Training in progress, epoch 0
Browse files- all_results.json +6 -6
- pytorch_model.bin +2 -2
- test_results.json +6 -6
- trainer_state.json +2625 -141
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 12.
|
| 6 |
-
"eval_samples_per_second": 12.
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 49.02,
|
| 3 |
+
"eval_accuracy": 0.9290322580645162,
|
| 4 |
+
"eval_loss": 0.18336611986160278,
|
| 5 |
+
"eval_runtime": 12.5538,
|
| 6 |
+
"eval_samples_per_second": 12.347,
|
| 7 |
+
"eval_steps_per_second": 3.107
|
| 8 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9096bcea0ea88532ce48f9fe3977c8863c167e714fc05191dc86fb3e1bc64c2
|
| 3 |
+
size 345004516
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 12.
|
| 6 |
-
"eval_samples_per_second": 12.
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 49.02,
|
| 3 |
+
"eval_accuracy": 0.9290322580645162,
|
| 4 |
+
"eval_loss": 0.18336611986160278,
|
| 5 |
+
"eval_runtime": 12.5538,
|
| 6 |
+
"eval_samples_per_second": 12.347,
|
| 7 |
+
"eval_steps_per_second": 3.107
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,259 +1,2743 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate": 1.
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 2.
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 2.
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 2.
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss":
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"eval_accuracy": 0.
|
| 55 |
-
"eval_loss":
|
| 56 |
-
"eval_runtime":
|
| 57 |
-
"eval_samples_per_second":
|
| 58 |
-
"eval_steps_per_second": 3.
|
| 59 |
"step": 75
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 1.
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss":
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch": 1.
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss":
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch": 1.
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss":
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch": 1.
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss":
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch": 1.
|
| 93 |
-
"learning_rate":
|
| 94 |
-
"loss":
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch": 1.
|
| 99 |
-
"learning_rate":
|
| 100 |
-
"loss":
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 1.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss":
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 1.
|
| 111 |
-
"eval_accuracy": 0.
|
| 112 |
-
"eval_loss":
|
| 113 |
-
"eval_runtime": 5.
|
| 114 |
-
"eval_samples_per_second": 12.
|
| 115 |
-
"eval_steps_per_second": 3.
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 2.
|
| 120 |
-
"learning_rate": 2.
|
| 121 |
-
"loss":
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 2.
|
| 126 |
-
"learning_rate": 2.
|
| 127 |
-
"loss":
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 2.
|
| 132 |
-
"learning_rate": 2.
|
| 133 |
-
"loss":
|
| 134 |
"step": 180
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 2.
|
| 138 |
-
"learning_rate": 2.
|
| 139 |
-
"loss":
|
| 140 |
"step": 190
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 2.
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss":
|
| 146 |
"step": 200
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch": 2.
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 210
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 2.
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 220
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 2.
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_loss": 0.
|
| 164 |
-
"eval_runtime": 5.
|
| 165 |
-
"eval_samples_per_second": 12.
|
| 166 |
-
"eval_steps_per_second": 3.
|
| 167 |
"step": 225
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 3.
|
| 171 |
-
"learning_rate":
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 230
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 3.
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 0.
|
| 179 |
"step": 240
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 3.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 3.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 3.
|
| 195 |
-
"learning_rate":
|
| 196 |
-
"loss": 0.
|
| 197 |
"step": 270
|
| 198 |
},
|
| 199 |
{
|
| 200 |
-
"epoch": 3.
|
| 201 |
-
"learning_rate": 3.
|
| 202 |
-
"loss": 0.
|
| 203 |
"step": 280
|
| 204 |
},
|
| 205 |
{
|
| 206 |
-
"epoch": 3.
|
| 207 |
-
"learning_rate":
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 290
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch": 3.
|
| 213 |
-
"learning_rate":
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 300
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch": 3.
|
| 219 |
-
"eval_accuracy": 0.
|
| 220 |
-
"eval_loss": 0.
|
| 221 |
-
"eval_runtime": 6.
|
| 222 |
-
"eval_samples_per_second": 11.
|
| 223 |
-
"eval_steps_per_second": 2.
|
| 224 |
"step": 300
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"train_runtime": 221.509,
|
| 232 |
-
"train_samples_per_second": 5.417,
|
| 233 |
-
"train_steps_per_second": 1.354
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch":
|
| 237 |
-
"
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"eval_samples_per_second": 11.105,
|
| 241 |
-
"eval_steps_per_second": 2.794,
|
| 242 |
-
"step": 300
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
}
|
| 253 |
],
|
| 254 |
-
"max_steps":
|
| 255 |
"num_train_epochs": 9223372036854775807,
|
| 256 |
-
"total_flos": 1.
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|
| 259 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9857142857142858,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-1425",
|
| 4 |
+
"epoch": 49.02,
|
| 5 |
+
"global_step": 3750,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 13 |
+
"loss": 2.3169,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 2.666666666666667e-06,
|
| 19 |
+
"loss": 2.3252,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.01,
|
| 24 |
+
"learning_rate": 4.000000000000001e-06,
|
| 25 |
+
"loss": 2.2807,
|
| 26 |
"step": 30
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.01,
|
| 30 |
+
"learning_rate": 5.333333333333334e-06,
|
| 31 |
+
"loss": 2.2992,
|
| 32 |
"step": 40
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.01,
|
| 36 |
+
"learning_rate": 6.666666666666667e-06,
|
| 37 |
+
"loss": 2.2765,
|
| 38 |
"step": 50
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 8.000000000000001e-06,
|
| 43 |
+
"loss": 2.2692,
|
| 44 |
"step": 60
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"learning_rate": 9.333333333333334e-06,
|
| 49 |
+
"loss": 2.2357,
|
| 50 |
"step": 70
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.02,
|
| 54 |
+
"eval_accuracy": 0.34285714285714286,
|
| 55 |
+
"eval_loss": 2.195152759552002,
|
| 56 |
+
"eval_runtime": 5.4445,
|
| 57 |
+
"eval_samples_per_second": 12.857,
|
| 58 |
+
"eval_steps_per_second": 3.306,
|
| 59 |
"step": 75
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 1.0,
|
| 63 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 64 |
+
"loss": 2.2979,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"learning_rate": 1.2e-05,
|
| 70 |
+
"loss": 2.1564,
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 1.01,
|
| 75 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 76 |
+
"loss": 2.1848,
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 1.01,
|
| 81 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 82 |
+
"loss": 2.072,
|
| 83 |
"step": 110
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 1.01,
|
| 87 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 88 |
+
"loss": 2.0733,
|
| 89 |
"step": 120
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 1.01,
|
| 93 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 94 |
+
"loss": 2.0719,
|
| 95 |
"step": 130
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 1.02,
|
| 99 |
+
"learning_rate": 1.866666666666667e-05,
|
| 100 |
+
"loss": 2.0285,
|
| 101 |
"step": 140
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 1.02,
|
| 105 |
+
"learning_rate": 2e-05,
|
| 106 |
+
"loss": 1.8271,
|
| 107 |
"step": 150
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 1.02,
|
| 111 |
+
"eval_accuracy": 0.35714285714285715,
|
| 112 |
+
"eval_loss": 1.8570266962051392,
|
| 113 |
+
"eval_runtime": 5.776,
|
| 114 |
+
"eval_samples_per_second": 12.119,
|
| 115 |
+
"eval_steps_per_second": 3.116,
|
| 116 |
"step": 150
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 2.0,
|
| 120 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 121 |
+
"loss": 1.6139,
|
| 122 |
"step": 160
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 2.01,
|
| 126 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 127 |
+
"loss": 1.424,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 2.01,
|
| 132 |
+
"learning_rate": 2.4e-05,
|
| 133 |
+
"loss": 1.3944,
|
| 134 |
"step": 180
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 2.01,
|
| 138 |
+
"learning_rate": 2.5333333333333337e-05,
|
| 139 |
+
"loss": 1.1121,
|
| 140 |
"step": 190
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 2.01,
|
| 144 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 145 |
+
"loss": 1.0835,
|
| 146 |
"step": 200
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 2.02,
|
| 150 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 151 |
+
"loss": 0.9839,
|
| 152 |
"step": 210
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 2.02,
|
| 156 |
+
"learning_rate": 2.9333333333333336e-05,
|
| 157 |
+
"loss": 0.8947,
|
| 158 |
"step": 220
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 2.02,
|
| 162 |
+
"eval_accuracy": 0.7285714285714285,
|
| 163 |
+
"eval_loss": 0.839695155620575,
|
| 164 |
+
"eval_runtime": 5.7359,
|
| 165 |
+
"eval_samples_per_second": 12.204,
|
| 166 |
+
"eval_steps_per_second": 3.138,
|
| 167 |
"step": 225
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 3.0,
|
| 171 |
+
"learning_rate": 3.066666666666667e-05,
|
| 172 |
+
"loss": 0.8324,
|
| 173 |
"step": 230
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 3.0,
|
| 177 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 178 |
+
"loss": 0.6889,
|
| 179 |
"step": 240
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 3.01,
|
| 183 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 184 |
+
"loss": 0.6668,
|
| 185 |
"step": 250
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 3.01,
|
| 189 |
+
"learning_rate": 3.466666666666667e-05,
|
| 190 |
+
