Commit
•
d17a57e
1
Parent(s):
8248681
End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +508 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9859259259259259,
|
| 4 |
+
"eval_loss": 0.057608071714639664,
|
| 5 |
+
"eval_runtime": 26.7664,
|
| 6 |
+
"eval_samples_per_second": 151.309,
|
| 7 |
+
"eval_steps_per_second": 4.745,
|
| 8 |
+
"total_flos": 2.3729757133844644e+18,
|
| 9 |
+
"train_loss": 0.2908774734962554,
|
| 10 |
+
"train_runtime": 1704.3854,
|
| 11 |
+
"train_samples_per_second": 55.445,
|
| 12 |
+
"train_steps_per_second": 0.431
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9859259259259259,
|
| 4 |
+
"eval_loss": 0.057608071714639664,
|
| 5 |
+
"eval_runtime": 26.7664,
|
| 6 |
+
"eval_samples_per_second": 151.309,
|
| 7 |
+
"eval_steps_per_second": 4.745
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 111373605
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d9642a495e346810e8cab9870317e8a3fb730506162c11ab33af3749d28140d
|
| 3 |
size 111373605
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"total_flos": 2.3729757133844644e+18,
|
| 4 |
+
"train_loss": 0.2908774734962554,
|
| 5 |
+
"train_runtime": 1704.3854,
|
| 6 |
+
"train_samples_per_second": 55.445,
|
| 7 |
+
"train_steps_per_second": 0.431
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9859259259259259,
|
| 3 |
+
"best_model_checkpoint": "vit-convnext-tiny-224-eurosat/checkpoint-588",
|
| 4 |
+
"epoch": 4.99492385786802,
|
| 5 |
+
"global_step": 735,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 6.7567567567567575e-06,
|
| 13 |
+
"loss": 2.2859,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.14,
|
| 18 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 19 |
+
"loss": 2.2442,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.2,
|
| 24 |
+
"learning_rate": 2.0270270270270273e-05,
|
| 25 |
+
"loss": 2.1563,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.27,
|
| 30 |
+
"learning_rate": 2.702702702702703e-05,
|
| 31 |
+
"loss": 2.0172,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.34,
|
| 36 |
+
"learning_rate": 3.3783783783783784e-05,
|
| 37 |
+
"loss": 1.8198,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.41,
|
| 42 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 43 |
+
"loss": 1.5871,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.47,
|
| 48 |
+
"learning_rate": 4.72972972972973e-05,
|
| 49 |
+
"loss": 1.3185,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.54,
|
| 54 |
+
"learning_rate": 4.9546142208774585e-05,
|
| 55 |
+
"loss": 1.0524,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.61,
|
| 60 |
+
"learning_rate": 4.878971255673222e-05,
|
| 61 |
+
"loss": 0.849,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.68,
|
| 66 |
+
"learning_rate": 4.803328290468986e-05,
|
| 67 |
+
"loss": 0.6729,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.74,
|
| 72 |
+
"learning_rate": 4.7276853252647505e-05,
|
| 73 |
+
"loss": 0.5013,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.81,
|
| 78 |
+
"learning_rate": 4.652042360060514e-05,
|
| 79 |
+
"loss": 0.4268,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.88,
|
| 84 |
+
"learning_rate": 4.576399394856278e-05,
|
| 85 |
+
"loss": 0.3198,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.95,
|
| 90 |
+
"learning_rate": 4.5007564296520425e-05,
|
| 91 |
+
"loss": 0.2881,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.99,
|
| 96 |
+
"eval_accuracy": 0.9587654320987654,
|
| 97 |
+
"eval_loss": 0.23249287903308868,
|
| 98 |
+
"eval_runtime": 26.3088,
|
| 99 |
+
