End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.03,
|
| 3 |
+
"eval_accuracy": 0.9281045751633987,
|
| 4 |
+
"eval_loss": 0.25746384263038635,
|
| 5 |
+
"eval_runtime": 53.448,
|
| 6 |
+
"eval_samples_per_second": 5.725,
|
| 7 |
+
"eval_steps_per_second": 1.441
|
| 8 |
+
}
|
runs/Nov07_00-11-12_7d06be926dc1/events.out.tfevents.1699331583.7d06be926dc1.1599.1
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:a260dc03edbcfeb0449b7ade2bf955295dc5e9bb364cfc9da793289e90afd4a9
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.03,
|
| 3 |
+
"eval_accuracy": 0.9281045751633987,
|
| 4 |
+
"eval_loss": 0.25746384263038635,
|
| 5 |
+
"eval_runtime": 53.448,
|
| 6 |
+
"eval_samples_per_second": 5.725,
|
| 7 |
+
"eval_steps_per_second": 1.441
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,436 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9525423728813559,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-soccer-action-recognitionx/checkpoint-733",
|
| 4 |
+
"epoch": 31.02843386627907,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1376,
|
| 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 |
+
"eval_accuracy": 0.36610169491525424,
|
| 14 |
+
"eval_loss": 1.8151326179504395,
|
| 15 |
+
"eval_runtime": 140.7286,
|
| 16 |
+
"eval_samples_per_second": 2.096,
|
| 17 |
+
"eval_steps_per_second": 0.526,
|
| 18 |
+
"step": 43
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.03,
|
| 22 |
+
"learning_rate": 2.8985507246376814e-05,
|
| 23 |
+
"loss": 1.7589,
|
| 24 |
+
"step": 80
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.03,
|
| 28 |
+
"eval_accuracy": 0.6915254237288135,
|
| 29 |
+
"eval_loss": 0.9133387804031372,
|
| 30 |
+
"eval_runtime": 53.0805,
|
| 31 |
+
"eval_samples_per_second": 5.558,
|
| 32 |
+
"eval_steps_per_second": 1.394,
|
| 33 |
+
"step": 86
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.03,
|
| 37 |
+
"eval_accuracy": 0.7966101694915254,
|
| 38 |
+
"eval_loss": 0.502605676651001,
|
| 39 |
+
"eval_runtime": 51.9943,
|
| 40 |
+
"eval_samples_per_second": 5.674,
|
| 41 |
+
"eval_steps_per_second": 1.423,
|
| 42 |
+
"step": 129
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.02,
|
| 46 |
+
"learning_rate": 4.9111470113085624e-05,
|
| 47 |
+
"loss": 0.5494,
|
| 48 |
+
"step": 160
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.03,
|
| 52 |
+
"eval_accuracy": 0.8677966101694915,
|
| 53 |
+
"eval_loss": 0.3936995267868042,
|
| 54 |
+
"eval_runtime": 51.8695,
|
| 55 |
+
"eval_samples_per_second": 5.687,
|
| 56 |
+
"eval_steps_per_second": 1.427,
|
| 57 |
+
"step": 172
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.03,
|
| 61 |
+
"eval_accuracy": 0.8677966101694915,
|
| 62 |
+
"eval_loss": 0.3942561149597168,
|
| 63 |
+
"eval_runtime": 51.889,
|
| 64 |
+
"eval_samples_per_second": 5.685,
|
| 65 |
+
"eval_steps_per_second": 1.426,
|
| 66 |
+
"step": 215
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.02,
|
| 70 |
+
"learning_rate": 4.588045234248788e-05,
|
| 71 |
+
"loss": 0.2747,
|
| 72 |
+
"step": 240
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.03,
|
| 76 |
+
"eval_accuracy": 0.8677966101694915,
|
| 77 |
+
"eval_loss": 0.38759008049964905,
|
| 78 |
+
"eval_runtime": 51.6207,
|
| 79 |
+
"eval_samples_per_second": 5.715,
|
| 80 |
+
"eval_steps_per_second": 1.434,
|
| 81 |
+
"step": 258
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.03,
|
| 85 |
+
"eval_accuracy": 0.9084745762711864,
|
| 86 |
+
"eval_loss": 0.28025880455970764,
|
| 87 |
+
"eval_runtime": 51.769,
|
| 88 |
+
"eval_samples_per_second": 5.698,
|
| 89 |
+
"eval_steps_per_second": 1.429,
|
| 90 |
+
"step": 301
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 7.01,
|
| 94 |
+