"loss": 0.6746,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 3.01,
|
| 195 |
+
"learning_rate": 3.6e-05,
|
| 196 |
+
"loss": 0.7853,
|
| 197 |
"step": 270
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 3.01,
|
| 201 |
+
"learning_rate": 3.733333333333334e-05,
|
| 202 |
+
"loss": 0.3688,
|
| 203 |
"step": 280
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 3.02,
|
| 207 |
+
"learning_rate": 3.866666666666667e-05,
|
| 208 |
+
"loss": 0.4888,
|
| 209 |
"step": 290
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 3.02,
|
| 213 |
+
"learning_rate": 4e-05,
|
| 214 |
+
"loss": 0.5347,
|
| 215 |
"step": 300
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 3.02,
|
| 219 |
+
"eval_accuracy": 0.8285714285714286,
|
| 220 |
+
"eval_loss": 0.5631577968597412,
|
| 221 |
+
"eval_runtime": 6.1294,
|
| 222 |
+
"eval_samples_per_second": 11.42,
|
| 223 |
+
"eval_steps_per_second": 2.937,
|
| 224 |
"step": 300
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 4.0,
|
| 228 |
+
"learning_rate": 4.133333333333333e-05,
|
| 229 |
+
"loss": 0.4236,
|
| 230 |
+
"step": 310
|
|
|
|
|
|
|
|
|
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 4.01,
|
| 234 |
+
"learning_rate": 4.266666666666667e-05,
|
| 235 |
+
"loss": 0.4206,
|
| 236 |
+
"step": 320
|
|
|
|
|
|
|
|
|
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 4.01,
|
| 240 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 241 |
+
"loss": 0.4133,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.01,
|
| 246 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 247 |
+
"loss": 0.6152,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.01,
|
| 252 |
+
"learning_rate": 4.666666666666667e-05,
|
| 253 |
+
"loss": 0.7022,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.02,
|
| 258 |
+
"learning_rate": 4.8e-05,
|
| 259 |
+
"loss": 0.4414,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.02,
|
| 264 |
+
"learning_rate": 4.933333333333334e-05,
|
| 265 |
+
"loss": 0.4101,
|
| 266 |
+
"step": 370
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.02,
|
| 270 |
+
"eval_accuracy": 0.8,
|
| 271 |
+
"eval_loss": 0.690824031829834,
|
| 272 |
+
"eval_runtime": 5.752,
|
| 273 |
+
"eval_samples_per_second": 12.17,
|
| 274 |
+
"eval_steps_per_second": 3.129,
|
| 275 |
+
"step": 375
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.0,
|
| 279 |
+
"learning_rate": 4.9925925925925926e-05,
|
| 280 |
+
"loss": 0.1599,
|
| 281 |
+
"step": 380
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 5.0,
|
| 285 |
+
"learning_rate": 4.977777777777778e-05,
|
| 286 |
+
"loss": 0.3312,
|
| 287 |
+
"step": 390
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.01,
|
| 291 |
+
"learning_rate": 4.962962962962963e-05,
|
| 292 |
+
"loss": 0.3967,
|
| 293 |
+
"step": 400
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.01,
|
| 297 |
+
"learning_rate": 4.9481481481481485e-05,
|
| 298 |
+
"loss": 0.3926,
|
| 299 |
+
"step": 410
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.01,
|
| 303 |
+
"learning_rate": 4.933333333333334e-05,
|
| 304 |
+
"loss": 0.8443,
|
| 305 |
+
"step": 420
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 5.01,
|
| 309 |
+
"learning_rate": 4.918518518518519e-05,
|
| 310 |
+
"loss": 0.4227,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 5.02,
|
| 315 |
+
"learning_rate": 4.903703703703704e-05,
|
| 316 |
+
"loss": 0.2168,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 5.02,
|
| 321 |
+
"learning_rate": 4.888888888888889e-05,
|
| 322 |
+
"loss": 0.0855,
|
| 323 |
+
"step": 450
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 5.02,
|
| 327 |
+
"eval_accuracy": 0.9571428571428572,
|
| 328 |
+
"eval_loss": 0.1541331708431244,
|
| 329 |
+
"eval_runtime": 5.9819,
|
| 330 |
+
"eval_samples_per_second": 11.702,
|
| 331 |
+
"eval_steps_per_second": 3.009,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.0,
|
| 336 |
+
"learning_rate": 4.874074074074074e-05,
|
| 337 |
+
"loss": 0.0751,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.01,
|
| 342 |
+
"learning_rate": 4.8592592592592596e-05,
|
| 343 |
+
"loss": 0.2454,
|
| 344 |
+
"step": 470
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.01,
|
| 348 |
+
"learning_rate": 4.844444444444445e-05,
|
| 349 |
+
"loss": 0.3209,
|
| 350 |
+
"step": 480
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.01,
|
| 354 |
+
"learning_rate": 4.82962962962963e-05,
|
| 355 |
+
"loss": 0.3679,
|
| 356 |
+
"step": 490
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.01,
|
| 360 |
+
"learning_rate": 4.814814814814815e-05,
|
| 361 |
+
"loss": 0.2122,
|
| 362 |
+
"step": 500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.02,
|
| 366 |
+
"learning_rate": 4.8e-05,
|
| 367 |
+
"loss": 0.1339,
|
| 368 |
+
"step": 510
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.02,
|
| 372 |
+
"learning_rate": 4.7851851851851854e-05,
|
| 373 |
+
"loss": 0.2286,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.02,
|
| 378 |
+
"eval_accuracy": 0.9,
|
| 379 |
+
"eval_loss": 0.2762179374694824,
|
| 380 |
+
"eval_runtime": 5.6813,
|
| 381 |
+
"eval_samples_per_second": 12.321,
|
| 382 |
+
"eval_steps_per_second": 3.168,
|
| 383 |
+
"step": 525
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.0,
|
| 387 |
+
"learning_rate": 4.770370370370371e-05,
|
| 388 |
+
"loss": 0.3897,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.0,
|
| 393 |
+
"learning_rate": 4.755555555555556e-05,
|
| 394 |
+
"loss": 0.0845,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.01,
|
| 399 |
+
"learning_rate": 4.740740740740741e-05,
|
| 400 |
+
"loss": 0.3024,
|
| 401 |
+
"step": 550
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.01,
|
| 405 |
+
"learning_rate": 4.7259259259259266e-05,
|
| 406 |
+
"loss": 0.0144,
|
| 407 |
+
"step": 560
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.01,
|
| 411 |
+
"learning_rate": 4.711111111111111e-05,
|
| 412 |
+
"loss": 0.4922,
|
| 413 |
+
"step": 570
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 7.01,
|
| 417 |
+
"learning_rate": 4.6962962962962966e-05,
|
| 418 |
+
"loss": 0.0182,
|
| 419 |
+
"step": 580
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.02,
|
| 423 |
+
"learning_rate": 4.681481481481482e-05,
|
| 424 |
+
"loss": 0.0056,
|
| 425 |
+
"step": 590
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 7.02,
|
| 429 |
+
"learning_rate": 4.666666666666667e-05,
|
| 430 |
+
"loss": 0.2905,
|
| 431 |
+
"step": 600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 7.02,
|
| 435 |
+
"eval_accuracy": 0.9,
|
| 436 |
+
"eval_loss": 0.23063896596431732,
|
| 437 |
+
"eval_runtime": 5.9851,
|
| 438 |
+
"eval_samples_per_second": 11.696,
|
| 439 |
+
"eval_steps_per_second": 3.007,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.0,
|
| 444 |
+
"learning_rate": 4.6518518518518525e-05,
|
| 445 |
+
"loss": 0.0139,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.01,
|
| 450 |
+
"learning_rate": 4.637037037037038e-05,
|
| 451 |
+
"loss": 0.3338,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.01,
|
| 456 |
+
"learning_rate": 4.6222222222222224e-05,
|
| 457 |
+
"loss": 0.0218,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.01,
|
| 462 |
+
"learning_rate": 4.607407407407408e-05,
|
| 463 |
+
"loss": 0.0053,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.01,
|
| 468 |
+
"learning_rate": 4.592592592592593e-05,
|
| 469 |
+
"loss": 0.0042,
|
| 470 |
+
"step": 650
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.02,
|
| 474 |
+
"learning_rate": 4.577777777777778e-05,
|
| 475 |
+
"loss": 0.0115,
|
| 476 |
+
"step": 660
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.02,
|
| 480 |
+
"learning_rate": 4.5629629629629636e-05,
|
| 481 |
+
"loss": 0.0051,
|
| 482 |
+
"step": 670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 8.02,
|
| 486 |
+
"eval_accuracy": 0.9571428571428572,
|
| 487 |
+
"eval_loss": 0.2053740918636322,
|
| 488 |
+
"eval_runtime": 5.9611,
|
| 489 |
+
"eval_samples_per_second": 11.743,
|
| 490 |
+
"eval_steps_per_second": 3.02,
|
| 491 |
+
"step": 675
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.0,
|
| 495 |
+
"learning_rate": 4.548148148148149e-05,
|
| 496 |
+
"loss": 0.0034,
|
| 497 |
+
"step": 680
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 9.0,
|
| 501 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 502 |
+
"loss": 0.006,
|
| 503 |
+
"step": 690
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.01,
|
| 507 |
+
"learning_rate": 4.518518518518519e-05,
|
| 508 |
+
"loss": 0.0663,
|
| 509 |
+
"step": 700
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 9.01,
|
| 513 |
+
"learning_rate": 4.503703703703704e-05,
|
| 514 |
+
"loss": 0.0074,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.01,
|
| 519 |
+
"learning_rate": 4.4888888888888894e-05,
|
| 520 |
+
"loss": 0.1151,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.01,
|
| 525 |
+
"learning_rate": 4.474074074074075e-05,
|
| 526 |
+
"loss": 0.0627,
|
| 527 |
+
"step": 730
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 9.02,
|
| 531 |
+
"learning_rate": 4.4592592592592594e-05,
|
| 532 |
+
"loss": 0.016,
|
| 533 |
+
"step": 740
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.02,
|
| 537 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 538 |
+
"loss": 0.1142,
|
| 539 |
+
"step": 750
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.02,
|
| 543 |
+
"eval_accuracy": 0.8714285714285714,
|
| 544 |
+
"eval_loss": 0.704865038394928,
|
| 545 |
+
"eval_runtime": 5.6807,
|
| 546 |
+
"eval_samples_per_second": 12.323,
|
| 547 |
+
"eval_steps_per_second": 3.169,
|
| 548 |
+
"step": 750
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 10.0,
|
| 552 |
+
"learning_rate": 4.42962962962963e-05,
|
| 553 |
+
"loss": 0.0937,
|
| 554 |
+
"step": 760
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 10.01,
|
| 558 |
+
"learning_rate": 4.414814814814815e-05,
|
| 559 |
+
"loss": 0.1874,
|
| 560 |
+
"step": 770
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 10.01,
|
| 564 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 565 |
+
"loss": 0.0798,
|
| 566 |
+
"step": 780
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 10.01,
|
| 570 |
+
"learning_rate": 4.385185185185185e-05,
|
| 571 |
+
"loss": 0.0028,
|
| 572 |
+
"step": 790
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 10.01,
|
| 576 |
+
"learning_rate": 4.3703703703703705e-05,
|
| 577 |
+
"loss": 0.1547,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 10.02,
|
| 582 |
+
"learning_rate": 4.355555555555556e-05,
|
| 583 |
+
"loss": 0.1714,
