End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +378 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.18974358974359,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.005171784199774265,
|
| 5 |
+
"eval_runtime": 47.2902,
|
| 6 |
+
"eval_samples_per_second": 4.166,
|
| 7 |
+
"eval_steps_per_second": 0.211
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.18974358974359,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.005171784199774265,
|
| 5 |
+
"eval_runtime": 47.2902,
|
| 6 |
+
"eval_samples_per_second": 4.166,
|
| 7 |
+
"eval_steps_per_second": 0.211
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,378 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset\\checkpoint-237",
|
| 4 |
+
"epoch": 4.18974358974359,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 390,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02564102564102564,
|
| 13 |
+
"grad_norm": 3.9795846939086914,
|
| 14 |
+
"learning_rate": 1.282051282051282e-05,
|
| 15 |
+
"loss": 1.2941,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05128205128205128,
|
| 20 |
+
"grad_norm": 4.371654510498047,
|
| 21 |
+
"learning_rate": 2.564102564102564e-05,
|
| 22 |
+
"loss": 0.9964,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07692307692307693,
|
| 27 |
+
"grad_norm": 3.8371341228485107,
|
| 28 |
+
"learning_rate": 3.846153846153846e-05,
|
| 29 |
+
"loss": 0.6155,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10256410256410256,
|
| 34 |
+
"grad_norm": 6.883916854858398,
|
| 35 |
+
"learning_rate": 4.985754985754986e-05,
|
| 36 |
+
"loss": 0.2122,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1282051282051282,
|
| 41 |
+
"grad_norm": 0.4472762644290924,
|
| 42 |
+
"learning_rate": 4.8433048433048433e-05,
|
| 43 |
+
"loss": 0.0886,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15384615384615385,
|
| 48 |
+
"grad_norm": 1.2847106456756592,
|
| 49 |
+
"learning_rate": 4.700854700854701e-05,
|
| 50 |
+
"loss": 0.152,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1794871794871795,
|
| 55 |
+
"grad_norm": 2.8317058086395264,
|
| 56 |
+
"learning_rate": 4.558404558404559e-05,
|
| 57 |
+
"loss": 0.1648,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.20256410256410257,
|
| 62 |
+
"eval_accuracy": 0.965,
|
| 63 |
+
"eval_loss": 0.08287694305181503,
|
| 64 |
+
"eval_runtime": 46.4491,
|
| 65 |
+
"eval_samples_per_second": 4.306,
|
| 66 |
+
"eval_steps_per_second": 0.215,
|
| 67 |
+
"step": 79
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.0025641025641026,
|
| 71 |
+
"grad_norm": 0.3571479618549347,
|
| 72 |
+
"learning_rate": 4.415954415954416e-05,
|
| 73 |
+
"loss": 0.0616,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.028205128205128,
|
| 78 |
+
"grad_norm": 0.1090891882777214,
|
| 79 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 80 |
+
"loss": 0.0393,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.0538461538461539,
|
| 85 |
+
"grad_norm": 1.746414065361023,
|
| 86 |
+
"learning_rate": 4.131054131054131e-05,
|
| 87 |
+
"loss": 0.0735,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.0794871794871794,
|
| 92 |
+
"grad_norm": 1.1220694780349731,
|
| 93 |
+
"learning_rate": 3.988603988603989e-05,
|
| 94 |
+
"loss": 0.0842,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.1051282051282052,
|
| 99 |
+
"grad_norm": 0.10681042075157166,
|
| 100 |
+
"learning_rate": 3.846153846153846e-05,
|
| 101 |
+
"loss": 0.0238,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.1307692307692307,
|
| 106 |
+
"grad_norm": 2.7694716453552246,
|
| 107 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 108 |
+
"loss": 0.089,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.1564102564102563,
|
| 113 |
+
"grad_norm": 1.5847387313842773,
|
| 114 |
+
"learning_rate": 3.561253561253561e-05,
|
| 115 |
+
"loss": 0.019,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.182051282051282,