"learning_rate": 4.264943457189014e-05,
|
| 95 |
+
"loss": 0.1731,
|
| 96 |
+
"step": 320
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 7.03,
|
| 100 |
+
"eval_accuracy": 0.911864406779661,
|
| 101 |
+
"eval_loss": 0.24141576886177063,
|
| 102 |
+
"eval_runtime": 51.5882,
|
| 103 |
+
"eval_samples_per_second": 5.718,
|
| 104 |
+
"eval_steps_per_second": 1.434,
|
| 105 |
+
"step": 345
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.03,
|
| 109 |
+
"eval_accuracy": 0.9288135593220339,
|
| 110 |
+
"eval_loss": 0.24339653551578522,
|
| 111 |
+
"eval_runtime": 52.5074,
|
| 112 |
+
"eval_samples_per_second": 5.618,
|
| 113 |
+
"eval_steps_per_second": 1.409,
|
| 114 |
+
"step": 388
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.01,
|
| 118 |
+
"learning_rate": 3.941841680129241e-05,
|
| 119 |
+
"loss": 0.1165,
|
| 120 |
+
"step": 400
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.03,
|
| 124 |
+
"eval_accuracy": 0.9457627118644067,
|
| 125 |
+
"eval_loss": 0.15595699846744537,
|
| 126 |
+
"eval_runtime": 51.5552,
|
| 127 |
+
"eval_samples_per_second": 5.722,
|
| 128 |
+
"eval_steps_per_second": 1.435,
|
| 129 |
+
"step": 431
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 10.03,
|
| 133 |
+
"eval_accuracy": 0.9254237288135593,
|
| 134 |
+
"eval_loss": 0.18938671052455902,
|
| 135 |
+
"eval_runtime": 51.3718,
|
| 136 |
+
"eval_samples_per_second": 5.742,
|
| 137 |
+
"eval_steps_per_second": 1.44,
|
| 138 |
+
"step": 474
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 11.0,
|
| 142 |
+
"learning_rate": 3.618739903069467e-05,
|
| 143 |
+
"loss": 0.07,
|
| 144 |
+
"step": 480
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 11.03,
|
| 148 |
+
"eval_accuracy": 0.9152542372881356,
|
| 149 |
+
"eval_loss": 0.2400982826948166,
|
| 150 |
+
"eval_runtime": 51.1883,
|
| 151 |
+
"eval_samples_per_second": 5.763,
|
| 152 |
+
"eval_steps_per_second": 1.446,
|
| 153 |
+
"step": 517
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 12.03,
|
| 157 |
+
"learning_rate": 3.295638126009693e-05,
|
| 158 |
+
"loss": 0.0417,
|
| 159 |
+
"step": 560
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.03,
|
| 163 |
+
"eval_accuracy": 0.9389830508474576,
|
| 164 |
+
"eval_loss": 0.18834476172924042,
|
| 165 |
+
"eval_runtime": 52.3816,
|
| 166 |
+
"eval_samples_per_second": 5.632,
|
| 167 |
+
"eval_steps_per_second": 1.413,
|
| 168 |
+
"step": 560
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.03,
|
| 172 |
+
"eval_accuracy": 0.9050847457627119,
|
| 173 |
+
"eval_loss": 0.2588905990123749,
|
| 174 |
+
"eval_runtime": 52.3591,
|
| 175 |
+
"eval_samples_per_second": 5.634,
|
| 176 |
+
"eval_steps_per_second": 1.413,
|
| 177 |
+
"step": 603
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 14.03,
|
| 181 |
+
"learning_rate": 2.9725363489499192e-05,
|
| 182 |
+
"loss": 0.0362,
|
| 183 |
+
"step": 640
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.03,
|
| 187 |
+
"eval_accuracy": 0.9491525423728814,
|
| 188 |
+
"eval_loss": 0.2125038504600525,
|
| 189 |
+
"eval_runtime": 52.038,
|
| 190 |
+
"eval_samples_per_second": 5.669,
|
| 191 |
+
"eval_steps_per_second": 1.422,
|
| 192 |
+
"step": 646
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 15.03,
|
| 196 |
+
"eval_accuracy": 0.9389830508474576,
|
| 197 |
+
"eval_loss": 0.22276653349399567,
|
| 198 |
+
"eval_runtime": 52.1385,
|
| 199 |
+
"eval_samples_per_second": 5.658,
|
| 200 |
+
"eval_steps_per_second": 1.419,
|
| 201 |
+
"step": 690
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 16.02,
|
| 205 |
+
"learning_rate": 2.6494345718901455e-05,
|
| 206 |
+
"loss": 0.0348,
|
| 207 |
+
"step": 720
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.03,