|
| 584 |
+
"step": 810
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 10.02,
|
| 588 |
+
"learning_rate": 4.340740740740741e-05,
|
| 589 |
+
"loss": 0.0022,
|
| 590 |
+
"step": 820
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 10.02,
|
| 594 |
+
"eval_accuracy": 0.9428571428571428,
|
| 595 |
+
"eval_loss": 0.1919040083885193,
|
| 596 |
+
"eval_runtime": 5.707,
|
| 597 |
+
"eval_samples_per_second": 12.266,
|
| 598 |
+
"eval_steps_per_second": 3.154,
|
| 599 |
+
"step": 825
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 11.0,
|
| 603 |
+
"learning_rate": 4.325925925925926e-05,
|
| 604 |
+
"loss": 0.0026,
|
| 605 |
+
"step": 830
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 11.0,
|
| 609 |
+
"learning_rate": 4.311111111111111e-05,
|
| 610 |
+
"loss": 0.0029,
|
| 611 |
+
"step": 840
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 11.01,
|
| 615 |
+
"learning_rate": 4.296296296296296e-05,
|
| 616 |
+
"loss": 0.0794,
|
| 617 |
+
"step": 850
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 11.01,
|
| 621 |
+
"learning_rate": 4.2814814814814816e-05,
|
| 622 |
+
"loss": 0.0708,
|
| 623 |
+
"step": 860
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 11.01,
|
| 627 |
+
"learning_rate": 4.266666666666667e-05,
|
| 628 |
+
"loss": 0.0705,
|
| 629 |
+
"step": 870
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 11.01,
|
| 633 |
+
"learning_rate": 4.2518518518518515e-05,
|
| 634 |
+
"loss": 0.0549,
|
| 635 |
+
"step": 880
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 11.02,
|
| 639 |
+
"learning_rate": 4.237037037037037e-05,
|
| 640 |
+
"loss": 0.0022,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 11.02,
|
| 645 |
+
"learning_rate": 4.222222222222222e-05,
|
| 646 |
+
"loss": 0.0019,
|
| 647 |
+
"step": 900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 11.02,
|
| 651 |
+
"eval_accuracy": 0.8857142857142857,
|
| 652 |
+
"eval_loss": 0.5478063225746155,
|
| 653 |
+
"eval_runtime": 5.7039,
|
| 654 |
+
"eval_samples_per_second": 12.272,
|
| 655 |
+
"eval_steps_per_second": 3.156,
|
| 656 |
+
"step": 900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 12.0,
|
| 660 |
+
"learning_rate": 4.2074074074074075e-05,
|
| 661 |
+
"loss": 0.0032,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 12.01,
|
| 666 |
+
"learning_rate": 4.192592592592593e-05,
|
| 667 |
+
"loss": 0.0159,
|
| 668 |
+
"step": 920
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 12.01,
|
| 672 |
+
"learning_rate": 4.177777777777778e-05,
|
| 673 |
+
"loss": 0.0861,
|
| 674 |
+
"step": 930
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 12.01,
|
| 678 |
+
"learning_rate": 4.162962962962963e-05,
|
| 679 |
+
"loss": 0.2058,
|
| 680 |
+
"step": 940
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 12.01,
|
| 684 |
+
"learning_rate": 4.148148148148148e-05,
|
| 685 |
+
"loss": 0.0042,
|
| 686 |
+
"step": 950
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 12.02,
|
| 690 |
+
"learning_rate": 4.133333333333333e-05,
|
| 691 |
+
"loss": 0.1814,
|
| 692 |
+
"step": 960
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 12.02,
|
| 696 |
+
"learning_rate": 4.1185185185185186e-05,
|
| 697 |
+
"loss": 0.0021,
|
| 698 |
+
"step": 970
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 12.02,
|
| 702 |
+
"eval_accuracy": 0.9285714285714286,
|
| 703 |
+
"eval_loss": 0.4232262670993805,
|
| 704 |
+
"eval_runtime": 5.5509,
|
| 705 |
+
"eval_samples_per_second": 12.611,
|
| 706 |
+
"eval_steps_per_second": 3.243,
|
| 707 |
+
"step": 975
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 13.0,
|
| 711 |
+
"learning_rate": 4.103703703703704e-05,
|
| 712 |
+
"loss": 0.0036,
|
| 713 |
+
"step": 980
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 13.0,
|
| 717 |
+
"learning_rate": 4.088888888888889e-05,
|
| 718 |
+
"loss": 0.0761,
|
| 719 |
+
"step": 990
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 13.01,
|
| 723 |
+
"learning_rate": 4.074074074074074e-05,
|
| 724 |
+
"loss": 0.0036,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 13.01,
|
| 729 |
+
"learning_rate": 4.059259259259259e-05,
|
| 730 |
+
"loss": 0.1052,
|
| 731 |
+
"step": 1010
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 13.01,
|
| 735 |
+
"learning_rate": 4.0444444444444444e-05,
|
| 736 |
+
"loss": 0.0165,
|
| 737 |
+
"step": 1020
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 13.01,
|
| 741 |
+
"learning_rate": 4.02962962962963e-05,
|
| 742 |
+
"loss": 0.0347,
|
| 743 |
+
"step": 1030
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 13.02,
|
| 747 |
+
"learning_rate": 4.014814814814815e-05,
|
| 748 |
+
"loss": 0.007,
|
| 749 |
+
"step": 1040
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 13.02,
|
| 753 |
+
"learning_rate": 4e-05,
|
| 754 |
+
"loss": 0.0019,
|
| 755 |
+
"step": 1050
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 13.02,
|
| 759 |
+
"eval_accuracy": 0.8857142857142857,
|
| 760 |
+
"eval_loss": 0.5436500310897827,
|
| 761 |
+
"eval_runtime": 5.8387,
|
| 762 |
+
"eval_samples_per_second": 11.989,
|
| 763 |
+
"eval_steps_per_second": 3.083,
|
| 764 |
+
"step": 1050
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 14.0,
|
| 768 |
+
"learning_rate": 3.985185185185185e-05,
|
| 769 |
+
"loss": 0.0304,
|
| 770 |
+
"step": 1060
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 14.01,
|
| 774 |
+
"learning_rate": 3.97037037037037e-05,
|
| 775 |
+
"loss": 0.0019,
|
| 776 |
+
"step": 1070
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 14.01,
|
| 780 |
+
"learning_rate": 3.9555555555555556e-05,
|
| 781 |
+
"loss": 0.1148,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 14.01,
|
| 786 |
+
"learning_rate": 3.940740740740741e-05,
|
| 787 |
+
"loss": 0.0148,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 14.01,
|
| 792 |
+
"learning_rate": 3.925925925925926e-05,
|
| 793 |
+
"loss": 0.0016,
|
| 794 |
+
"step": 1100
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 14.02,
|
| 798 |
+
"learning_rate": 3.9111111111111115e-05,
|
| 799 |
+
"loss": 0.0113,
|
| 800 |
+
"step": 1110
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 14.02,
|
| 804 |
+
"learning_rate": 3.896296296296296e-05,
|
| 805 |
+
"loss": 0.002,
|
| 806 |
+
"step": 1120
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 14.02,
|
| 810 |
+
"eval_accuracy": 0.7857142857142857,
|
| 811 |
+
"eval_loss": 1.0354480743408203,
|
| 812 |
+
"eval_runtime": 5.6448,
|
| 813 |
+
"eval_samples_per_second": 12.401,
|
| 814 |
+
"eval_steps_per_second": 3.189,
|
| 815 |
+
"step": 1125
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 15.0,
|
| 819 |
+
"learning_rate": 3.8814814814814814e-05,
|
| 820 |
+
"loss": 0.0017,
|
| 821 |
+
"step": 1130
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 15.0,
|
| 825 |
+
"learning_rate": 3.866666666666667e-05,
|
| 826 |
+
"loss": 0.1468,
|
| 827 |
+
"step": 1140
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 15.01,
|
| 831 |
+
"learning_rate": 3.851851851851852e-05,
|
| 832 |
+
"loss": 0.0023,
|
| 833 |
+
"step": 1150
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 15.01,
|
| 837 |
+
"learning_rate": 3.837037037037037e-05,
|
| 838 |
+
"loss": 0.0082,
|
| 839 |
+
"step": 1160
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 15.01,
|
| 843 |
+
"learning_rate": 3.8222222222222226e-05,
|
| 844 |
+
"loss": 0.003,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 15.01,
|
| 849 |
+
"learning_rate": 3.807407407407408e-05,
|
| 850 |
+
"loss": 0.0822,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 15.02,
|
| 855 |
+
"learning_rate": 3.7925925925925925e-05,
|
| 856 |
+
"loss": 0.0015,
|
| 857 |
+
"step": 1190
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 15.02,
|
| 861 |
+
"learning_rate": 3.777777777777778e-05,
|
| 862 |
+
"loss": 0.0028,
|
| 863 |
+
"step": 1200
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 15.02,
|
| 867 |
+
"eval_accuracy": 0.9714285714285714,
|
| 868 |
+
"eval_loss": 0.10393200069665909,
|
| 869 |
+
"eval_runtime": 5.6145,
|
| 870 |
+
"eval_samples_per_second": 12.468,
|
| 871 |
+
"eval_steps_per_second": 3.206,
|
| 872 |
+
"step": 1200
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 16.0,
|
| 876 |
+
"learning_rate": 3.762962962962963e-05,
|
| 877 |
+
"loss": 0.0019,
|
| 878 |
+
"step": 1210
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 16.01,
|
| 882 |
+
"learning_rate": 3.7481481481481484e-05,
|
| 883 |
+
"loss": 0.0029,
|
| 884 |
+
"step": 1220
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 16.01,
|
| 888 |
+
"learning_rate": 3.733333333333334e-05,
|
| 889 |
+
"loss": 0.0042,
|
| 890 |
+
"step": 1230
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 16.01,
|
| 894 |
+
"learning_rate": 3.718518518518519e-05,
|
| 895 |
+
"loss": 0.0012,
|
| 896 |
+
"step": 1240
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 16.01,
|
| 900 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 901 |
+
"loss": 0.0014,
|
| 902 |
+
"step": 1250
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 16.02,
|
| 906 |
+
"learning_rate": 3.688888888888889e-05,
|
| 907 |
+
"loss": 0.1956,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 16.02,
|
| 912 |
+
"learning_rate": 3.674074074074074e-05,
|
| 913 |
+
"loss": 0.0013,
|
| 914 |
+
"step": 1270
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 16.02,
|
| 918 |
+
"eval_accuracy": 0.9714285714285714,
|
| 919 |
+
"eval_loss": 0.1551610380411148,
|
| 920 |
+
"eval_runtime": 5.9927,
|
| 921 |
+
"eval_samples_per_second": 11.681,
|
| 922 |
+
"eval_steps_per_second": 3.004,
|
| 923 |
+
"step": 1275
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 17.0,
|
| 927 |
+
"learning_rate": 3.6592592592592596e-05,
|
| 928 |
+
"loss": 0.2917,
|
| 929 |
+
"step": 1280
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 17.0,
|
| 933 |
+
"learning_rate": 3.644444444444445e-05,
|
| 934 |
+
"loss": 0.0015,
|
| 935 |
+
"step": 1290
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 17.01,
|
| 939 |
+
"learning_rate": 3.62962962962963e-05,
|
| 940 |
+
"loss": 0.3129,
|
| 941 |
+
"step": 1300
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 17.01,
|
| 945 |
+
"learning_rate": 3.614814814814815e-05,
|
| 946 |
+
"loss": 0.0016,
|
| 947 |
+
"step": 1310
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 17.01,
|
| 951 |
+
"learning_rate": 3.6e-05,
|
| 952 |
+
"loss": 0.1919,
|
| 953 |
+
"step": 1320
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 17.01,
|
| 957 |
+
"learning_rate": 3.5851851851851854e-05,
|
| 958 |
+
"loss": 0.0335,
