Commit
·
8b57fae
1
Parent(s):
69562f0
Training in progress, epoch 1
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Nov03_21-21-00_ee159d4dd62e/events.out.tfevents.1699046460.ee159d4dd62e.5505.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +508 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.9093674240032072e+18,
|
| 4 |
+
"train_loss": 1.0707446556586724,
|
| 5 |
+
"train_runtime": 668.48,
|
| 6 |
+
"train_samples_per_second": 36.857,
|
| 7 |
+
"train_steps_per_second": 1.152
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343245508
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a356ec54d57fe4f1e0397a86b8fafc281f6f1a2def876b01e7848344dc18bddd
|
| 3 |
size 343245508
|
runs/Nov03_21-21-00_ee159d4dd62e/events.out.tfevents.1699046460.ee159d4dd62e.5505.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1d5eba1aca3174343ba5601c428e6d1943d77fadfcf71d1d4cf2cde7e5d86be
|
| 3 |
+
size 10746
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 1.9093674240032072e+18,
|
| 4 |
+
"train_loss": 1.0707446556586724,
|
| 5 |
+
"train_runtime": 668.48,
|
| 6 |
+
"train_samples_per_second": 36.857,
|
| 7 |
+
"train_steps_per_second": 1.152
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6668800115585327,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-age-classification/checkpoint-770",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 770,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 0.00019740259740259742,
|
| 14 |
+
"loss": 1.678,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.05,
|
| 19 |
+
"learning_rate": 0.0001948051948051948,
|
| 20 |
+
"loss": 1.5725,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 0.00019220779220779222,
|
| 26 |
+
"loss": 1.4755,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.1,
|
| 31 |
+
"learning_rate": 0.00018961038961038963,
|
| 32 |
+
"loss": 1.4616,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.13,
|
| 37 |
+
"learning_rate": 0.000187012987012987,
|
| 38 |
+
"loss": 1.4189,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.16,
|
| 43 |
+
"learning_rate": 0.00018441558441558442,
|
| 44 |
+
"loss": 1.4155,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.18,
|
| 49 |
+
"learning_rate": 0.00018181818181818183,
|
| 50 |
+
"loss": 1.3158,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21,
|
| 55 |
+
"learning_rate": 0.00017922077922077922,
|
| 56 |
+
"loss": 1.5087,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.23,
|
| 61 |
+
"learning_rate": 0.00017662337662337663,
|
| 62 |
+
"loss": 1.3685,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.26,
|
| 67 |
+
"learning_rate": 0.00017402597402597401,
|
| 68 |
+
"loss": 1.3054,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.29,
|
| 73 |
+
"learning_rate": 0.00017142857142857143,
|
| 74 |
+
"loss": 1.3126,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.31,
|
| 79 |
+
"learning_rate": 0.00016883116883116884,
|
| 80 |
+
"loss": 1.3627,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.34,
|
| 85 |
+
"learning_rate": 0.00016623376623376625,
|
| 86 |
+
"loss": 1.2071,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.36,
|
| 91 |
+
"learning_rate": 0.00016363636363636366,
|
| 92 |
+
"loss": 1.2976,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39,
|
| 97 |
+
"learning_rate": 0.00016103896103896104,
|
| 98 |
+
"loss": 1.2975,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.42,
|
| 103 |
+
"learning_rate": 0.00015844155844155845,
|
| 104 |
+
"loss": 1.3719,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.44,
|
| 109 |
+
"learning_rate": 0.00015584415584415587,
|
| 110 |
+
"loss": 1.3048,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.47,
|
| 115 |
+
"learning_rate": 0.00015324675324675325,
|
| 116 |
+
"loss": 1.1897,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.49,
|
| 121 |
+
"learning_rate": 0.00015064935064935066,
|
| 122 |
+
"loss": 1.114,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.52,
|
| 127 |
+
"learning_rate": 0.00014805194805194807,
|
| 128 |
+
"loss": 1.2517,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.55,
|
| 133 |
+
"learning_rate": 0.00014545454545454546,
|
| 134 |
+
"loss": 1.1583,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.57,
|
| 139 |
+
"learning_rate": 0.00014285714285714287,
|
| 140 |
+
"loss": 1.2316,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.6,
|
| 145 |
+
"learning_rate": 0.00014025974025974028,
|
| 146 |
+
"loss": 1.2343,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.62,
|
| 151 |
+
"learning_rate": 0.00013766233766233766,
|
| 152 |
+
"loss": 1.2562,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.65,
|
| 157 |
+
"learning_rate": 0.00013506493506493507,
|
| 158 |
+