|
| 211 |
+
"eval_accuracy": 0.9525423728813559,
|
| 212 |
+
"eval_loss": 0.1796749383211136,
|
| 213 |
+
"eval_runtime": 51.9086,
|
| 214 |
+
"eval_samples_per_second": 5.683,
|
| 215 |
+
"eval_steps_per_second": 1.426,
|
| 216 |
+
"step": 733
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 17.03,
|
| 220 |
+
"eval_accuracy": 0.9389830508474576,
|
| 221 |
+
"eval_loss": 0.17283643782138824,
|
| 222 |
+
"eval_runtime": 54.9977,
|
| 223 |
+
"eval_samples_per_second": 5.364,
|
| 224 |
+
"eval_steps_per_second": 1.346,
|
| 225 |
+
"step": 776
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 18.02,
|
| 229 |
+
"learning_rate": 2.3263327948303717e-05,
|
| 230 |
+
"loss": 0.0129,
|
| 231 |
+
"step": 800
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.03,
|
| 235 |
+
"eval_accuracy": 0.9254237288135593,
|
| 236 |
+
"eval_loss": 0.22526715695858002,
|
| 237 |
+
"eval_runtime": 50.2328,
|
| 238 |
+
"eval_samples_per_second": 5.873,
|
| 239 |
+
"eval_steps_per_second": 1.473,
|
| 240 |
+
"step": 819
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 19.03,
|
| 244 |
+
"eval_accuracy": 0.9355932203389831,
|
| 245 |
+
"eval_loss": 0.1983296275138855,
|
| 246 |
+
"eval_runtime": 51.3454,
|
| 247 |
+
"eval_samples_per_second": 5.745,
|
| 248 |
+
"eval_steps_per_second": 1.441,
|
| 249 |
+
"step": 862
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 20.01,
|
| 253 |
+
"learning_rate": 2.003231017770598e-05,
|
| 254 |
+
"loss": 0.0112,
|
| 255 |
+
"step": 880
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 20.03,
|
| 259 |
+
"eval_accuracy": 0.9220338983050848,
|
| 260 |
+
"eval_loss": 0.28206783533096313,
|
| 261 |
+
"eval_runtime": 51.8364,
|
| 262 |
+
"eval_samples_per_second": 5.691,
|
| 263 |
+
"eval_steps_per_second": 1.428,
|
| 264 |
+
"step": 905
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 21.03,
|
| 268 |
+
"eval_accuracy": 0.9355932203389831,
|
| 269 |
+
"eval_loss": 0.2527361810207367,
|
| 270 |
+
"eval_runtime": 51.2851,
|
| 271 |
+
"eval_samples_per_second": 5.752,
|
| 272 |
+
"eval_steps_per_second": 1.443,
|
| 273 |
+
"step": 948
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 22.01,
|
| 277 |
+
"learning_rate": 1.6801292407108242e-05,
|
| 278 |
+
"loss": 0.0165,
|
| 279 |
+
"step": 960
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 22.03,
|
| 283 |
+
"eval_accuracy": 0.9288135593220339,
|
| 284 |
+
"eval_loss": 0.2598176896572113,
|
| 285 |
+
"eval_runtime": 51.1087,
|
| 286 |
+
"eval_samples_per_second": 5.772,
|
| 287 |
+
"eval_steps_per_second": 1.448,
|
| 288 |
+
"step": 991
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 23.03,
|
| 292 |
+
"eval_accuracy": 0.9288135593220339,
|
| 293 |
+
"eval_loss": 0.2689870595932007,
|
| 294 |
+
"eval_runtime": 52.0484,
|
| 295 |
+
"eval_samples_per_second": 5.668,
|
| 296 |
+
"eval_steps_per_second": 1.422,
|
| 297 |
+
"step": 1035
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 24.0,
|
| 301 |
+
"learning_rate": 1.3570274636510503e-05,
|
| 302 |
+
"loss": 0.0056,
|
| 303 |
+
"step": 1040
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 24.03,
|
| 307 |
+
"eval_accuracy": 0.9220338983050848,
|
| 308 |
+
"eval_loss": 0.2817440629005432,
|
| 309 |
+
"eval_runtime": 50.9874,
|
| 310 |
+
"eval_samples_per_second": 5.786,
|
| 311 |
+
"eval_steps_per_second": 1.451,
|
| 312 |
+
"step": 1078
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 25.03,
|
| 316 |
+
"learning_rate": 1.0339256865912764e-05,
|
| 317 |
+
"loss": 0.0026,
|
| 318 |
+
"step": 1120
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 25.03,
|
| 322 |
+
"eval_accuracy": 0.9423728813559322,
|
| 323 |
+
"eval_loss": 0.2038636952638626,
|
| 324 |
+