|
| 959 |
+
"step": 1330
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 17.02,
|
| 963 |
+
"learning_rate": 3.570370370370371e-05,
|
| 964 |
+
"loss": 0.0014,
|
| 965 |
+
"step": 1340
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 17.02,
|
| 969 |
+
"learning_rate": 3.555555555555556e-05,
|
| 970 |
+
"loss": 0.2309,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 17.02,
|
| 975 |
+
"eval_accuracy": 0.9285714285714286,
|
| 976 |
+
"eval_loss": 0.2719881236553192,
|
| 977 |
+
"eval_runtime": 5.759,
|
| 978 |
+
"eval_samples_per_second": 12.155,
|
| 979 |
+
"eval_steps_per_second": 3.126,
|
| 980 |
+
"step": 1350
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 18.0,
|
| 984 |
+
"learning_rate": 3.540740740740741e-05,
|
| 985 |
+
"loss": 0.0013,
|
| 986 |
+
"step": 1360
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 18.01,
|
| 990 |
+
"learning_rate": 3.525925925925926e-05,
|
| 991 |
+
"loss": 0.0018,
|
| 992 |
+
"step": 1370
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 18.01,
|
| 996 |
+
"learning_rate": 3.511111111111111e-05,
|
| 997 |
+
"loss": 0.2065,
|
| 998 |
+
"step": 1380
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 18.01,
|
| 1002 |
+
"learning_rate": 3.4962962962962965e-05,
|
| 1003 |
+
"loss": 0.0106,
|
| 1004 |
+
"step": 1390
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 18.01,
|
| 1008 |
+
"learning_rate": 3.481481481481482e-05,
|
| 1009 |
+
"loss": 0.0019,
|
| 1010 |
+
"step": 1400
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 18.02,
|
| 1014 |
+
"learning_rate": 3.466666666666667e-05,
|
| 1015 |
+
"loss": 0.0179,
|
| 1016 |
+
"step": 1410
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 18.02,
|
| 1020 |
+
"learning_rate": 3.4518518518518524e-05,
|
| 1021 |
+
"loss": 0.1662,
|
| 1022 |
+
"step": 1420
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 18.02,
|
| 1026 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1027 |
+
"eval_loss": 0.031152786687016487,
|
| 1028 |
+
"eval_runtime": 5.8068,
|
| 1029 |
+
"eval_samples_per_second": 12.055,
|
| 1030 |
+
"eval_steps_per_second": 3.1,
|
| 1031 |
+
"step": 1425
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 19.0,
|
| 1035 |
+
"learning_rate": 3.437037037037037e-05,
|
| 1036 |
+
"loss": 0.0945,
|
| 1037 |
+
"step": 1430
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 19.0,
|
| 1041 |
+
"learning_rate": 3.4222222222222224e-05,
|
| 1042 |
+
"loss": 0.1443,
|
| 1043 |
+
"step": 1440
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 19.01,
|
| 1047 |
+
"learning_rate": 3.4074074074074077e-05,
|
| 1048 |
+
"loss": 0.0583,
|
| 1049 |
+
"step": 1450
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 19.01,
|
| 1053 |
+
"learning_rate": 3.392592592592593e-05,
|
| 1054 |
+
"loss": 0.0015,
|
| 1055 |
+
"step": 1460
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 19.01,
|
| 1059 |
+
"learning_rate": 3.377777777777778e-05,
|
| 1060 |
+
"loss": 0.1515,
|
| 1061 |
+
"step": 1470
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 19.01,
|
| 1065 |
+
"learning_rate": 3.3629629629629636e-05,
|
| 1066 |
+
"loss": 0.008,
|
| 1067 |
+
"step": 1480
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 19.02,
|
| 1071 |
+
"learning_rate": 3.348148148148148e-05,
|
| 1072 |
+
"loss": 0.2176,
|
| 1073 |
+
"step": 1490
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 19.02,
|
| 1077 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1078 |
+
"loss": 0.0199,
|
| 1079 |
+
"step": 1500
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 19.02,
|
| 1083 |
+
"eval_accuracy": 0.9571428571428572,
|
| 1084 |
+
"eval_loss": 0.14778082072734833,
|
| 1085 |
+
"eval_runtime": 5.8359,
|
| 1086 |
+
"eval_samples_per_second": 11.995,
|
| 1087 |
+
"eval_steps_per_second": 3.084,
|
| 1088 |
+
"step": 1500
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 20.0,
|
| 1092 |
+
"learning_rate": 3.318518518518519e-05,
|
| 1093 |
+
"loss": 0.0017,
|
| 1094 |
+
"step": 1510
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 20.01,
|
| 1098 |
+
"learning_rate": 3.303703703703704e-05,
|
| 1099 |
+
"loss": 0.001,
|
| 1100 |
+
"step": 1520
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 20.01,
|
| 1104 |
+
"learning_rate": 3.2888888888888894e-05,
|
| 1105 |
+
"loss": 0.0442,
|
| 1106 |
+
"step": 1530
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 20.01,
|
| 1110 |
+
"learning_rate": 3.274074074074075e-05,
|
| 1111 |
+
"loss": 0.0019,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 20.01,
|
| 1116 |
+
"learning_rate": 3.25925925925926e-05,
|
| 1117 |
+
"loss": 0.0015,
|
| 1118 |
+
"step": 1550
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 20.02,
|
| 1122 |
+
"learning_rate": 3.2444444444444446e-05,
|
| 1123 |
+
"loss": 0.0012,
|
| 1124 |
+
"step": 1560
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 20.02,
|
| 1128 |
+
"learning_rate": 3.22962962962963e-05,
|
| 1129 |
+
"loss": 0.001,
|
| 1130 |
+
"step": 1570
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 20.02,
|
| 1134 |
+
"eval_accuracy": 0.9714285714285714,
|
| 1135 |
+
"eval_loss": 0.21894989907741547,
|
| 1136 |
+
"eval_runtime": 5.952,
|
| 1137 |
+
"eval_samples_per_second": 11.761,
|
| 1138 |
+
"eval_steps_per_second": 3.024,
|
| 1139 |
+
"step": 1575
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 21.0,
|
| 1143 |
+
"learning_rate": 3.214814814814815e-05,
|
| 1144 |
+
"loss": 0.0058,
|
| 1145 |
+
"step": 1580
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 21.0,
|
| 1149 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 1150 |
+
"loss": 0.001,
|
| 1151 |
+
"step": 1590
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 21.01,
|
| 1155 |
+
"learning_rate": 3.185185185185185e-05,
|
| 1156 |
+
"loss": 0.0271,
|
| 1157 |
+
"step": 1600
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 21.01,
|
| 1161 |
+
"learning_rate": 3.1703703703703705e-05,
|
| 1162 |
+
"loss": 0.0009,
|
| 1163 |
+
"step": 1610
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 21.01,
|
| 1167 |
+
"learning_rate": 3.155555555555556e-05,
|
| 1168 |
+
"loss": 0.001,
|
| 1169 |
+
"step": 1620
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 21.01,
|
| 1173 |
+
"learning_rate": 3.140740740740741e-05,
|
| 1174 |
+
"loss": 0.1786,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 21.02,
|
| 1179 |
+
"learning_rate": 3.1259259259259264e-05,
|
| 1180 |
+
"loss": 0.0056,
|
| 1181 |
+
"step": 1640
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 21.02,
|
| 1185 |
+
"learning_rate": 3.111111111111111e-05,
|
| 1186 |
+
"loss": 0.0009,
|
| 1187 |
+
"step": 1650
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 21.02,
|
| 1191 |
+
"eval_accuracy": 0.9714285714285714,
|
| 1192 |
+
"eval_loss": 0.15684819221496582,
|
| 1193 |
+
"eval_runtime": 5.7784,
|
| 1194 |
+
"eval_samples_per_second": 12.114,
|
| 1195 |
+
"eval_steps_per_second": 3.115,
|
| 1196 |
+
"step": 1650
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 22.0,
|
| 1200 |
+
"learning_rate": 3.096296296296296e-05,
|
| 1201 |
+
"loss": 0.1822,
|
| 1202 |
+
"step": 1660
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 22.01,
|
| 1206 |
+
"learning_rate": 3.0814814814814816e-05,
|
| 1207 |
+
"loss": 0.0009,
|
| 1208 |
+
"step": 1670
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 22.01,
|
| 1212 |
+
"learning_rate": 3.066666666666667e-05,
|
| 1213 |
+
"loss": 0.0009,
|
| 1214 |
+
"step": 1680
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 22.01,
|
| 1218 |
+
"learning_rate": 3.0518518518518515e-05,
|
| 1219 |
+
"loss": 0.0008,
|
| 1220 |
+
"step": 1690
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 22.01,
|
| 1224 |
+
"learning_rate": 3.037037037037037e-05,
|
| 1225 |
+
"loss": 0.0009,
|
| 1226 |
+
"step": 1700
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 22.02,
|
| 1230 |
+
"learning_rate": 3.0222222222222225e-05,
|
| 1231 |
+
"loss": 0.001,
|
| 1232 |
+
"step": 1710
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 22.02,
|
| 1236 |
+
"learning_rate": 3.0074074074074078e-05,
|
| 1237 |
+
"loss": 0.0008,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 22.02,
|
| 1242 |
+
"eval_accuracy": 0.9428571428571428,
|
| 1243 |
+
"eval_loss": 0.213576078414917,
|
| 1244 |
+
"eval_runtime": 5.6561,
|
| 1245 |
+
"eval_samples_per_second": 12.376,
|
| 1246 |
+
"eval_steps_per_second": 3.182,
|
| 1247 |
+
"step": 1725
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 23.0,
|
| 1251 |
+
"learning_rate": 2.992592592592593e-05,
|
| 1252 |
+
"loss": 0.0008,
|
| 1253 |
+
"step": 1730
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 23.0,
|
| 1257 |
+
"learning_rate": 2.9777777777777777e-05,
|
| 1258 |
+
"loss": 0.0008,
|
| 1259 |
+
"step": 1740
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 23.01,
|
| 1263 |
+
"learning_rate": 2.962962962962963e-05,
|
| 1264 |
+
"loss": 0.0008,
|
| 1265 |
+
"step": 1750
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 23.01,
|
| 1269 |
+
"learning_rate": 2.9481481481481483e-05,
|
| 1270 |
+
"loss": 0.0238,
|
| 1271 |
+
"step": 1760
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 23.01,
|
| 1275 |
+
"learning_rate": 2.9333333333333336e-05,
|
| 1276 |
+
"loss": 0.0008,
|
| 1277 |
+
"step": 1770
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 23.01,
|
| 1281 |
+
"learning_rate": 2.918518518518519e-05,
|
| 1282 |
+
"loss": 0.0007,
|
| 1283 |
+
"step": 1780
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 23.02,
|
| 1287 |
+
"learning_rate": 2.9037037037037042e-05,
|
| 1288 |
+
"loss": 0.0009,
|
| 1289 |
+
"step": 1790
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 23.02,
|
| 1293 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 1294 |
+
"loss": 0.0007,
|
| 1295 |
+
"step": 1800
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 23.02,
|
| 1299 |
+
"eval_accuracy": 0.9714285714285714,
|
| 1300 |
+
"eval_loss": 0.10322745889425278,
|
| 1301 |
+
"eval_runtime": 5.6572,
|
| 1302 |
+
"eval_samples_per_second": 12.374,
|
| 1303 |
+
"eval_steps_per_second": 3.182,
|
| 1304 |
+
"step": 1800
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 24.0,
|
| 1308 |
+
"learning_rate": 2.874074074074074e-05,
|
| 1309 |
+
"loss": 0.0008,
|
| 1310 |
+
"step": 1810
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 24.01,
|
| 1314 |
+
"learning_rate": 2.8592592592592594e-05,
|
| 1315 |
+
"loss": 0.0007,
|
| 1316 |
+
"step": 1820
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 24.01,
|
| 1320 |
+
"learning_rate": 2.8444444444444447e-05,
|
| 1321 |
+