|
| 120 |
+
"grad_norm": 5.06767463684082,
|
| 121 |
+
"learning_rate": 3.418803418803419e-05,
|
| 122 |
+
"loss": 0.0751,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2025641025641025,
|
| 127 |
+
"eval_accuracy": 0.96,
|
| 128 |
+
"eval_loss": 0.07137803733348846,
|
| 129 |
+
"eval_runtime": 45.3454,
|
| 130 |
+
"eval_samples_per_second": 4.411,
|
| 131 |
+
"eval_steps_per_second": 0.221,
|
| 132 |
+
"step": 158
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.005128205128205,
|
| 136 |
+
"grad_norm": 0.07452063262462616,
|
| 137 |
+
"learning_rate": 3.2763532763532764e-05,
|
| 138 |
+
"loss": 0.0373,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.0307692307692307,
|
| 143 |
+
"grad_norm": 0.04081596061587334,
|
| 144 |
+
"learning_rate": 3.133903133903134e-05,
|
| 145 |
+
"loss": 0.0629,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.056410256410256,
|
| 150 |
+
"grad_norm": 0.3062734305858612,
|
| 151 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 152 |
+
"loss": 0.0289,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.082051282051282,
|
| 157 |
+
"grad_norm": 0.08387012779712677,
|
| 158 |
+
"learning_rate": 2.8490028490028492e-05,
|
| 159 |
+
"loss": 0.0287,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.1076923076923078,
|
| 164 |
+
"grad_norm": 0.26985999941825867,
|
| 165 |
+
"learning_rate": 2.706552706552707e-05,
|
| 166 |
+
"loss": 0.0052,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.1333333333333333,
|
| 171 |
+
"grad_norm": 0.11916792392730713,
|
| 172 |
+
"learning_rate": 2.564102564102564e-05,
|
| 173 |
+
"loss": 0.0571,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.158974358974359,
|
| 178 |
+
"grad_norm": 0.18876294791698456,
|
| 179 |
+
"learning_rate": 2.4216524216524217e-05,
|
| 180 |
+
"loss": 0.0347,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.184615384615385,
|
| 185 |
+
"grad_norm": 0.23059749603271484,
|
| 186 |
+
"learning_rate": 2.2792022792022794e-05,
|
| 187 |
+
"loss": 0.03,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.2025641025641027,
|
| 192 |
+
"eval_accuracy": 1.0,
|
| 193 |
+
"eval_loss": 0.007003530394285917,
|
| 194 |
+
"eval_runtime": 44.7765,
|
| 195 |
+
"eval_samples_per_second": 4.467,
|
| 196 |
+
"eval_steps_per_second": 0.223,
|
| 197 |
+
"step": 237
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.0076923076923077,
|
| 201 |
+
"grad_norm": 0.06344188004732132,
|
| 202 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 203 |
+
"loss": 0.005,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.033333333333333,
|
| 208 |
+
"grad_norm": 0.05598565936088562,
|
| 209 |
+
"learning_rate": 1.9943019943019945e-05,
|
| 210 |
+
"loss": 0.0032,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.0589743589743588,
|
| 215 |
+
"grad_norm": 0.05869239196181297,
|
| 216 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 217 |
+
"loss": 0.0211,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.0846153846153848,
|
| 222 |
+
"grad_norm": 0.013849779032170773,
|
| 223 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 224 |
+
"loss": 0.0016,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.1102564102564103,
|
| 229 |
+
"grad_norm": 0.019467826932668686,
|
| 230 |
+
"learning_rate": 1.566951566951567e-05,
|
| 231 |
+
"loss": 0.0018,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.135897435897436,
|
| 236 |
+
"grad_norm": 0.012761811725795269,
|
| 237 |
+
"learning_rate": 1.4245014245014246e-05,
|
| 238 |
+
"loss": 0.0015,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.1615384615384614,
|
| 243 |
+
"grad_norm": 0.026674192398786545,
|
| 244 |
+
"learning_rate": 1.282051282051282e-05,
|
| 245 |
+
"loss": 0.0098,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.1871794871794874,
|
| 250 |
+
"grad_norm": 0.06651380658149719,
|
| 251 |
+
"learning_rate": 1.1396011396011397e-05,