"loss": 1.2292,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.68,
|
| 163 |
+
"learning_rate": 0.00013246753246753249,
|
| 164 |
+
"loss": 1.1743,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.7,
|
| 169 |
+
"learning_rate": 0.00012987012987012987,
|
| 170 |
+
"loss": 1.2493,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.73,
|
| 175 |
+
"learning_rate": 0.00012727272727272728,
|
| 176 |
+
"loss": 1.1411,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.75,
|
| 181 |
+
"learning_rate": 0.00012467532467532467,
|
| 182 |
+
"loss": 1.1051,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.78,
|
| 187 |
+
"learning_rate": 0.00012207792207792208,
|
| 188 |
+
"loss": 1.0832,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.81,
|
| 193 |
+
"learning_rate": 0.00011948051948051949,
|
| 194 |
+
"loss": 1.1295,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.83,
|
| 199 |
+
"learning_rate": 0.00011688311688311689,
|
| 200 |
+
"loss": 1.1054,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.86,
|
| 205 |
+
"learning_rate": 0.00011428571428571428,
|
| 206 |
+
"loss": 1.1406,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.88,
|
| 211 |
+
"learning_rate": 0.00011168831168831168,
|
| 212 |
+
"loss": 1.1486,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.91,
|
| 217 |
+
"learning_rate": 0.00010909090909090909,
|
| 218 |
+
"loss": 1.1239,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.94,
|
| 223 |
+
"learning_rate": 0.00010649350649350649,
|
| 224 |
+
"loss": 1.0806,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.96,
|
| 229 |
+
"learning_rate": 0.00010389610389610389,
|
| 230 |
+
"loss": 1.1452,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.99,
|
| 235 |
+
"learning_rate": 0.0001012987012987013,
|
| 236 |
+
"loss": 1.1069,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.0,
|
| 241 |
+
"eval_accuracy": 0.620910788213329,
|
| 242 |
+
"eval_loss": 0.9425380825996399,
|
| 243 |
+
"eval_runtime": 112.3377,
|
| 244 |
+
"eval_samples_per_second": 109.66,
|
| 245 |
+
"eval_steps_per_second": 13.709,
|
| 246 |
+
"step": 385
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.01,
|
| 250 |
+
"learning_rate": 9.870129870129871e-05,
|
| 251 |
+
"loss": 0.944,
|
| 252 |
+
"step": 390
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.04,
|
| 256 |
+
"learning_rate": 9.610389610389611e-05,
|
| 257 |
+
"loss": 0.9775,
|
| 258 |
+
"step": 400
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.06,
|
| 262 |
+
"learning_rate": 9.35064935064935e-05,
|
| 263 |
+
"loss": 0.9443,
|
| 264 |
+
"step": 410
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.09,
|
| 268 |
+
"learning_rate": 9.090909090909092e-05,
|
| 269 |
+
"loss": 0.8547,
|
| 270 |
+
"step": 420
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.12,
|
| 274 |
+
"learning_rate": 8.831168831168831e-05,
|
| 275 |
+
"loss": 0.8672,
|
| 276 |
+
"step": 430
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.14,
|
| 280 |
+
"learning_rate": 8.571428571428571e-05,
|
| 281 |
+
"loss": 0.8914,
|
| 282 |
+
"step": 440
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.17,
|
| 286 |
+
"learning_rate": 8.311688311688312e-05,
|
| 287 |
+
"loss": 0.9796,
|
| 288 |
+
"step": 450
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.19,
|
| 292 |
+
"learning_rate": 8.051948051948052e-05,
|
| 293 |
+
"loss": 0.8171,
|
| 294 |
+
"step": 460
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.22,
|
| 298 |
+
"learning_rate": 7.792207792207793e-05,
|
| 299 |
+
"loss": 0.9133,
|
| 300 |
+
"step": 470
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.25,
|
| 304 |
+
"learning_rate": 7.532467532467533e-05,
|
| 305 |
+
"loss": 0.8922,
|
| 306 |
+
"step": 480
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.27,
|
| 310 |
+
"learning_rate": 7.272727272727273e-05,
|
| 311 |
+
"loss": 0.9447,
|
| 312 |
+
"step": 490
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.3,
|
| 316 |
+
"learning_rate": 7.012987012987014e-05,
|
| 317 |
+
"loss": 0.9278,
|
| 318 |
+
"step": 500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.32,
|
| 322 |
+
"learning_rate": 6.753246753246754e-05,
|
| 323 |
+
"loss": 0.9201,
|
| 324 |
+
"step": 510
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.35,
|
| 328 |
+
"learning_rate": 6.493506493506494e-05,
|
| 329 |
+
"loss": 0.9333,
|
| 330 |
+
"step": 520
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.38,
|
| 334 |
+
"learning_rate": 6.233766233766233e-05,
|
| 335 |
+
"loss": 0.9163,
|
| 336 |
+
"step": 530
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.4,
|
| 340 |
+
"learning_rate": 5.9740259740259744e-05,
|
| 341 |
+
"loss": 0.8924,
|
| 342 |
+
"step": 540
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.43,