"loss": 0.0008,
|
| 1322 |
+
"step": 1830
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 24.01,
|
| 1326 |
+
"learning_rate": 2.8296296296296297e-05,
|
| 1327 |
+
"loss": 0.0007,
|
| 1328 |
+
"step": 1840
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 24.01,
|
| 1332 |
+
"learning_rate": 2.814814814814815e-05,
|
| 1333 |
+
"loss": 0.0007,
|
| 1334 |
+
"step": 1850
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 24.02,
|
| 1338 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 1339 |
+
"loss": 0.0006,
|
| 1340 |
+
"step": 1860
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 24.02,
|
| 1344 |
+
"learning_rate": 2.7851851851851853e-05,
|
| 1345 |
+
"loss": 0.0007,
|
| 1346 |
+
"step": 1870
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 24.02,
|
| 1350 |
+
"eval_accuracy": 0.9714285714285714,
|
| 1351 |
+
"eval_loss": 0.10255812108516693,
|
| 1352 |
+
"eval_runtime": 5.7489,
|
| 1353 |
+
"eval_samples_per_second": 12.176,
|
| 1354 |
+
"eval_steps_per_second": 3.131,
|
| 1355 |
+
"step": 1875
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 25.0,
|
| 1359 |
+
"learning_rate": 2.7703703703703706e-05,
|
| 1360 |
+
"loss": 0.0007,
|
| 1361 |
+
"step": 1880
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 25.0,
|
| 1365 |
+
"learning_rate": 2.7555555555555555e-05,
|
| 1366 |
+
"loss": 0.0007,
|
| 1367 |
+
"step": 1890
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 25.01,
|
| 1371 |
+
"learning_rate": 2.7407407407407408e-05,
|
| 1372 |
+
"loss": 0.0008,
|
| 1373 |
+
"step": 1900
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 25.01,
|
| 1377 |
+
"learning_rate": 2.725925925925926e-05,
|
| 1378 |
+
"loss": 0.0007,
|
| 1379 |
+
"step": 1910
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 25.01,
|
| 1383 |
+
"learning_rate": 2.7111111111111114e-05,
|
| 1384 |
+
"loss": 0.0006,
|
| 1385 |
+
"step": 1920
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 25.01,
|
| 1389 |
+
"learning_rate": 2.696296296296296e-05,
|
| 1390 |
+
"loss": 0.0006,
|
| 1391 |
+
"step": 1930
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 25.02,
|
| 1395 |
+
"learning_rate": 2.6814814814814814e-05,
|
| 1396 |
+
"loss": 0.0006,
|
| 1397 |
+
"step": 1940
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 25.02,
|
| 1401 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1402 |
+
"loss": 0.0006,
|
| 1403 |
+
"step": 1950
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 25.02,
|
| 1407 |
+
"eval_accuracy": 0.9571428571428572,
|
| 1408 |
+
"eval_loss": 0.11298384517431259,
|
| 1409 |
+
"eval_runtime": 5.7507,
|
| 1410 |
+
"eval_samples_per_second": 12.173,
|
| 1411 |
+
"eval_steps_per_second": 3.13,
|
| 1412 |
+
"step": 1950
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 26.0,
|
| 1416 |
+
"learning_rate": 2.651851851851852e-05,
|
| 1417 |
+
"loss": 0.0006,
|
| 1418 |
+
"step": 1960
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 26.01,
|
| 1422 |
+
"learning_rate": 2.6370370370370373e-05,
|
| 1423 |
+
"loss": 0.0006,
|
| 1424 |
+
"step": 1970
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 26.01,
|
| 1428 |
+
"learning_rate": 2.6222222222222226e-05,
|
| 1429 |
+
"loss": 0.0006,
|
| 1430 |
+
"step": 1980
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 26.01,
|
| 1434 |
+
"learning_rate": 2.6074074074074072e-05,
|
| 1435 |
+
"loss": 0.0007,
|
| 1436 |
+
"step": 1990
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 26.01,
|
| 1440 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 1441 |
+
"loss": 0.0006,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 26.02,
|
| 1446 |
+
"learning_rate": 2.5777777777777778e-05,
|
| 1447 |
+
"loss": 0.0006,
|
| 1448 |
+
"step": 2010
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 26.02,
|
| 1452 |
+
"learning_rate": 2.562962962962963e-05,
|
| 1453 |
+
"loss": 0.0006,
|
| 1454 |
+
"step": 2020
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 26.02,
|
| 1458 |
+
"eval_accuracy": 0.9714285714285714,
|
| 1459 |
+
"eval_loss": 0.11467116326093674,
|
| 1460 |
+
"eval_runtime": 5.8139,
|
| 1461 |
+
"eval_samples_per_second": 12.04,
|
| 1462 |
+
"eval_steps_per_second": 3.096,
|
| 1463 |
+
"step": 2025
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 27.0,
|
| 1467 |
+
"learning_rate": 2.5481481481481484e-05,
|
| 1468 |
+
"loss": 0.0007,
|
| 1469 |
+
"step": 2030
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 27.0,
|
| 1473 |
+
"learning_rate": 2.5333333333333337e-05,
|
| 1474 |
+
"loss": 0.0007,
|
| 1475 |
+
"step": 2040
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 27.01,
|
| 1479 |
+
"learning_rate": 2.5185185185185183e-05,
|
| 1480 |
+
"loss": 0.0006,
|
| 1481 |
+
"step": 2050
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 27.01,
|
| 1485 |
+
"learning_rate": 2.5037037037037036e-05,
|
| 1486 |
+
"loss": 0.0006,
|
| 1487 |
+
"step": 2060
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 27.01,
|
| 1491 |
+
"learning_rate": 2.488888888888889e-05,
|
| 1492 |
+
"loss": 0.0006,
|
| 1493 |
+
"step": 2070
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 27.01,
|
| 1497 |
+
"learning_rate": 2.4740740740740742e-05,
|
| 1498 |
+
"loss": 0.0006,
|
| 1499 |
+
"step": 2080
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 27.02,
|
| 1503 |
+
"learning_rate": 2.4592592592592595e-05,
|
| 1504 |
+
"loss": 0.0006,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 27.02,
|
| 1509 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 1510 |
+
"loss": 0.0006,
|
| 1511 |
+
"step": 2100
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 27.02,
|
| 1515 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1516 |
+
"eval_loss": 0.0858125165104866,
|
| 1517 |
+
"eval_runtime": 5.7371,
|
| 1518 |
+
"eval_samples_per_second": 12.201,
|
| 1519 |
+
"eval_steps_per_second": 3.137,
|
| 1520 |
+
"step": 2100
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 28.0,
|
| 1524 |
+
"learning_rate": 2.4296296296296298e-05,
|
| 1525 |
+
"loss": 0.0006,
|
| 1526 |
+
"step": 2110
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 28.01,
|
| 1530 |
+
"learning_rate": 2.414814814814815e-05,
|
| 1531 |
+
"loss": 0.0006,
|
| 1532 |
+
"step": 2120
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 28.01,
|
| 1536 |
+
"learning_rate": 2.4e-05,
|
| 1537 |
+
"loss": 0.0006,
|
| 1538 |
+
"step": 2130
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 28.01,
|
| 1542 |
+
"learning_rate": 2.3851851851851854e-05,
|
| 1543 |
+
"loss": 0.0005,
|
| 1544 |
+
"step": 2140
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 28.01,
|
| 1548 |
+
"learning_rate": 2.3703703703703707e-05,
|
| 1549 |
+
"loss": 0.0006,
|
| 1550 |
+
"step": 2150
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 28.02,
|
| 1554 |
+
"learning_rate": 2.3555555555555556e-05,
|
| 1555 |
+
"loss": 0.0006,
|
| 1556 |
+
"step": 2160
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 28.02,
|
| 1560 |
+
"learning_rate": 2.340740740740741e-05,
|
| 1561 |
+
"loss": 0.0006,
|
| 1562 |
+
"step": 2170
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 28.02,
|
| 1566 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1567 |
+
"eval_loss": 0.08683785051107407,
|
| 1568 |
+
"eval_runtime": 5.8537,
|
| 1569 |
+
"eval_samples_per_second": 11.958,
|
| 1570 |
+
"eval_steps_per_second": 3.075,
|
| 1571 |
+
"step": 2175
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 29.0,
|
| 1575 |
+
"learning_rate": 2.3259259259259262e-05,
|
| 1576 |
+
"loss": 0.0006,
|
| 1577 |
+
"step": 2180
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 29.0,
|
| 1581 |
+
"learning_rate": 2.3111111111111112e-05,
|
| 1582 |
+
"loss": 0.0005,
|
| 1583 |
+
"step": 2190
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 29.01,
|
| 1587 |
+
"learning_rate": 2.2962962962962965e-05,
|
| 1588 |
+
"loss": 0.0006,
|
| 1589 |
+
"step": 2200
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 29.01,
|
| 1593 |
+
"learning_rate": 2.2814814814814818e-05,
|
| 1594 |
+
"loss": 0.0006,
|
| 1595 |
+
"step": 2210
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 29.01,
|
| 1599 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 1600 |
+
"loss": 0.0005,
|
| 1601 |
+
"step": 2220
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 29.01,
|
| 1605 |
+
"learning_rate": 2.251851851851852e-05,
|
| 1606 |
+
"loss": 0.0005,
|
| 1607 |
+
"step": 2230
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 29.02,
|
| 1611 |
+
"learning_rate": 2.2370370370370374e-05,
|
| 1612 |
+
"loss": 0.0005,
|
| 1613 |
+
"step": 2240
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 29.02,
|
| 1617 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1618 |
+
"loss": 0.0006,
|
| 1619 |
+
"step": 2250
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 29.02,
|
| 1623 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1624 |
+
"eval_loss": 0.08798635751008987,
|
| 1625 |
+
"eval_runtime": 5.7007,
|
| 1626 |
+
"eval_samples_per_second": 12.279,
|
| 1627 |
+
"eval_steps_per_second": 3.158,
|
| 1628 |
+
"step": 2250
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 30.0,
|
| 1632 |
+
"learning_rate": 2.2074074074074076e-05,
|
| 1633 |
+
"loss": 0.0005,
|
| 1634 |
+
"step": 2260
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 30.01,
|
| 1638 |
+
"learning_rate": 2.1925925925925926e-05,
|
| 1639 |
+
"loss": 0.0006,
|
| 1640 |
+
"step": 2270
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 30.01,
|
| 1644 |
+
"learning_rate": 2.177777777777778e-05,
|
| 1645 |
+
"loss": 0.0005,
|
| 1646 |
+
"step": 2280
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 30.01,
|
| 1650 |
+
"learning_rate": 2.162962962962963e-05,
|
| 1651 |
+
"loss": 0.0005,
|
| 1652 |
+
"step": 2290
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 30.01,
|
| 1656 |
+
"learning_rate": 2.148148148148148e-05,
|
| 1657 |
+
"loss": 0.0006,
|
| 1658 |
+
"step": 2300
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 30.02,
|
| 1662 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 1663 |
+
"loss": 0.0005,
|
| 1664 |
+
"step": 2310
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 30.02,
|
| 1668 |
+
"learning_rate": 2.1185185185185184e-05,
|
| 1669 |
+
"loss": 0.0005,
|
| 1670 |
+
"step": 2320
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 30.02,
|
| 1674 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1675 |
+
"eval_loss": 0.08717390149831772,
|
| 1676 |
+
"eval_runtime": 5.8675,
|
| 1677 |
+
"eval_samples_per_second": 11.93,
|
| 1678 |
+
"eval_steps_per_second": 3.068,
|
| 1679 |
+
