Commit
•
0bfb810
1
Parent(s):
3db441f
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.8250355618776671,
|
| 4 |
+
"eval_loss": 0.4995260536670685,
|
| 5 |
+
"eval_runtime": 75.0907,
|
| 6 |
+
"eval_samples_per_second": 18.724,
|
| 7 |
+
"eval_steps_per_second": 2.344,
|
| 8 |
+
"total_flos": 4.6009321944033853e+18,
|
| 9 |
+
"train_loss": 0.9024475538162958,
|
| 10 |
+
"train_runtime": 1330.277,
|
| 11 |
+
"train_samples_per_second": 12.676,
|
| 12 |
+
"train_steps_per_second": 0.395
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"eval_accuracy": 0.8250355618776671,
|
| 4 |
+
"eval_loss": 0.4995260536670685,
|
| 5 |
+
"eval_runtime": 75.0907,
|
| 6 |
+
"eval_samples_per_second": 18.724,
|
| 7 |
+
"eval_steps_per_second": 2.344
|
| 8 |
+
}
|
runs/Feb08_11-37-30_2e1711bee12f/events.out.tfevents.1707393729.2e1711bee12f.4745.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ef9681941633cf1540edc3962f20ee51d60897244786cd3962175baca87703
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.99,
|
| 3 |
+
"total_flos": 4.6009321944033853e+18,
|
| 4 |
+
"train_loss": 0.9024475538162958,
|
| 5 |
+
"train_runtime": 1330.277,
|
| 6 |
+
"train_samples_per_second": 12.676,
|
| 7 |
+
"train_steps_per_second": 0.395
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8250355618776671,
|
| 3 |
+
"best_model_checkpoint": "MRR_image_classification_dit_29_jan-finetuned-eurosat/checkpoint-525",
|
| 4 |
+
"epoch": 2.987197724039829,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 525,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.433962264150944e-06,
|
| 14 |
+
"loss": 2.0011,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 1.8867924528301888e-05,
|
| 20 |
+
"loss": 1.411,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 2.830188679245283e-05,
|
| 26 |
+
"loss": 1.2419,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 3.7735849056603776e-05,
|
| 32 |
+
"loss": 1.24,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.28,
|
| 37 |
+
"learning_rate": 4.716981132075472e-05,
|
| 38 |
+
"loss": 1.1031,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.34,
|
| 43 |
+
"learning_rate": 4.925847457627119e-05,
|
| 44 |
+
"loss": 1.0103,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4,
|
| 49 |
+
"learning_rate": 4.819915254237288e-05,
|
| 50 |
+
"loss": 1.1038,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.46,
|
| 55 |
+
"learning_rate": 4.7139830508474584e-05,
|
| 56 |
+
"loss": 1.1555,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.51,
|
| 61 |
+
"learning_rate": 4.608050847457627e-05,
|
| 62 |
+
"loss": 1.0994,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.57,
|
| 67 |
+
"learning_rate": 4.502118644067797e-05,
|
| 68 |
+
"loss": 1.1303,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.63,
|
| 73 |
+
"learning_rate": 4.396186440677966e-05,
|
| 74 |
+
"loss": 1.0542,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.68,
|
| 79 |
+
"learning_rate": 4.290254237288136e-05,
|
| 80 |
+
"loss": 1.0717,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.74,
|
| 85 |
+
"learning_rate": 4.1843220338983054e-05,
|
| 86 |
+
"loss": 1.0289,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8,
|
| 91 |
+
"learning_rate": 4.078389830508475e-05,
|
| 92 |
+
"loss": 0.9717,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.85,
|
| 97 |
+
"learning_rate": 3.9724576271186445e-05,
|
| 98 |
+
"loss": 0.9926,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.91,
|
| 103 |
+
"learning_rate": 3.866525423728814e-05,
|
| 104 |
+
"loss": 0.9859,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.97,
|
| 109 |
+
