5853658536585367,
|
| 106 |
+
"grad_norm": 2.231985569000244,
|
| 107 |
+
"learning_rate": 1.3658536585365855e-05,
|
| 108 |
+
"loss": 0.4764,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.7073170731707317,
|
| 113 |
+
"grad_norm": 2.486055850982666,
|
| 114 |
+
"learning_rate": 1.3170731707317076e-05,
|
| 115 |
+
"loss": 0.3848,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.8292682926829267,
|
| 120 |
+
"grad_norm": 4.828785419464111,
|
| 121 |
+
"learning_rate": 1.2682926829268294e-05,
|
| 122 |
+
"loss": 0.5178,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.951219512195122,
|
| 127 |
+
"grad_norm": 2.4976108074188232,
|
| 128 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 129 |
+
"loss": 0.5097,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.0,
|
| 134 |
+
"eval_accuracy": 0.7652173913043478,
|
| 135 |
+
"eval_loss": 0.4945763945579529,
|
| 136 |
+
"eval_runtime": 13.2493,
|
| 137 |
+
"eval_samples_per_second": 8.68,
|
| 138 |
+
"eval_steps_per_second": 1.132,
|
| 139 |
+
"step": 164
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.073170731707317,
|
| 143 |
+
"grad_norm": 3.168379068374634,
|
| 144 |
+
"learning_rate": 1.1707317073170731e-05,
|
| 145 |
+
"loss": 0.4253,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.1951219512195124,
|
| 150 |
+
"grad_norm": 4.656283378601074,
|
| 151 |
+
"learning_rate": 1.1219512195121953e-05,
|
| 152 |
+
"loss": 0.5243,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.317073170731707,
|
| 157 |
+
"grad_norm": 2.9091641902923584,
|
| 158 |
+
"learning_rate": 1.0731707317073172e-05,
|
| 159 |
+
"loss": 0.4482,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.4390243902439024,
|
| 164 |
+
"grad_norm": 3.3256161212921143,
|
| 165 |
+
"learning_rate": 1.024390243902439e-05,
|
| 166 |
+
"loss": 0.6001,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.5609756097560976,
|
| 171 |
+
"grad_norm": 4.491713047027588,
|
| 172 |
+
"learning_rate": 9.756097560975611e-06,
|
| 173 |
+
"loss": 0.4818,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.682926829268293,
|
| 178 |
+
"grad_norm": 2.668192148208618,
|
| 179 |
+
"learning_rate": 9.268292682926831e-06,
|
| 180 |
+
"loss": 0.4202,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.8048780487804876,
|
| 185 |
+
"grad_norm": 3.90390944480896,
|
| 186 |
+
"learning_rate": 8.78048780487805e-06,
|
| 187 |
+
"loss": 0.447,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.926829268292683,
|
| 192 |
+
"grad_norm": 4.300001621246338,
|
| 193 |
+
"learning_rate": 8.292682926829268e-06,
|
| 194 |
+
"loss": 0.452,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.0,
|
| 199 |
+
"eval_accuracy": 0.7565217391304347,
|
| 200 |
+
"eval_loss": 0.48406168818473816,
|
| 201 |
+
"eval_runtime": 12.8922,
|
| 202 |
+
"eval_samples_per_second": 8.92,
|
| 203 |
+
"eval_steps_per_second": 1.163,
|
| 204 |
+
"step": 246
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.048780487804878,
|
| 208 |
+
"grad_norm": 1.386968970298767,
|
| 209 |
+
"learning_rate": 7.804878048780489e-06,
|
| 210 |
+
"loss": 0.4124,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.1707317073170733,
|
| 215 |
+
"grad_norm": 3.373535633087158,
|
| 216 |
+
"learning_rate": 7.317073170731707e-06,
|
| 217 |
+
"loss": 0.4285,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.292682926829268,
|
| 222 |
+
"grad_norm": 4.440028190612793,
|
| 223 |
+
"learning_rate": 6.829268292682928e-06,
|
| 224 |
+
"loss": 0.5181,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.4146341463414633,
|
| 229 |
+
"grad_norm": 3.297926425933838,
|
| 230 |
+
"learning_rate": 6.341463414634147e-06,
|
| 231 |
+
"loss": 0.452,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.5365853658536586,
|
| 236 |
+
"grad_norm": 1.8083200454711914,
|
| 237 |
+
"learning_rate": 5.853658536585366e-06,
|
| 238 |
+
"loss": 0.4684,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.658536585365854,