"step": 2325
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 31.0,
|
| 1683 |
+
"learning_rate": 2.1037037037037037e-05,
|
| 1684 |
+
"loss": 0.0005,
|
| 1685 |
+
"step": 2330
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 31.0,
|
| 1689 |
+
"learning_rate": 2.088888888888889e-05,
|
| 1690 |
+
"loss": 0.0005,
|
| 1691 |
+
"step": 2340
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 31.01,
|
| 1695 |
+
"learning_rate": 2.074074074074074e-05,
|
| 1696 |
+
"loss": 0.0005,
|
| 1697 |
+
"step": 2350
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 31.01,
|
| 1701 |
+
"learning_rate": 2.0592592592592593e-05,
|
| 1702 |
+
"loss": 0.0005,
|
| 1703 |
+
"step": 2360
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 31.01,
|
| 1707 |
+
"learning_rate": 2.0444444444444446e-05,
|
| 1708 |
+
"loss": 0.0006,
|
| 1709 |
+
"step": 2370
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 31.01,
|
| 1713 |
+
"learning_rate": 2.0296296296296296e-05,
|
| 1714 |
+
"loss": 0.0005,
|
| 1715 |
+
"step": 2380
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 31.02,
|
| 1719 |
+
"learning_rate": 2.014814814814815e-05,
|
| 1720 |
+
"loss": 0.0005,
|
| 1721 |
+
"step": 2390
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 31.02,
|
| 1725 |
+
"learning_rate": 2e-05,
|
| 1726 |
+
"loss": 0.0005,
|
| 1727 |
+
"step": 2400
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 31.02,
|
| 1731 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1732 |
+
"eval_loss": 0.09013553708791733,
|
| 1733 |
+
"eval_runtime": 5.7699,
|
| 1734 |
+
"eval_samples_per_second": 12.132,
|
| 1735 |
+
"eval_steps_per_second": 3.12,
|
| 1736 |
+
"step": 2400
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 32.0,
|
| 1740 |
+
"learning_rate": 1.985185185185185e-05,
|
| 1741 |
+
"loss": 0.0005,
|
| 1742 |
+
"step": 2410
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 32.01,
|
| 1746 |
+
"learning_rate": 1.9703703703703704e-05,
|
| 1747 |
+
"loss": 0.0005,
|
| 1748 |
+
"step": 2420
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 32.01,
|
| 1752 |
+
"learning_rate": 1.9555555555555557e-05,
|
| 1753 |
+
"loss": 0.0005,
|
| 1754 |
+
"step": 2430
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 32.01,
|
| 1758 |
+
"learning_rate": 1.9407407407407407e-05,
|
| 1759 |
+
"loss": 0.0005,
|
| 1760 |
+
"step": 2440
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 32.01,
|
| 1764 |
+
"learning_rate": 1.925925925925926e-05,
|
| 1765 |
+
"loss": 0.0005,
|
| 1766 |
+
"step": 2450
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 32.02,
|
| 1770 |
+
"learning_rate": 1.9111111111111113e-05,
|
| 1771 |
+
"loss": 0.0005,
|
| 1772 |
+
"step": 2460
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 32.02,
|
| 1776 |
+
"learning_rate": 1.8962962962962963e-05,
|
| 1777 |
+
"loss": 0.0005,
|
| 1778 |
+
"step": 2470
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 32.02,
|
| 1782 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1783 |
+
"eval_loss": 0.08940133452415466,
|
| 1784 |
+
"eval_runtime": 5.7037,
|
| 1785 |
+
"eval_samples_per_second": 12.273,
|
| 1786 |
+
"eval_steps_per_second": 3.156,
|
| 1787 |
+
"step": 2475
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 33.0,
|
| 1791 |
+
"learning_rate": 1.8814814814814816e-05,
|
| 1792 |
+
"loss": 0.0005,
|
| 1793 |
+
"step": 2480
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 33.0,
|
| 1797 |
+
"learning_rate": 1.866666666666667e-05,
|
| 1798 |
+
"loss": 0.0005,
|
| 1799 |
+
"step": 2490
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 33.01,
|
| 1803 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1804 |
+
"loss": 0.0005,
|
| 1805 |
+
"step": 2500
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 33.01,
|
| 1809 |
+
"learning_rate": 1.837037037037037e-05,
|
| 1810 |
+
"loss": 0.0005,
|
| 1811 |
+
"step": 2510
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 33.01,
|
| 1815 |
+
"learning_rate": 1.8222222222222224e-05,
|
| 1816 |
+
"loss": 0.0004,
|
| 1817 |
+
"step": 2520
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 33.01,
|
| 1821 |
+
"learning_rate": 1.8074074074074074e-05,
|
| 1822 |
+
"loss": 0.0005,
|
| 1823 |
+
"step": 2530
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 33.02,
|
| 1827 |
+
"learning_rate": 1.7925925925925927e-05,
|
| 1828 |
+
"loss": 0.0005,
|
| 1829 |
+
"step": 2540
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 33.02,
|
| 1833 |
+
"learning_rate": 1.777777777777778e-05,
|
| 1834 |
+
"loss": 0.0005,
|
| 1835 |
+
"step": 2550
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 33.02,
|
| 1839 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1840 |
+
"eval_loss": 0.08584433048963547,
|
| 1841 |
+
"eval_runtime": 5.7242,
|
| 1842 |
+
"eval_samples_per_second": 12.229,
|
| 1843 |
+
"eval_steps_per_second": 3.145,
|
| 1844 |
+
"step": 2550
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 34.0,
|
| 1848 |
+
"learning_rate": 1.762962962962963e-05,
|
| 1849 |
+
"loss": 0.0004,
|
| 1850 |
+
"step": 2560
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 34.01,
|
| 1854 |
+
"learning_rate": 1.7481481481481483e-05,
|
| 1855 |
+
"loss": 0.0005,
|
| 1856 |
+
"step": 2570
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 34.01,
|
| 1860 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 1861 |
+
"loss": 0.0005,
|
| 1862 |
+
"step": 2580
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 34.01,
|
| 1866 |
+
"learning_rate": 1.7185185185185185e-05,
|
| 1867 |
+
"loss": 0.0004,
|
| 1868 |
+
"step": 2590
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 34.01,
|
| 1872 |
+
"learning_rate": 1.7037037037037038e-05,
|
| 1873 |
+
"loss": 0.0005,
|
| 1874 |
+
"step": 2600
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 34.02,
|
| 1878 |
+
"learning_rate": 1.688888888888889e-05,
|
| 1879 |
+
"loss": 0.0005,
|
| 1880 |
+
"step": 2610
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 34.02,
|
| 1884 |
+
"learning_rate": 1.674074074074074e-05,
|
| 1885 |
+
"loss": 0.0005,
|
| 1886 |
+
"step": 2620
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 34.02,
|
| 1890 |
+
"eval_accuracy": 0.9857142857142858,
|
| 1891 |
+
"eval_loss": 0.0912405401468277,
|
| 1892 |
+
"eval_runtime": 5.7854,
|
| 1893 |
+
"eval_samples_per_second": 12.099,
|
| 1894 |
+
"eval_steps_per_second": 3.111,
|
| 1895 |
+
"step": 2625
|
| 1896 |
+
},
|
| 1897 |
+
{
|
| 1898 |
+
"epoch": 35.0,
|
| 1899 |
+
"learning_rate": 1.6592592592592594e-05,
|
| 1900 |
+
"loss": 0.0005,
|
| 1901 |
+
"step": 2630
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 35.0,
|
| 1905 |
+
"learning_rate": 1.6444444444444447e-05,
|
| 1906 |
+
"loss": 0.0004,
|
| 1907 |
+
"step": 2640
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 35.01,
|
| 1911 |
+
"learning_rate": 1.62962962962963e-05,
|
| 1912 |
+
"loss": 0.0005,
|
| 1913 |
+
"step": 2650
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 35.01,
|
| 1917 |
+
"learning_rate": 1.614814814814815e-05,
|
| 1918 |
+
"loss": 0.0005,
|
| 1919 |
+
"step": 2660
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 35.01,
|
| 1923 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1924 |
+
"loss": 0.1029,
|
| 1925 |
+
"step": 2670
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 35.01,
|
| 1929 |
+
"learning_rate": 1.5851851851851852e-05,
|
| 1930 |
+
"loss": 0.0005,
|
| 1931 |
+
"step": 2680
|
| 1932 |
+
},
|
| 1933 |
+
{
|
| 1934 |
+
"epoch": 35.02,
|
| 1935 |
+
"learning_rate": 1.5703703703703705e-05,
|
| 1936 |
+
"loss": 0.0006,
|
| 1937 |
+
"step": 2690
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 35.02,
|
| 1941 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 1942 |
+
"loss": 0.0005,
|
| 1943 |
+
"step": 2700
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 35.02,
|
| 1947 |
+
"eval_accuracy": 0.9428571428571428,
|
| 1948 |
+
"eval_loss": 0.33030033111572266,
|
| 1949 |
+
"eval_runtime": 5.6632,
|
| 1950 |
+
"eval_samples_per_second": 12.361,
|
| 1951 |
+
"eval_steps_per_second": 3.178,
|
| 1952 |
+
"step": 2700
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 36.0,
|
| 1956 |
+
"learning_rate": 1.5407407407407408e-05,
|
| 1957 |
+
"loss": 0.0005,
|
| 1958 |
+
"step": 2710
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 36.01,
|
| 1962 |
+
"learning_rate": 1.5259259259259258e-05,
|
| 1963 |
+
"loss": 0.0004,
|
| 1964 |
+
"step": 2720
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 36.01,
|
| 1968 |
+
"learning_rate": 1.5111111111111112e-05,
|
| 1969 |
+
"loss": 0.0004,
|
| 1970 |
+
"step": 2730
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 36.01,
|
| 1974 |
+
"learning_rate": 1.4962962962962965e-05,
|
| 1975 |
+
"loss": 0.0005,
|
| 1976 |
+
"step": 2740
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 36.01,
|
| 1980 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1981 |
+
"loss": 0.0005,
|
| 1982 |
+
"step": 2750
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 36.02,
|
| 1986 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 1987 |
+
"loss": 0.0004,
|
| 1988 |
+
"step": 2760
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 36.02,
|
| 1992 |
+
"learning_rate": 1.4518518518518521e-05,
|
| 1993 |
+
"loss": 0.0004,
|
| 1994 |
+
"step": 2770
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 36.02,
|
| 1998 |
+
"eval_accuracy": 0.9428571428571428,
|
| 1999 |
+
"eval_loss": 0.17365017533302307,
|
| 2000 |
+
"eval_runtime": 5.6606,
|
| 2001 |
+
"eval_samples_per_second": 12.366,
|
| 2002 |
+
"eval_steps_per_second": 3.18,
|
| 2003 |
+
"step": 2775
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 37.0,
|
| 2007 |
+
"learning_rate": 1.437037037037037e-05,
|
| 2008 |
+
"loss": 0.0004,
|
| 2009 |
+
"step": 2780
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 37.0,
|
| 2013 |
+
"learning_rate": 1.4222222222222224e-05,
|
| 2014 |
+
"loss": 0.0005,
|
| 2015 |
+
"step": 2790
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 37.01,
|
| 2019 |
+
"learning_rate": 1.4074074074074075e-05,
|
| 2020 |
+
"loss": 0.0004,
|
| 2021 |
+
"step": 2800
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 37.01,
|
| 2025 |
+
"learning_rate": 1.3925925925925926e-05,
|
| 2026 |
+
"loss": 0.0004,
|
| 2027 |
+
"step": 2810
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 37.01,
|
| 2031 |
+
"learning_rate": 1.3777777777777778e-05,
|
| 2032 |
+
"loss": 0.0004,
|
| 2033 |
+
"step": 2820
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 37.01,
|
| 2037 |
+
"learning_rate": 1.362962962962963e-05,
|
| 2038 |
+