"eval_samples_per_second": 153.941,
|
| 100 |
+
"eval_steps_per_second": 4.827,
|
| 101 |
+
"step": 147
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.02,
|
| 105 |
+
"learning_rate": 4.425113464447806e-05,
|
| 106 |
+
"loss": 0.2379,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.09,
|
| 111 |
+
"learning_rate": 4.34947049924357e-05,
|
| 112 |
+
"loss": 0.1822,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.16,
|
| 117 |
+
"learning_rate": 4.2738275340393345e-05,
|
| 118 |
+
"loss": 0.1815,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.22,
|
| 123 |
+
"learning_rate": 4.198184568835098e-05,
|
| 124 |
+
"loss": 0.1558,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.29,
|
| 129 |
+
"learning_rate": 4.122541603630862e-05,
|
| 130 |
+
"loss": 0.1337,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.36,
|
| 135 |
+
"learning_rate": 4.0468986384266265e-05,
|
| 136 |
+
"loss": 0.1429,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.43,
|
| 141 |
+
"learning_rate": 3.97125567322239e-05,
|
| 142 |
+
"loss": 0.1149,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.49,
|
| 147 |
+
"learning_rate": 3.895612708018154e-05,
|
| 148 |
+
"loss": 0.1199,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.56,
|
| 153 |
+
"learning_rate": 3.8199697428139184e-05,
|
| 154 |
+
"loss": 0.1194,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.63,
|
| 159 |
+
"learning_rate": 3.744326777609682e-05,
|
| 160 |
+
"loss": 0.1027,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.7,
|
| 165 |
+
"learning_rate": 3.668683812405446e-05,
|
| 166 |
+
"loss": 0.1092,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.76,
|
| 171 |
+
"learning_rate": 3.5930408472012104e-05,
|
| 172 |
+
"loss": 0.1038,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.83,
|
| 177 |
+
"learning_rate": 3.517397881996974e-05,
|
| 178 |
+
"loss": 0.0811,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.9,
|
| 183 |
+
"learning_rate": 3.441754916792738e-05,
|
| 184 |
+
"loss": 0.0988,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.97,
|
| 189 |
+
"learning_rate": 3.3661119515885024e-05,
|
| 190 |
+
"loss": 0.0869,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.99,
|
| 195 |
+
"eval_accuracy": 0.9753086419753086,
|
| 196 |
+
"eval_loss": 0.09120676666498184,
|
| 197 |
+
"eval_runtime": 25.7061,
|
| 198 |
+
"eval_samples_per_second": 157.55,
|
| 199 |
+
"eval_steps_per_second": 4.94,
|
| 200 |
+
"step": 294
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.04,
|
| 204 |
+
"learning_rate": 3.290468986384266e-05,
|
| 205 |
+
"loss": 0.0707,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.11,
|
| 210 |
+
"learning_rate": 3.21482602118003e-05,
|
| 211 |
+
"loss": 0.0525,
|
| 212 |
+
"step": 310
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.18,
|
| 216 |
+
"learning_rate": 3.1391830559757944e-05,
|
| 217 |
+
"loss": 0.0632,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.24,
|
| 222 |
+
"learning_rate": 3.063540090771558e-05,
|
| 223 |
+
"loss": 0.0926,
|
| 224 |
+
"step": 330
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.31,
|
| 228 |
+
"learning_rate": 2.9878971255673223e-05,
|
| 229 |
+
"loss": 0.0628,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.38,
|
| 234 |
+
"learning_rate": 2.9122541603630864e-05,
|
| 235 |
+
"loss": 0.0677,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.45,
|
| 240 |
+
"learning_rate": 2.83661119515885e-05,
|
| 241 |
+
"loss": 0.0436,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.51,
|
| 246 |
+
"learning_rate": 2.7609682299546143e-05,