"eval_runtime": 51.3576,
|
| 325 |
+
"eval_samples_per_second": 5.744,
|
| 326 |
+
"eval_steps_per_second": 1.441,
|
| 327 |
+
"step": 1121
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 26.03,
|
| 331 |
+
"eval_accuracy": 0.9457627118644067,
|
| 332 |
+
"eval_loss": 0.21635624766349792,
|
| 333 |
+
"eval_runtime": 50.2612,
|
| 334 |
+
"eval_samples_per_second": 5.869,
|
| 335 |
+
"eval_steps_per_second": 1.472,
|
| 336 |
+
"step": 1164
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 27.03,
|
| 340 |
+
"learning_rate": 7.108239095315025e-06,
|
| 341 |
+
"loss": 0.0033,
|
| 342 |
+
"step": 1200
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 27.03,
|
| 346 |
+
"eval_accuracy": 0.9423728813559322,
|
| 347 |
+
"eval_loss": 0.20629702508449554,
|
| 348 |
+
"eval_runtime": 52.4013,
|
| 349 |
+
"eval_samples_per_second": 5.63,
|
| 350 |
+
"eval_steps_per_second": 1.412,
|
| 351 |
+
"step": 1207
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 28.03,
|
| 355 |
+
"eval_accuracy": 0.9525423728813559,
|
| 356 |
+
"eval_loss": 0.18356993794441223,
|
| 357 |
+
"eval_runtime": 51.9433,
|
| 358 |
+
"eval_samples_per_second": 5.679,
|
| 359 |
+
"eval_steps_per_second": 1.425,
|
| 360 |
+
"step": 1250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 29.02,
|
| 364 |
+
"learning_rate": 3.877221324717286e-06,
|
| 365 |
+
"loss": 0.0038,
|
| 366 |
+
"step": 1280
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 29.03,
|
| 370 |
+
"eval_accuracy": 0.9457627118644067,
|
| 371 |
+
"eval_loss": 0.1899212896823883,
|
| 372 |
+
"eval_runtime": 50.6974,
|
| 373 |
+
"eval_samples_per_second": 5.819,
|
| 374 |
+
"eval_steps_per_second": 1.46,
|
| 375 |
+
"step": 1293
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 30.03,
|
| 379 |
+
"eval_accuracy": 0.9491525423728814,
|
| 380 |
+
"eval_loss": 0.18148240447044373,
|
| 381 |
+
"eval_runtime": 51.0875,
|
| 382 |
+
"eval_samples_per_second": 5.774,
|
| 383 |
+
"eval_steps_per_second": 1.448,
|
| 384 |
+
"step": 1336
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 31.02,
|
| 388 |
+
"learning_rate": 6.462035541195477e-07,
|
| 389 |
+
"loss": 0.0024,
|
| 390 |
+
"step": 1360
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 31.03,
|
| 394 |
+
"eval_accuracy": 0.9525423728813559,
|
| 395 |
+
"eval_loss": 0.1816376894712448,
|
| 396 |
+
"eval_runtime": 51.6789,
|
| 397 |
+
"eval_samples_per_second": 5.708,
|
| 398 |
+
"eval_steps_per_second": 1.432,
|
| 399 |
+
"step": 1376
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 31.03,
|
| 403 |
+
"step": 1376,
|
| 404 |
+
"total_flos": 5.4792880339785155e+19,
|
| 405 |
+
"train_loss": 0.18103733560920499,
|
| 406 |
+
"train_runtime": 13691.8843,
|
| 407 |
+
"train_samples_per_second": 3.216,
|
| 408 |
+
"train_steps_per_second": 0.1
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 31.03,
|
| 412 |
+
"eval_accuracy": 0.9281045751633987,
|
| 413 |
+
"eval_loss": 0.25746384263038635,
|
| 414 |
+
"eval_runtime": 158.37,
|
| 415 |
+
"eval_samples_per_second": 1.932,
|
| 416 |
+
"eval_steps_per_second": 0.486,
|
| 417 |
+
"step": 1376
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 31.03,
|
| 421 |
+
"eval_accuracy": 0.9281045751633987,
|
| 422 |
+
"eval_loss": 0.25746384263038635,
|
| 423 |
+
"eval_runtime": 53.448,
|
| 424 |
+
"eval_samples_per_second": 5.725,
|
| 425 |
+
"eval_steps_per_second": 1.441,
|
| 426 |
+
"step": 1376
|
| 427 |
+
}
|
| 428 |
+
],
|
| 429 |
+
"logging_steps": 80,
|
| 430 |
+
"max_steps": 1376,
|
| 431 |
+
"num_train_epochs": 9223372036854775807,
|
| 432 |
+
"save_steps": 500,
|
| 433 |
+
"total_flos": 5.4792880339785155e+19,
|
| 434 |
+
"trial_name": null,
|
| 435 |
+
"trial_params": null
|
| 436 |
+
}
|