"learning_rate": 3.7605932203389835e-05,
|
| 110 |
+
"loss": 1.0588,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.0,
|
| 115 |
+
"eval_accuracy": 0.6621621621621622,
|
| 116 |
+
"eval_loss": 0.8930806517601013,
|
| 117 |
+
"eval_runtime": 59.7101,
|
| 118 |
+
"eval_samples_per_second": 23.547,
|
| 119 |
+
"eval_steps_per_second": 2.948,
|
| 120 |
+
"step": 175
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.02,
|
| 124 |
+
"learning_rate": 3.654661016949153e-05,
|
| 125 |
+
"loss": 0.9578,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.08,
|
| 130 |
+
"learning_rate": 3.548728813559322e-05,
|
| 131 |
+
"loss": 0.9455,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.14,
|
| 136 |
+
"learning_rate": 3.442796610169492e-05,
|
| 137 |
+
"loss": 0.9959,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.19,
|
| 142 |
+
"learning_rate": 3.336864406779661e-05,
|
| 143 |
+
"loss": 0.9689,
|
| 144 |
+
"step": 210
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.25,
|
| 148 |
+
"learning_rate": 3.230932203389831e-05,
|
| 149 |
+
"loss": 0.9743,
|
| 150 |
+
"step": 220
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.31,
|
| 154 |
+
"learning_rate": 3.125e-05,
|
| 155 |
+
"loss": 0.8971,
|
| 156 |
+
"step": 230
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.37,
|
| 160 |
+
"learning_rate": 3.0190677966101693e-05,
|
| 161 |
+
"loss": 0.8917,
|
| 162 |
+
"step": 240
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.42,
|
| 166 |
+
"learning_rate": 2.913135593220339e-05,
|
| 167 |
+
"loss": 0.7242,
|
| 168 |
+
"step": 250
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.48,
|
| 172 |
+
"learning_rate": 2.8072033898305083e-05,
|
| 173 |
+
"loss": 0.9562,
|
| 174 |
+
"step": 260
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.54,
|
| 178 |
+
"learning_rate": 2.7012711864406782e-05,
|
| 179 |
+
"loss": 0.8342,
|
| 180 |
+
"step": 270
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.59,
|
| 184 |
+
"learning_rate": 2.5953389830508474e-05,
|
| 185 |
+
"loss": 0.8166,
|
| 186 |
+
"step": 280
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.65,
|
| 190 |
+
"learning_rate": 2.489406779661017e-05,
|
| 191 |
+
"loss": 0.829,
|
| 192 |
+
"step": 290
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.71,
|
| 196 |
+
"learning_rate": 2.3834745762711865e-05,
|
| 197 |
+
"loss": 0.7821,
|
| 198 |
+
"step": 300
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.76,
|
| 202 |
+
"learning_rate": 2.277542372881356e-05,
|
| 203 |
+
"loss": 0.8847,
|
| 204 |
+
"step": 310
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.82,
|
| 208 |
+
"learning_rate": 2.1716101694915255e-05,
|
| 209 |
+
"loss": 0.7451,
|
| 210 |
+
"step": 320
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.88,
|
| 214 |
+
"learning_rate": 2.065677966101695e-05,
|
| 215 |
+
"loss": 0.7431,
|
| 216 |
+
"step": 330
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.93,
|
| 220 |
+
"learning_rate": 1.9597457627118646e-05,
|
| 221 |
+
"loss": 0.7861,
|
| 222 |
+
"step": 340
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.99,
|
| 226 |
+
"learning_rate": 1.853813559322034e-05,
|
| 227 |
+
"loss": 0.7206,
|
| 228 |
+
"step": 350
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.0,
|
| 232 |
+
"eval_accuracy": 0.7773826458036984,
|
| 233 |
+
"eval_loss": 0.6266400218009949,
|
| 234 |
+
"eval_runtime": 57.5992,
|
| 235 |
+
"eval_samples_per_second": 24.41,
|
| 236 |
+
"eval_steps_per_second": 3.056,
|
| 237 |
+
"step": 351
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.05,
|
| 241 |
+
"learning_rate": 1.7478813559322037e-05,
|
