🍻 cheers
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9870689655172413,
|
| 4 |
+
"eval_loss": 0.042032137513160706,
|
| 5 |
+
"eval_runtime": 13.1494,
|
| 6 |
+
"eval_samples_per_second": 158.791,
|
| 7 |
+
"eval_steps_per_second": 19.849,
|
| 8 |
+
"total_flos": 3.450110813048955e+18,
|
| 9 |
+
"train_loss": 0.08533312985138304,
|
| 10 |
+
"train_runtime": 324.7828,
|
| 11 |
+
"train_samples_per_second": 137.138,
|
| 12 |
+
"train_steps_per_second": 1.071
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9870689655172413,
|
| 4 |
+
"eval_loss": 0.042032137513160706,
|
| 5 |
+
"eval_runtime": 13.1494,
|
| 6 |
+
"eval_samples_per_second": 158.791,
|
| 7 |
+
"eval_steps_per_second": 19.849
|
| 8 |
+
}
|
runs/Nov18_18-36-37_db1ae2342b0f/events.out.tfevents.1668797402.db1ae2342b0f.1025.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b0ed8ea0e8b0b4e7e780a992004fc0a175f886df885540732fbda699a2f4d43
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 3.450110813048955e+18,
|
| 4 |
+
"train_loss": 0.08533312985138304,
|
| 5 |
+
"train_runtime": 324.7828,
|
| 6 |
+
"train_samples_per_second": 137.138,
|
| 7 |
+
"train_steps_per_second": 1.071
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.042032137513160706,
|
| 3 |
+
"best_model_checkpoint": "./beit-base-ches-demo-v0/checkpoint-300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 348,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 0.00019540229885057472,
|
| 13 |
+
"loss": 0.9259,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.23,
|
| 18 |
+
"learning_rate": 0.00019022988505747128,
|
| 19 |
+
"loss": 0.384,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.34,
|
| 24 |
+
"learning_rate": 0.00018448275862068968,
|
| 25 |
+
"loss": 0.1864,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.46,
|
| 30 |
+
"learning_rate": 0.00017873563218390805,
|
| 31 |
+
"loss": 0.1273,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.57,
|
| 36 |
+
"learning_rate": 0.00017298850574712645,
|
| 37 |
+
"loss": 0.1345,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.69,
|
| 42 |
+
"learning_rate": 0.00016724137931034482,
|
| 43 |
+
"loss": 0.1201,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8,
|
| 48 |
+
"learning_rate": 0.00016149425287356324,
|
| 49 |
+
"loss": 0.1063,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.92,
|
| 54 |
+
"learning_rate": 0.00015574712643678162,
|
| 55 |
+
"loss": 0.1019,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.03,
|
| 60 |
+
"learning_rate": 0.00015000000000000001,
|
| 61 |
+
"loss": 0.0904,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.15,
|
| 66 |
+
"learning_rate": 0.00014425287356321839,
|
| 67 |
+
"loss": 0.0526,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.26,
|
| 72 |
+
"learning_rate": 0.00013850574712643678,
|
| 73 |
+
"loss": 0.0761,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.38,
|
| 78 |
+
"learning_rate": 0.00013275862068965518,
|
| 79 |
+
"loss": 0.0569,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.49,
|
| 84 |
+
"learning_rate": 0.00012701149425287358,
|
| 85 |
+
"loss": 0.064,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.61,
|
| 90 |
+
"learning_rate": 0.00012126436781609197,
|
| 91 |
+
"loss": 0.0463,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.72,
|
| 96 |
+
"learning_rate": 0.00011551724137931035,
|
| 97 |
+
"loss": 0.0657,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.84,
|
| 102 |
+
"learning_rate": 0.00010977011494252874,
|
| 103 |
+
"loss": 0.0571,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.95,
|
| 108 |
+
"learning_rate": 0.00010402298850574712,
|
| 109 |
+
"loss": 0.0481,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.07,
|
| 114 |
+
"learning_rate": 9.827586206896552e-05,
|
| 115 |
+
"loss": 0.0474,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.18,
|
| 120 |
+
"learning_rate": 9.252873563218392e-05,
|
| 121 |
+
"loss": 0.0173,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.3,
|
| 126 |
+
"learning_rate": 8.67816091954023e-05,
|
| 127 |
+
"loss": 0.0284,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.41,
|
| 132 |
+
"learning_rate": 8.103448275862069e-05,
|
| 133 |
+
"loss": 0.0322,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.53,
|
| 138 |
+
"learning_rate": 7.528735632183909e-05,
|
| 139 |
+
"loss": 0.0288,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.64,
|
| 144 |
+
"learning_rate": 6.954022988505747e-05,
|
| 145 |
+
"loss": 0.0165,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.76,
|
| 150 |
+
"learning_rate": 6.379310344827587e-05,
|
| 151 |
+
"loss": 0.0251,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.87,
|
| 156 |
+
"learning_rate": 5.8045977011494254e-05,
|
| 157 |
+
"loss": 0.0256,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.99,
|
| 162 |
+
"learning_rate": 5.2298850574712646e-05,
|
| 163 |
+
"loss": 0.0271,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.1,
|
| 168 |
+
"learning_rate": 4.655172413793104e-05,
|
| 169 |
+
"loss": 0.0115,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.22,
|
| 174 |
+
"learning_rate": 4.080459770114943e-05,
|
| 175 |
+
"loss": 0.0084,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.33,
|
| 180 |
+
"learning_rate": 3.505747126436782e-05,
|
| 181 |
+
"loss": 0.0049,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.45,
|
| 186 |
+
"learning_rate": 2.9310344827586206e-05,
|
| 187 |
+
"loss": 0.0183,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.45,
|
| 192 |
+
"eval_accuracy": 0.9870689655172413,
|
| 193 |
+
"eval_loss": 0.042032137513160706,
|
| 194 |
+
"eval_runtime": 12.8713,
|
| 195 |
+
"eval_samples_per_second": 162.221,
|
| 196 |
+
"eval_steps_per_second": 20.278,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.56,
|
| 201 |
+
"learning_rate": 2.3563218390804597e-05,
|
| 202 |
+
"loss": 0.0096,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.68,
|
| 207 |
+
"learning_rate": 1.781609195402299e-05,
|
| 208 |
+
"loss": 0.0138,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.79,
|
| 213 |
+
"learning_rate": 1.206896551724138e-05,
|
| 214 |
+
"loss": 0.003,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.91,
|
| 219 |
+
"learning_rate": 6.321839080459771e-06,
|
| 220 |
+
"loss": 0.0037,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.0,
|
| 225 |
+
"step": 348,
|
| 226 |
+
"total_flos": 3.450110813048955e+18,
|
| 227 |
+
"train_loss": 0.08533312985138304,
|
| 228 |
+
"train_runtime": 324.7828,
|
| 229 |
+
"train_samples_per_second": 137.138,
|
| 230 |
+
"train_steps_per_second": 1.071
|
| 231 |
+
}
|
| 232 |
+
],
|
| 233 |
+
"max_steps": 348,
|
| 234 |
+
"num_train_epochs": 4,
|
| 235 |
+
"total_flos": 3.450110813048955e+18,
|
| 236 |
+
"trial_name": null,
|
| 237 |
+
"trial_params": null
|
| 238 |
+
}
|