"loss": 0.0004,
|
| 2039 |
+
"step": 2830
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 37.02,
|
| 2043 |
+
"learning_rate": 1.348148148148148e-05,
|
| 2044 |
+
"loss": 0.0004,
|
| 2045 |
+
"step": 2840
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 37.02,
|
| 2049 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 2050 |
+
"loss": 0.0004,
|
| 2051 |
+
"step": 2850
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 37.02,
|
| 2055 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2056 |
+
"eval_loss": 0.15336854755878448,
|
| 2057 |
+
"eval_runtime": 5.7371,
|
| 2058 |
+
"eval_samples_per_second": 12.201,
|
| 2059 |
+
"eval_steps_per_second": 3.137,
|
| 2060 |
+
"step": 2850
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 38.0,
|
| 2064 |
+
"learning_rate": 1.3185185185185186e-05,
|
| 2065 |
+
"loss": 0.0004,
|
| 2066 |
+
"step": 2860
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 38.01,
|
| 2070 |
+
"learning_rate": 1.3037037037037036e-05,
|
| 2071 |
+
"loss": 0.0004,
|
| 2072 |
+
"step": 2870
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 38.01,
|
| 2076 |
+
"learning_rate": 1.2888888888888889e-05,
|
| 2077 |
+
"loss": 0.0004,
|
| 2078 |
+
"step": 2880
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 38.01,
|
| 2082 |
+
"learning_rate": 1.2740740740740742e-05,
|
| 2083 |
+
"loss": 0.0004,
|
| 2084 |
+
"step": 2890
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 38.01,
|
| 2088 |
+
"learning_rate": 1.2592592592592592e-05,
|
| 2089 |
+
"loss": 0.0004,
|
| 2090 |
+
"step": 2900
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 38.02,
|
| 2094 |
+
"learning_rate": 1.2444444444444445e-05,
|
| 2095 |
+
"loss": 0.0004,
|
| 2096 |
+
"step": 2910
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 38.02,
|
| 2100 |
+
"learning_rate": 1.2296296296296298e-05,
|
| 2101 |
+
"loss": 0.0004,
|
| 2102 |
+
"step": 2920
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 38.02,
|
| 2106 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2107 |
+
"eval_loss": 0.13503512740135193,
|
| 2108 |
+
"eval_runtime": 5.8822,
|
| 2109 |
+
"eval_samples_per_second": 11.9,
|
| 2110 |
+
"eval_steps_per_second": 3.06,
|
| 2111 |
+
"step": 2925
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 39.0,
|
| 2115 |
+
"learning_rate": 1.2148148148148149e-05,
|
| 2116 |
+
"loss": 0.0004,
|
| 2117 |
+
"step": 2930
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 39.0,
|
| 2121 |
+
"learning_rate": 1.2e-05,
|
| 2122 |
+
"loss": 0.0004,
|
| 2123 |
+
"step": 2940
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 39.01,
|
| 2127 |
+
"learning_rate": 1.1851851851851853e-05,
|
| 2128 |
+
"loss": 0.0005,
|
| 2129 |
+
"step": 2950
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 39.01,
|
| 2133 |
+
"learning_rate": 1.1703703703703705e-05,
|
| 2134 |
+
"loss": 0.0004,
|
| 2135 |
+
"step": 2960
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 39.01,
|
| 2139 |
+
"learning_rate": 1.1555555555555556e-05,
|
| 2140 |
+
"loss": 0.0004,
|
| 2141 |
+
"step": 2970
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 39.01,
|
| 2145 |
+
"learning_rate": 1.1407407407407409e-05,
|
| 2146 |
+
"loss": 0.0004,
|
| 2147 |
+
"step": 2980
|
| 2148 |
+
},
|
| 2149 |
+
{
|
| 2150 |
+
"epoch": 39.02,
|
| 2151 |
+
"learning_rate": 1.125925925925926e-05,
|
| 2152 |
+
"loss": 0.0004,
|
| 2153 |
+
"step": 2990
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 39.02,
|
| 2157 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 2158 |
+
"loss": 0.0004,
|
| 2159 |
+
"step": 3000
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 39.02,
|
| 2163 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2164 |
+
"eval_loss": 0.1270487755537033,
|
| 2165 |
+
"eval_runtime": 5.5912,
|
| 2166 |
+
"eval_samples_per_second": 12.52,
|
| 2167 |
+
"eval_steps_per_second": 3.219,
|
| 2168 |
+
"step": 3000
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 40.0,
|
| 2172 |
+
"learning_rate": 1.0962962962962963e-05,
|
| 2173 |
+
"loss": 0.0004,
|
| 2174 |
+
"step": 3010
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 40.01,
|
| 2178 |
+
"learning_rate": 1.0814814814814814e-05,
|
| 2179 |
+
"loss": 0.0004,
|
| 2180 |
+
"step": 3020
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 40.01,
|
| 2184 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 2185 |
+
"loss": 0.0004,
|
| 2186 |
+
"step": 3030
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 40.01,
|
| 2190 |
+
"learning_rate": 1.0518518518518519e-05,
|
| 2191 |
+
"loss": 0.0004,
|
| 2192 |
+
"step": 3040
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 40.01,
|
| 2196 |
+
"learning_rate": 1.037037037037037e-05,
|
| 2197 |
+
"loss": 0.0004,
|
| 2198 |
+
"step": 3050
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 40.02,
|
| 2202 |
+
"learning_rate": 1.0222222222222223e-05,
|
| 2203 |
+
"loss": 0.0004,
|
| 2204 |
+
"step": 3060
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 40.02,
|
| 2208 |
+
"learning_rate": 1.0074074074074074e-05,
|
| 2209 |
+
"loss": 0.0004,
|
| 2210 |
+
"step": 3070
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 40.02,
|
| 2214 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2215 |
+
"eval_loss": 0.1252710521221161,
|
| 2216 |
+
"eval_runtime": 5.672,
|
| 2217 |
+
"eval_samples_per_second": 12.341,
|
| 2218 |
+
"eval_steps_per_second": 3.173,
|
| 2219 |
+
"step": 3075
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 41.0,
|
| 2223 |
+
"learning_rate": 9.925925925925926e-06,
|
| 2224 |
+
"loss": 0.0004,
|
| 2225 |
+
"step": 3080
|
| 2226 |
+
},
|
| 2227 |
+
{
|
| 2228 |
+
"epoch": 41.0,
|
| 2229 |
+
"learning_rate": 9.777777777777779e-06,
|
| 2230 |
+
"loss": 0.0004,
|
| 2231 |
+
"step": 3090
|
| 2232 |
+
},
|
| 2233 |
+
{
|
| 2234 |
+
"epoch": 41.01,
|
| 2235 |
+
"learning_rate": 9.62962962962963e-06,
|
| 2236 |
+
"loss": 0.0004,
|
| 2237 |
+
"step": 3100
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 41.01,
|
| 2241 |
+
"learning_rate": 9.481481481481481e-06,
|
| 2242 |
+
"loss": 0.0004,
|
| 2243 |
+
"step": 3110
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 41.01,
|
| 2247 |
+
"learning_rate": 9.333333333333334e-06,
|
| 2248 |
+
"loss": 0.0004,
|
| 2249 |
+
"step": 3120
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 41.01,
|
| 2253 |
+
"learning_rate": 9.185185185185186e-06,
|
| 2254 |
+
"loss": 0.0004,
|
| 2255 |
+
"step": 3130
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 41.02,
|
| 2259 |
+
"learning_rate": 9.037037037037037e-06,
|
| 2260 |
+
"loss": 0.0004,
|
| 2261 |
+
"step": 3140
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 41.02,
|
| 2265 |
+
"learning_rate": 8.88888888888889e-06,
|
| 2266 |
+
"loss": 0.0004,
|
| 2267 |
+
"step": 3150
|
| 2268 |
+
},
|
| 2269 |
+
{
|
| 2270 |
+
"epoch": 41.02,
|
| 2271 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2272 |
+
"eval_loss": 0.12408071011304855,
|
| 2273 |
+
"eval_runtime": 5.7302,
|
| 2274 |
+
"eval_samples_per_second": 12.216,
|
| 2275 |
+
"eval_steps_per_second": 3.141,
|
| 2276 |
+
"step": 3150
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 42.0,
|
| 2280 |
+
"learning_rate": 8.740740740740741e-06,
|
| 2281 |
+
"loss": 0.0004,
|
| 2282 |
+
"step": 3160
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 42.01,
|
| 2286 |
+
"learning_rate": 8.592592592592593e-06,
|
| 2287 |
+
"loss": 0.0004,
|
| 2288 |
+
"step": 3170
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 42.01,
|
| 2292 |
+
"learning_rate": 8.444444444444446e-06,
|
| 2293 |
+
"loss": 0.0004,
|
| 2294 |
+
"step": 3180
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 42.01,
|
| 2298 |
+
"learning_rate": 8.296296296296297e-06,
|
| 2299 |
+
"loss": 0.0004,
|
| 2300 |
+
"step": 3190
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 42.01,
|
| 2304 |
+
"learning_rate": 8.14814814814815e-06,
|
| 2305 |
+
"loss": 0.0004,
|
| 2306 |
+
"step": 3200
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 42.02,
|
| 2310 |
+
"learning_rate": 8.000000000000001e-06,
|
| 2311 |
+
"loss": 0.0004,
|
| 2312 |
+
"step": 3210
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 42.02,
|
| 2316 |
+
"learning_rate": 7.851851851851853e-06,
|
| 2317 |
+
"loss": 0.0004,
|
| 2318 |
+
"step": 3220
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 42.02,
|
| 2322 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2323 |
+
"eval_loss": 0.12468262761831284,
|
| 2324 |
+
"eval_runtime": 5.8752,
|
| 2325 |
+
"eval_samples_per_second": 11.915,
|
| 2326 |
+
"eval_steps_per_second": 3.064,
|
| 2327 |
+
"step": 3225
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 43.0,
|
| 2331 |
+
"learning_rate": 7.703703703703704e-06,
|
| 2332 |
+
"loss": 0.0004,
|
| 2333 |
+
"step": 3230
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 43.0,
|
| 2337 |
+
"learning_rate": 7.555555555555556e-06,
|
| 2338 |
+
"loss": 0.0004,
|
| 2339 |
+
"step": 3240
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 43.01,
|
| 2343 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 2344 |
+
"loss": 0.0004,
|
| 2345 |
+
"step": 3250
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 43.01,
|
| 2349 |
+
"learning_rate": 7.2592592592592605e-06,
|
| 2350 |
+
"loss": 0.0004,
|
| 2351 |
+
"step": 3260
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 43.01,
|
| 2355 |
+
"learning_rate": 7.111111111111112e-06,
|
| 2356 |
+
"loss": 0.0004,
|
| 2357 |
+
"step": 3270
|
| 2358 |
+
},
|
| 2359 |
+
{
|
| 2360 |
+
"epoch": 43.01,
|
| 2361 |
+
"learning_rate": 6.962962962962963e-06,
|
| 2362 |
+
"loss": 0.0004,
|
| 2363 |
+
"step": 3280
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 43.02,
|
| 2367 |
+
"learning_rate": 6.814814814814815e-06,
|
| 2368 |
+
"loss": 0.0004,
|
| 2369 |
+
"step": 3290
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 43.02,
|
| 2373 |
+
"learning_rate": 6.666666666666667e-06,
|
| 2374 |
+
"loss": 0.0004,
|
| 2375 |
+
"step": 3300
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 43.02,
|
| 2379 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2380 |
+
"eval_loss": 0.12618018686771393,
|
| 2381 |
+
"eval_runtime": 5.7926,
|
| 2382 |
+
"eval_samples_per_second": 12.084,
|
| 2383 |
+
"eval_steps_per_second": 3.107,
|
| 2384 |
+
"step": 3300
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 44.0,
|
| 2388 |
+
"learning_rate": 6.518518518518518e-06,
|
| 2389 |
+
"loss": 0.0004,
|
| 2390 |
+
"step": 3310
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 44.01,
|
| 2394 |
+
"learning_rate": 6.370370370370371e-06,
|
| 2395 |