| 242 |
+
"loss": 0.6948,
|
| 243 |
+
"step": 360
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.11,
|
| 247 |
+
"learning_rate": 1.641949152542373e-05,
|
| 248 |
+
"loss": 0.7623,
|
| 249 |
+
"step": 370
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.16,
|
| 253 |
+
"learning_rate": 1.5360169491525424e-05,
|
| 254 |
+
"loss": 0.6679,
|
| 255 |
+
"step": 380
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.22,
|
| 259 |
+
"learning_rate": 1.430084745762712e-05,
|
| 260 |
+
"loss": 0.623,
|
| 261 |
+
"step": 390
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.28,
|
| 265 |
+
"learning_rate": 1.3241525423728815e-05,
|
| 266 |
+
"loss": 0.7125,
|
| 267 |
+
"step": 400
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.33,
|
| 271 |
+
"learning_rate": 1.2182203389830509e-05,
|
| 272 |
+
"loss": 0.8716,
|
| 273 |
+
"step": 410
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.39,
|
| 277 |
+
"learning_rate": 1.1122881355932204e-05,
|
| 278 |
+
"loss": 0.7073,
|
| 279 |
+
"step": 420
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.45,
|
| 283 |
+
"learning_rate": 1.0063559322033898e-05,
|
| 284 |
+
"loss": 0.722,
|
| 285 |
+
"step": 430
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.5,
|
| 289 |
+
"learning_rate": 9.004237288135593e-06,
|
| 290 |
+
"loss": 0.733,
|
| 291 |
+
"step": 440
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.56,
|
| 295 |
+
"learning_rate": 7.944915254237288e-06,
|
| 296 |
+
"loss": 0.6861,
|
| 297 |
+
"step": 450
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.62,
|
| 301 |
+
"learning_rate": 6.885593220338983e-06,
|
| 302 |
+
"loss": 0.6785,
|
| 303 |
+
"step": 460
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.67,
|
| 307 |
+
"learning_rate": 5.826271186440678e-06,
|
| 308 |
+
"loss": 0.71,
|
| 309 |
+
"step": 470
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.73,
|
| 313 |
+
"learning_rate": 4.766949152542373e-06,
|
| 314 |
+
"loss": 0.6091,
|
| 315 |
+
"step": 480
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.79,
|
| 319 |
+
"learning_rate": 3.707627118644068e-06,
|
| 320 |
+
"loss": 0.754,
|
| 321 |
+
"step": 490
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.84,
|
| 325 |
+
"learning_rate": 2.648305084745763e-06,
|
| 326 |
+
"loss": 0.6406,
|
| 327 |
+
"step": 500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.9,
|
| 331 |
+
"learning_rate": 1.5889830508474576e-06,
|
| 332 |
+
"loss": 0.6826,
|
| 333 |
+
"step": 510
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.96,
|
| 337 |
+
"learning_rate": 5.296610169491525e-07,
|
| 338 |
+
"loss": 0.6833,
|
| 339 |
+
"step": 520
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.99,
|
| 343 |
+
"eval_accuracy": 0.8250355618776671,
|
| 344 |
+
"eval_loss": 0.4995260536670685,
|
| 345 |
+
"eval_runtime": 58.3941,
|
| 346 |
+
"eval_samples_per_second": 24.078,
|
| 347 |
+
"eval_steps_per_second": 3.014,
|
| 348 |
+
"step": 525
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.99,
|
| 352 |
+
"step": 525,
|
| 353 |
+
"total_flos": 4.6009321944033853e+18,
|
| 354 |
+
"train_loss": 0.9024475538162958,
|
| 355 |
+
"train_runtime": 1330.277,
|
| 356 |
+
"train_samples_per_second": 12.676,
|
| 357 |
+
"train_steps_per_second": 0.395
|
| 358 |
+
}
|
| 359 |
+
],
|
| 360 |
+
"logging_steps": 10,
|
| 361 |
+
"max_steps": 525,
|
| 362 |
+
"num_input_tokens_seen": 0,
|
| 363 |
+
"num_train_epochs": 3,
|
| 364 |
+
"save_steps": 500,
|
| 365 |
+
"total_flos": 4.6009321944033853e+18,
|
| 366 |
+
"train_batch_size": 8,
|
| 367 |
+
"trial_name": null,
|
| 368 |
+
"trial_params": null
|
| 369 |
+
}
|