|
| 252 |
+
"loss": 0.0029,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 3.2025641025641027,
|
| 257 |
+
"eval_accuracy": 1.0,
|
| 258 |
+
"eval_loss": 0.0017288248054683208,
|
| 259 |
+
"eval_runtime": 45.3086,
|
| 260 |
+
"eval_samples_per_second": 4.414,
|
| 261 |
+
"eval_steps_per_second": 0.221,
|
| 262 |
+
"step": 316
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.01025641025641,
|
| 266 |
+
"grad_norm": 0.013002458028495312,
|
| 267 |
+
"learning_rate": 9.971509971509972e-06,
|
| 268 |
+
"loss": 0.002,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.035897435897436,
|
| 273 |
+
"grad_norm": 0.014323906041681767,
|
| 274 |
+
"learning_rate": 8.547008547008548e-06,
|
| 275 |
+
"loss": 0.0014,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.061538461538461,
|
| 280 |
+
"grad_norm": 0.05807347595691681,
|
| 281 |
+
"learning_rate": 7.122507122507123e-06,
|
| 282 |
+
"loss": 0.0014,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.087179487179487,
|
| 287 |
+
"grad_norm": 0.013779590837657452,
|
| 288 |
+
"learning_rate": 5.6980056980056985e-06,
|
| 289 |
+
"loss": 0.0021,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.112820512820512,
|
| 294 |
+
"grad_norm": 0.048702094703912735,
|
| 295 |
+
"learning_rate": 4.273504273504274e-06,
|
| 296 |
+
"loss": 0.0013,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.138461538461539,
|
| 301 |
+
"grad_norm": 0.020250266417860985,
|
| 302 |
+
"learning_rate": 2.8490028490028492e-06,
|
| 303 |
+
"loss": 0.0013,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.164102564102564,
|
| 308 |
+
"grad_norm": 0.011229473166167736,
|
| 309 |
+
"learning_rate": 1.4245014245014246e-06,
|
| 310 |
+
"loss": 0.0012,
|
| 311 |
+
"step": 380
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.18974358974359,
|
| 315 |
+
"grad_norm": 0.014126256108283997,
|
| 316 |
+
"learning_rate": 0.0,
|
| 317 |
+
"loss": 0.0012,
|
| 318 |
+
"step": 390
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.18974358974359,
|
| 322 |
+
"eval_accuracy": 1.0,
|
| 323 |
+
"eval_loss": 0.0015335038769990206,
|
| 324 |
+
"eval_runtime": 45.755,
|
| 325 |
+
"eval_samples_per_second": 4.371,
|
| 326 |
+
"eval_steps_per_second": 0.219,
|
| 327 |
+
"step": 390
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.18974358974359,
|
| 331 |
+
"step": 390,
|
| 332 |
+
"total_flos": 9.66963368152793e+18,
|
| 333 |
+
"train_loss": 0.11110094871180944,
|
| 334 |
+
"train_runtime": 2152.4894,
|
| 335 |
+
"train_samples_per_second": 3.624,
|
| 336 |
+
"train_steps_per_second": 0.181
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 4.18974358974359,
|
| 340 |
+
"eval_accuracy": 1.0,
|
| 341 |
+
"eval_loss": 0.005171784199774265,
|
| 342 |
+
"eval_runtime": 49.0405,
|
| 343 |
+
"eval_samples_per_second": 4.017,
|
| 344 |
+
"eval_steps_per_second": 0.204,
|
| 345 |
+
"step": 390
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.18974358974359,
|
| 349 |
+
"eval_accuracy": 1.0,
|
| 350 |
+
"eval_loss": 0.005171784199774265,
|
| 351 |
+
"eval_runtime": 47.2902,
|
| 352 |
+
"eval_samples_per_second": 4.166,
|
| 353 |
+
"eval_steps_per_second": 0.211,
|
| 354 |
+
"step": 390
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 10,
|
| 358 |
+
"max_steps": 390,
|
| 359 |
+
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 9223372036854775807,
|
| 361 |
+
"save_steps": 500,
|
| 362 |
+
"stateful_callbacks": {
|
| 363 |
+
"TrainerControl": {
|
| 364 |
+
"args": {
|
| 365 |
+
"should_epoch_stop": false,
|
| 366 |
+
"should_evaluate": false,
|
| 367 |
+
"should_log": false,
|
| 368 |
+
"should_save": true,
|
| 369 |
+
"should_training_stop": true
|
| 370 |
+
},
|
| 371 |
+
"attributes": {}
|
| 372 |
+
}
|
| 373 |
+
},
|
| 374 |
+
"total_flos": 9.66963368152793e+18,
|
| 375 |
+
"train_batch_size": 20,
|
| 376 |
+
"trial_name": null,
|
| 377 |
+
"trial_params": null
|
| 378 |
+
}
|