|
| 247 |
+
"loss": 0.0821,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.58,
|
| 252 |
+
"learning_rate": 2.6853252647503784e-05,
|
| 253 |
+
"loss": 0.0567,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.65,
|
| 258 |
+
"learning_rate": 2.609682299546142e-05,
|
| 259 |
+
"loss": 0.0641,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.72,
|
| 264 |
+
"learning_rate": 2.5340393343419063e-05,
|
| 265 |
+
"loss": 0.0534,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.79,
|
| 270 |
+
"learning_rate": 2.45839636913767e-05,
|
| 271 |
+
"loss": 0.0454,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.85,
|
| 276 |
+
"learning_rate": 2.382753403933434e-05,
|
| 277 |
+
"loss": 0.0627,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.92,
|
| 282 |
+
"learning_rate": 2.3071104387291982e-05,
|
| 283 |
+
"loss": 0.036,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.99,
|
| 288 |
+
"learning_rate": 2.231467473524962e-05,
|
| 289 |
+
"loss": 0.0687,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.99,
|
| 294 |
+
"eval_accuracy": 0.9804938271604938,
|
| 295 |
+
"eval_loss": 0.06631184369325638,
|
| 296 |
+
"eval_runtime": 25.6488,
|
| 297 |
+
"eval_samples_per_second": 157.902,
|
| 298 |
+
"eval_steps_per_second": 4.952,
|
| 299 |
+
"step": 441
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.06,
|
| 303 |
+
"learning_rate": 2.155824508320726e-05,
|
| 304 |
+
"loss": 0.0542,
|
| 305 |
+
"step": 450
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 3.13,
|
| 309 |
+
"learning_rate": 2.0801815431164902e-05,
|
| 310 |
+
"loss": 0.044,
|
| 311 |
+
"step": 460
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.2,
|
| 315 |
+
"learning_rate": 2.004538577912254e-05,
|
| 316 |
+
"loss": 0.0346,
|
| 317 |
+
"step": 470
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.26,
|
| 321 |
+
"learning_rate": 1.928895612708018e-05,
|
| 322 |
+
"loss": 0.0406,
|
| 323 |
+
"step": 480
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.33,
|
| 327 |
+
"learning_rate": 1.8532526475037822e-05,
|
| 328 |
+
"loss": 0.0496,
|
| 329 |
+
"step": 490
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.4,
|
| 333 |
+
"learning_rate": 1.777609682299546e-05,
|
| 334 |
+
"loss": 0.046,
|
| 335 |
+
"step": 500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.47,
|
| 339 |
+
"learning_rate": 1.70196671709531e-05,
|
| 340 |
+
"loss": 0.0356,
|
| 341 |
+
"step": 510
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.53,
|
| 345 |
+
"learning_rate": 1.6263237518910742e-05,
|
| 346 |
+
"loss": 0.0339,
|
| 347 |
+
"step": 520
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.6,
|
| 351 |
+
"learning_rate": 1.550680786686838e-05,
|
| 352 |
+
"loss": 0.0384,
|
| 353 |
+
"step": 530
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.67,
|
| 357 |
+
"learning_rate": 1.4750378214826023e-05,
|
| 358 |
+
"loss": 0.0319,
|
| 359 |
+
"step": 540
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.74,
|
| 363 |
+
"learning_rate": 1.3993948562783662e-05,
|
| 364 |
+
"loss": 0.0333,
|
| 365 |
+
"step": 550
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.81,
|
| 369 |
+
"learning_rate": 1.3237518910741301e-05,
|
| 370 |
+
"loss": 0.0258,
|
| 371 |
+
"step": 560
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.87,
|
| 375 |
+
"learning_rate": 1.248108925869894e-05,
|
| 376 |
+
"loss": 0.0377,
|
| 377 |
+
"step": 570
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.94,
|
| 381 |
+
"learning_rate": 1.172465960665658e-05,
|
| 382 |
+
"loss": 0.0272,
|
| 383 |
+
"step": 580