|
| 346 |
+
"learning_rate": 5.714285714285714e-05,
|
| 347 |
+
"loss": 0.9369,
|
| 348 |
+
"step": 550
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.45,
|
| 352 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 353 |
+
"loss": 0.8954,
|
| 354 |
+
"step": 560
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.48,
|
| 358 |
+
"learning_rate": 5.1948051948051944e-05,
|
| 359 |
+
"loss": 0.8396,
|
| 360 |
+
"step": 570
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.51,
|
| 364 |
+
"learning_rate": 4.9350649350649355e-05,
|
| 365 |
+
"loss": 0.8785,
|
| 366 |
+
"step": 580
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.53,
|
| 370 |
+
"learning_rate": 4.675324675324675e-05,
|
| 371 |
+
"loss": 0.8982,
|
| 372 |
+
"step": 590
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.56,
|
| 376 |
+
"learning_rate": 4.415584415584416e-05,
|
| 377 |
+
"loss": 0.8245,
|
| 378 |
+
"step": 600
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.58,
|
| 382 |
+
"learning_rate": 4.155844155844156e-05,
|
| 383 |
+
"loss": 0.8395,
|
| 384 |
+
"step": 610
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.61,
|
| 388 |
+
"learning_rate": 3.8961038961038966e-05,
|
| 389 |
+
"loss": 0.8432,
|
| 390 |
+
"step": 620
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.64,
|
| 394 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 395 |
+
"loss": 0.8502,
|
| 396 |
+
"step": 630
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.66,
|
| 400 |
+
"learning_rate": 3.376623376623377e-05,
|
| 401 |
+
"loss": 0.841,
|
| 402 |
+
"step": 640
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.69,
|
| 406 |
+
"learning_rate": 3.1168831168831166e-05,
|
| 407 |
+
"loss": 0.8699,
|
| 408 |
+
"step": 650
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.71,
|
| 412 |
+
"learning_rate": 2.857142857142857e-05,
|
| 413 |
+
"loss": 0.8441,
|
| 414 |
+
"step": 660
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.74,
|
| 418 |
+
"learning_rate": 2.5974025974025972e-05,
|
| 419 |
+
"loss": 0.8556,
|
| 420 |
+
"step": 670
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.77,
|
| 424 |
+
"learning_rate": 2.3376623376623376e-05,
|
| 425 |
+
"loss": 0.8814,
|
| 426 |
+
"step": 680
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.79,
|
| 430 |
+
"learning_rate": 2.077922077922078e-05,
|
| 431 |
+
"loss": 0.96,
|
| 432 |
+
"step": 690
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.82,
|
| 436 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 437 |
+
"loss": 0.8597,
|
| 438 |
+
"step": 700
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.84,
|
| 442 |
+
"learning_rate": 1.5584415584415583e-05,
|
| 443 |
+
"loss": 0.9041,
|
| 444 |
+
"step": 710
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.87,
|
| 448 |
+
"learning_rate": 1.2987012987012986e-05,
|
| 449 |
+
"loss": 0.832,
|
| 450 |
+
"step": 720
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.9,
|
| 454 |
+
"learning_rate": 1.038961038961039e-05,
|
| 455 |
+
"loss": 0.8599,
|
| 456 |
+
"step": 730
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.92,
|
| 460 |
+
"learning_rate": 7.792207792207792e-06,
|
| 461 |
+
"loss": 0.7605,
|
| 462 |
+
"step": 740
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.95,
|
| 466 |
+
"learning_rate": 5.194805194805195e-06,
|
| 467 |
+
"loss": 0.8849,
|
| 468 |
+
"step": 750
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.97,
|
| 472 |
+
"learning_rate": 2.5974025974025976e-06,
|
| 473 |
+
"loss": 0.7527,
|
| 474 |
+
"step": 760
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.0,
|
| 478 |
+
"learning_rate": 0.0,
|
| 479 |
+
"loss": 0.8465,
|
| 480 |
+
"step": 770
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.0,
|
| 484 |
+
"eval_accuracy": 0.7656465622209595,
|
| 485 |
+
"eval_loss": 0.6668800115585327,
|
| 486 |
+
"eval_runtime": 111.2647,
|
| 487 |
+
"eval_samples_per_second": 110.718,
|
| 488 |
+
"eval_steps_per_second": 13.841,
|
| 489 |
+
"step": 770
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.0,
|
| 493 |
+
"step": 770,
|
| 494 |
+
"total_flos": 1.9093674240032072e+18,
|
| 495 |
+
"train_loss": 1.0707446556586724,
|
| 496 |
+
"train_runtime": 668.48,
|
| 497 |
+
"train_samples_per_second": 36.857,
|
| 498 |
+
"train_steps_per_second": 1.152
|
| 499 |
+
}
|
| 500 |
+
],
|
| 501 |
+
"logging_steps": 10,
|
| 502 |
+
"max_steps": 770,
|
| 503 |
+
"num_train_epochs": 2,
|
| 504 |
+
"save_steps": 500,
|
| 505 |
+
"total_flos": 1.9093674240032072e+18,
|
| 506 |
+
"trial_name": null,
|
| 507 |
+
"trial_params": null
|
| 508 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d71937760213e437781f6fe80330fc0491399186fc2a8167835ad5b3fc8cf71d
|
| 3 |
size 4600
|