+
"loss": 0.0004,
|
| 2396 |
+
"step": 3320
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 44.01,
|
| 2400 |
+
"learning_rate": 6.222222222222222e-06,
|
| 2401 |
+
"loss": 0.0004,
|
| 2402 |
+
"step": 3330
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 44.01,
|
| 2406 |
+
"learning_rate": 6.0740740740740745e-06,
|
| 2407 |
+
"loss": 0.0004,
|
| 2408 |
+
"step": 3340
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 44.01,
|
| 2412 |
+
"learning_rate": 5.925925925925927e-06,
|
| 2413 |
+
"loss": 0.0004,
|
| 2414 |
+
"step": 3350
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 44.02,
|
| 2418 |
+
"learning_rate": 5.777777777777778e-06,
|
| 2419 |
+
"loss": 0.0004,
|
| 2420 |
+
"step": 3360
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 44.02,
|
| 2424 |
+
"learning_rate": 5.62962962962963e-06,
|
| 2425 |
+
"loss": 0.0004,
|
| 2426 |
+
"step": 3370
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 44.02,
|
| 2430 |
+
"eval_accuracy": 0.9571428571428572,
|
| 2431 |
+
"eval_loss": 0.12661002576351166,
|
| 2432 |
+
"eval_runtime": 5.8019,
|
| 2433 |
+
"eval_samples_per_second": 12.065,
|
| 2434 |
+
"eval_steps_per_second": 3.102,
|
| 2435 |
+
"step": 3375
|
| 2436 |
+
},
|
| 2437 |
+
{
|
| 2438 |
+
"epoch": 45.0,
|
| 2439 |
+
"learning_rate": 5.4814814814814815e-06,
|
| 2440 |
+
"loss": 0.0004,
|
| 2441 |
+
"step": 3380
|
| 2442 |
+
},
|
| 2443 |
+
{
|
| 2444 |
+
"epoch": 45.0,
|
| 2445 |
+
"learning_rate": 5.333333333333334e-06,
|
| 2446 |
+
"loss": 0.0004,
|
| 2447 |
+
"step": 3390
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 45.01,
|
| 2451 |
+
"learning_rate": 5.185185185185185e-06,
|
| 2452 |
+
"loss": 0.0004,
|
| 2453 |
+
"step": 3400
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 45.01,
|
| 2457 |
+
"learning_rate": 5.037037037037037e-06,
|
| 2458 |
+
"loss": 0.0004,
|
| 2459 |
+
"step": 3410
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 45.01,
|
| 2463 |
+
"learning_rate": 4.888888888888889e-06,
|
| 2464 |
+
"loss": 0.0253,
|
| 2465 |
+
"step": 3420
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 45.01,
|
| 2469 |
+
"learning_rate": 4.740740740740741e-06,
|
| 2470 |
+
"loss": 0.0004,
|
| 2471 |
+
"step": 3430
|
| 2472 |
+
},
|
| 2473 |
+
{
|
| 2474 |
+
"epoch": 45.02,
|
| 2475 |
+
"learning_rate": 4.592592592592593e-06,
|
| 2476 |
+
"loss": 0.0004,
|
| 2477 |
+
"step": 3440
|
| 2478 |
+
},
|
| 2479 |
+
{
|
| 2480 |
+
"epoch": 45.02,
|
| 2481 |
+
"learning_rate": 4.444444444444445e-06,
|
| 2482 |
+
"loss": 0.0004,
|
| 2483 |
+
"step": 3450
|
| 2484 |
+
},
|
| 2485 |
+
{
|
| 2486 |
+
"epoch": 45.02,
|
| 2487 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2488 |
+
"eval_loss": 0.17405559122562408,
|
| 2489 |
+
"eval_runtime": 5.6182,
|
| 2490 |
+
"eval_samples_per_second": 12.459,
|
| 2491 |
+
"eval_steps_per_second": 3.204,
|
| 2492 |
+
"step": 3450
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 46.0,
|
| 2496 |
+
"learning_rate": 4.296296296296296e-06,
|
| 2497 |
+
"loss": 0.0004,
|
| 2498 |
+
"step": 3460
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 46.01,
|
| 2502 |
+
"learning_rate": 4.1481481481481485e-06,
|
| 2503 |
+
"loss": 0.0004,
|
| 2504 |
+
"step": 3470
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 46.01,
|
| 2508 |
+
"learning_rate": 4.000000000000001e-06,
|
| 2509 |
+
"loss": 0.0004,
|
| 2510 |
+
"step": 3480
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 46.01,
|
| 2514 |
+
"learning_rate": 3.851851851851852e-06,
|
| 2515 |
+
"loss": 0.0004,
|
| 2516 |
+
"step": 3490
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 46.01,
|
| 2520 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 2521 |
+
"loss": 0.0004,
|
| 2522 |
+
"step": 3500
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 46.02,
|
| 2526 |
+
"learning_rate": 3.555555555555556e-06,
|
| 2527 |
+
"loss": 0.0004,
|
| 2528 |
+
"step": 3510
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 46.02,
|
| 2532 |
+
"learning_rate": 3.4074074074074077e-06,
|
| 2533 |
+
"loss": 0.0004,
|
| 2534 |
+
"step": 3520
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 46.02,
|
| 2538 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2539 |
+
"eval_loss": 0.17525674402713776,
|
| 2540 |
+
"eval_runtime": 5.8413,
|
| 2541 |
+
"eval_samples_per_second": 11.984,
|
| 2542 |
+
"eval_steps_per_second": 3.082,
|
| 2543 |
+
"step": 3525
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 47.0,
|
| 2547 |
+
"learning_rate": 3.259259259259259e-06,
|
| 2548 |
+
"loss": 0.0004,
|
| 2549 |
+
"step": 3530
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 47.0,
|
| 2553 |
+
"learning_rate": 3.111111111111111e-06,
|
| 2554 |
+
"loss": 0.0004,
|
| 2555 |
+
"step": 3540
|
| 2556 |
+
},
|
| 2557 |
+
{
|
| 2558 |
+
"epoch": 47.01,
|
| 2559 |
+
"learning_rate": 2.9629629629629633e-06,
|
| 2560 |
+
"loss": 0.0004,
|
| 2561 |
+
"step": 3550
|
| 2562 |
+
},
|
| 2563 |
+
{
|
| 2564 |
+
"epoch": 47.01,
|
| 2565 |
+
"learning_rate": 2.814814814814815e-06,
|
| 2566 |
+
"loss": 0.0004,
|
| 2567 |
+
"step": 3560
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 47.01,
|
| 2571 |
+
"learning_rate": 2.666666666666667e-06,
|
| 2572 |
+
"loss": 0.0004,
|
| 2573 |
+
"step": 3570
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 47.01,
|
| 2577 |
+
"learning_rate": 2.5185185185185186e-06,
|
| 2578 |
+
"loss": 0.0004,
|
| 2579 |
+
"step": 3580
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 47.02,
|
| 2583 |
+
"learning_rate": 2.3703703703703703e-06,
|
| 2584 |
+
"loss": 0.0006,
|
| 2585 |
+
"step": 3590
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 47.02,
|
| 2589 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 2590 |
+
"loss": 0.0004,
|
| 2591 |
+
"step": 3600
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 47.02,
|
| 2595 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2596 |
+
"eval_loss": 0.1633566915988922,
|
| 2597 |
+
"eval_runtime": 5.6957,
|
| 2598 |
+
"eval_samples_per_second": 12.29,
|
| 2599 |
+
"eval_steps_per_second": 3.16,
|
| 2600 |
+
"step": 3600
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 48.0,
|
| 2604 |
+
"learning_rate": 2.0740740740740742e-06,
|
| 2605 |
+
"loss": 0.0004,
|
| 2606 |
+
"step": 3610
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 48.01,
|
| 2610 |
+
"learning_rate": 1.925925925925926e-06,
|
| 2611 |
+
"loss": 0.0003,
|
| 2612 |
+
"step": 3620
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 48.01,
|
| 2616 |
+
"learning_rate": 1.777777777777778e-06,
|
| 2617 |
+
"loss": 0.0004,
|
| 2618 |
+
"step": 3630
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 48.01,
|
| 2622 |
+
"learning_rate": 1.6296296296296295e-06,
|
| 2623 |
+
"loss": 0.0004,
|
| 2624 |
+
"step": 3640
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 48.01,
|
| 2628 |
+
"learning_rate": 1.4814814814814817e-06,
|
| 2629 |
+
"loss": 0.0004,
|
| 2630 |
+
"step": 3650
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 48.02,
|
| 2634 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 2635 |
+
"loss": 0.0004,
|
| 2636 |
+
"step": 3660
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 48.02,
|
| 2640 |
+
"learning_rate": 1.1851851851851852e-06,
|
| 2641 |
+
"loss": 0.0004,
|
| 2642 |
+
"step": 3670
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 48.02,
|
| 2646 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2647 |
+
"eval_loss": 0.1603454053401947,
|
| 2648 |
+
"eval_runtime": 5.9217,
|
| 2649 |
+
"eval_samples_per_second": 11.821,
|
| 2650 |
+
"eval_steps_per_second": 3.04,
|
| 2651 |
+
"step": 3675
|
| 2652 |
+
},
|
| 2653 |
+
{
|
| 2654 |
+
"epoch": 49.0,
|
| 2655 |
+
"learning_rate": 1.0370370370370371e-06,
|
| 2656 |
+
"loss": 0.0004,
|
| 2657 |
+
"step": 3680
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 49.0,
|
| 2661 |
+
"learning_rate": 8.88888888888889e-07,
|
| 2662 |
+
"loss": 0.0004,
|
| 2663 |
+
"step": 3690
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 49.01,
|
| 2667 |
+
"learning_rate": 7.407407407407408e-07,
|
| 2668 |
+
"loss": 0.0004,
|
| 2669 |
+
"step": 3700
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 49.01,
|
| 2673 |
+
"learning_rate": 5.925925925925926e-07,
|
| 2674 |
+
"loss": 0.0004,
|
| 2675 |
+
"step": 3710
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 49.01,
|
| 2679 |
+
"learning_rate": 4.444444444444445e-07,
|
| 2680 |
+
"loss": 0.0004,
|
| 2681 |
+
"step": 3720
|
| 2682 |
+
},
|
| 2683 |
+
{
|
| 2684 |
+
"epoch": 49.01,
|
| 2685 |
+
"learning_rate": 2.962962962962963e-07,
|
| 2686 |
+
"loss": 0.0004,
|
| 2687 |
+
"step": 3730
|
| 2688 |
+
},
|
| 2689 |
+
{
|
| 2690 |
+
"epoch": 49.02,
|
| 2691 |
+
"learning_rate": 1.4814814814814815e-07,
|
| 2692 |
+
"loss": 0.0004,
|
| 2693 |
+
"step": 3740
|
| 2694 |
+
},
|
| 2695 |
+
{
|
| 2696 |
+
"epoch": 49.02,
|
| 2697 |
+
"learning_rate": 0.0,
|
| 2698 |
+
"loss": 0.0004,
|
| 2699 |
+
"step": 3750
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 49.02,
|
| 2703 |
+
"eval_accuracy": 0.9714285714285714,
|
| 2704 |
+
"eval_loss": 0.16023388504981995,
|
| 2705 |
+
"eval_runtime": 5.6893,
|
| 2706 |
+
"eval_samples_per_second": 12.304,
|
| 2707 |
+
"eval_steps_per_second": 3.164,
|
| 2708 |
+
"step": 3750
|
| 2709 |
+
},
|
| 2710 |
+
{
|
| 2711 |
+
"epoch": 49.02,
|
| 2712 |
+
"step": 3750,
|
| 2713 |
+
"total_flos": 1.86923023515648e+19,
|
| 2714 |
+
"train_loss": 0.1646428666052719,
|
| 2715 |
+
"train_runtime": 3006.4065,
|
| 2716 |
+
"train_samples_per_second": 4.989,
|
| 2717 |
+
"train_steps_per_second": 1.247
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 49.02,
|
| 2721 |
+
"eval_accuracy": 0.9290322580645162,
|
| 2722 |
+
"eval_loss": 0.18336611986160278,
|
| 2723 |
+
"eval_runtime": 15.2988,
|
| 2724 |
+
"eval_samples_per_second": 10.132,
|
| 2725 |
+
"eval_steps_per_second": 2.549,
|
| 2726 |
+
"step": 3750
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 49.02,
|
| 2730 |
+
"eval_accuracy": 0.9290322580645162,
|
| 2731 |
+
"eval_loss": 0.18336611986160278,
|
| 2732 |
+
"eval_runtime": 12.5538,
|
| 2733 |
+
"eval_samples_per_second": 12.347,
|
| 2734 |
+
"eval_steps_per_second": 3.107,
|
| 2735 |
+
"step": 3750
|
| 2736 |
}
|
| 2737 |
],
|
| 2738 |
+
"max_steps": 3750,
|
| 2739 |
"num_train_epochs": 9223372036854775807,
|
| 2740 |
+
"total_flos": 1.86923023515648e+19,
|
| 2741 |
"trial_name": null,
|
| 2742 |
"trial_params": null
|
| 2743 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e3454d677f838f72c44c0d25ed5379fc596af582a8d2edaaedf4baaf9e9edc
|
| 3 |
size 3439
|