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.99,
|
| 387 |
+
"eval_accuracy": 0.9859259259259259,
|
| 388 |
+
"eval_loss": 0.057608071714639664,
|
| 389 |
+
"eval_runtime": 25.6469,
|
| 390 |
+
"eval_samples_per_second": 157.914,
|
| 391 |
+
"eval_steps_per_second": 4.952,
|
| 392 |
+
"step": 588
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 4.01,
|
| 396 |
+
"learning_rate": 1.0968229954614221e-05,
|
| 397 |
+
"loss": 0.0313,
|
| 398 |
+
"step": 590
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.08,
|
| 402 |
+
"learning_rate": 1.021180030257186e-05,
|
| 403 |
+
"loss": 0.0232,
|
| 404 |
+
"step": 600
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.15,
|
| 408 |
+
"learning_rate": 9.4553706505295e-06,
|
| 409 |
+
"loss": 0.0308,
|
| 410 |
+
"step": 610
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 4.22,
|
| 414 |
+
"learning_rate": 8.698940998487141e-06,
|
| 415 |
+
"loss": 0.0245,
|
| 416 |
+
"step": 620
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.28,
|
| 420 |
+
"learning_rate": 7.94251134644478e-06,
|
| 421 |
+
"loss": 0.0334,
|
| 422 |
+
"step": 630
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.35,
|
| 426 |
+
"learning_rate": 7.186081694402421e-06,
|
| 427 |
+
"loss": 0.0318,
|
| 428 |
+
"step": 640
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.42,
|
| 432 |
+
"learning_rate": 6.429652042360061e-06,
|
| 433 |
+
"loss": 0.0238,
|
| 434 |
+
"step": 650
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.49,
|
| 438 |
+
"learning_rate": 5.6732223903177e-06,
|
| 439 |
+
"loss": 0.0333,
|
| 440 |
+
"step": 660
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.55,
|
| 444 |
+
"learning_rate": 4.9167927382753406e-06,
|
| 445 |
+
"loss": 0.0266,
|
| 446 |
+
"step": 670
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.62,
|
| 450 |
+
"learning_rate": 4.16036308623298e-06,
|
| 451 |
+
"loss": 0.0222,
|
| 452 |
+
"step": 680
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.69,
|
| 456 |
+
"learning_rate": 3.40393343419062e-06,
|
| 457 |
+
"loss": 0.0229,
|
| 458 |
+
"step": 690
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.76,
|
| 462 |
+
"learning_rate": 2.64750378214826e-06,
|
| 463 |
+
"loss": 0.0286,
|
| 464 |
+
"step": 700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.83,
|
| 468 |
+
"learning_rate": 1.8910741301059002e-06,
|
| 469 |
+
"loss": 0.0222,
|
| 470 |
+
"step": 710
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.89,
|
| 474 |
+
"learning_rate": 1.13464447806354e-06,
|
| 475 |
+
"loss": 0.0197,
|
| 476 |
+
"step": 720
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.96,
|
| 480 |
+
"learning_rate": 3.7821482602118004e-07,
|
| 481 |
+
"loss": 0.0247,
|
| 482 |
+
"step": 730
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.99,
|
| 486 |
+
"eval_accuracy": 0.9854320987654321,
|
| 487 |
+
"eval_loss": 0.053181808441877365,
|
| 488 |
+
"eval_runtime": 25.598,
|
| 489 |
+
"eval_samples_per_second": 158.216,
|
| 490 |
+
"eval_steps_per_second": 4.961,
|
| 491 |
+
"step": 735
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.99,
|
| 495 |
+
"step": 735,
|
| 496 |
+
"total_flos": 2.3729757133844644e+18,
|
| 497 |
+
"train_loss": 0.2908774734962554,
|
| 498 |
+
"train_runtime": 1704.3854,
|
| 499 |
+
"train_samples_per_second": 55.445,
|
| 500 |
+
"train_steps_per_second": 0.431
|
| 501 |
+
}
|
| 502 |
+
],
|
| 503 |
+
"max_steps": 735,
|
| 504 |
+
"num_train_epochs": 5,
|
| 505 |
+
"total_flos": 2.3729757133844644e+18,
|
| 506 |
+
"trial_name": null,
|
| 507 |
+
"trial_params": null
|
| 508 |
+
}
|