|
| 243 |
+
"grad_norm": 2.8701059818267822,
|
| 244 |
+
"learning_rate": 5.365853658536586e-06,
|
| 245 |
+
"loss": 0.3982,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.7804878048780486,
|
| 250 |
+
"grad_norm": 5.826732635498047,
|
| 251 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 252 |
+
"loss": 0.4161,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.902439024390244,
|
| 257 |
+
"grad_norm": 1.7296645641326904,
|
| 258 |
+
"learning_rate": 4.390243902439025e-06,
|
| 259 |
+
"loss": 0.3885,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.0,
|
| 264 |
+
"eval_accuracy": 0.7565217391304347,
|
| 265 |
+
"eval_loss": 0.48118799924850464,
|
| 266 |
+
"eval_runtime": 13.093,
|
| 267 |
+
"eval_samples_per_second": 8.783,
|
| 268 |
+
"eval_steps_per_second": 1.146,
|
| 269 |
+
"step": 328
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.024390243902439,
|
| 273 |
+
"grad_norm": 1.9118701219558716,
|
| 274 |
+
"learning_rate": 3.902439024390244e-06,
|
| 275 |
+
"loss": 0.4334,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.146341463414634,
|
| 280 |
+
"grad_norm": 2.3522226810455322,
|
| 281 |
+
"learning_rate": 3.414634146341464e-06,
|
| 282 |
+
"loss": 0.4392,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.2682926829268295,
|
| 287 |
+
"grad_norm": 2.4978580474853516,
|
| 288 |
+
"learning_rate": 2.926829268292683e-06,
|
| 289 |
+
"loss": 0.3711,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.390243902439025,
|
| 294 |
+
"grad_norm": 7.186872959136963,
|
| 295 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 296 |
+
"loss": 0.524,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.512195121951219,
|
| 301 |
+
"grad_norm": 2.313222885131836,
|
| 302 |
+
"learning_rate": 1.951219512195122e-06,
|
| 303 |
+
"loss": 0.3826,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.634146341463414,
|
| 308 |
+
"grad_norm": 4.187412261962891,
|
| 309 |
+
"learning_rate": 1.4634146341463414e-06,
|
| 310 |
+
"loss": 0.3764,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.7560975609756095,
|
| 315 |
+
"grad_norm": 3.5783486366271973,
|
| 316 |
+
"learning_rate": 9.75609756097561e-07,
|
| 317 |
+
"loss": 0.414,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.878048780487805,
|
| 322 |
+
"grad_norm": 6.643193244934082,
|
| 323 |
+
"learning_rate": 4.878048780487805e-07,
|
| 324 |
+
"loss": 0.4708,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 5.0,
|
| 329 |
+
"grad_norm": 4.836371898651123,
|
| 330 |
+
"learning_rate": 0.0,
|
| 331 |
+
"loss": 0.4743,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 5.0,
|
| 336 |
+
"eval_accuracy": 0.7739130434782608,
|
| 337 |
+
"eval_loss": 0.46259966492652893,
|
| 338 |
+
"eval_runtime": 13.4253,
|
| 339 |
+
"eval_samples_per_second": 8.566,
|
| 340 |
+
"eval_steps_per_second": 1.117,
|
| 341 |
+
"step": 410
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.0,
|
| 345 |
+
"step": 410,
|
| 346 |
+
"total_flos": 2.5223642619549696e+17,
|
| 347 |
+
"train_loss": 0.48874526954278713,
|
| 348 |
+
"train_runtime": 1194.2371,
|
| 349 |
+
"train_samples_per_second": 2.726,
|
| 350 |
+
"train_steps_per_second": 0.343
|
| 351 |
+
}
|
| 352 |
+
],
|
| 353 |
+
"logging_steps": 10,
|
| 354 |
+
"max_steps": 410,
|
| 355 |
+
"num_input_tokens_seen": 0,
|
| 356 |
+
"num_train_epochs": 5,
|
| 357 |
+
"save_steps": 500,
|
| 358 |
+
"stateful_callbacks": {
|
| 359 |
+
"TrainerControl": {
|
| 360 |
+
"args": {
|
| 361 |
+
"should_epoch_stop": false,
|
| 362 |
+
"should_evaluate": false,
|
| 363 |
+
"should_log": false,
|
| 364 |
+
"should_save": true,
|
| 365 |
+
"should_training_stop": true
|
| 366 |
+
},
|
| 367 |
+
"attributes": {}
|
| 368 |
+
}
|
| 369 |
+
},
|
| 370 |
+
"total_flos": 2.5223642619549696e+17,
|
| 371 |
+
"train_batch_size": 8,
|
| 372 |
+
"trial_name": null,
|
| 373 |
+
"trial_params": null
|
| 374 |
+
}
|