Commit
·
f4fe17e
1
Parent(s):
637556f
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6685789938217123,
|
| 4 |
+
"eval_loss": 1.0471274852752686,
|
| 5 |
+
"eval_runtime": 21.7503,
|
| 6 |
+
"eval_samples_per_second": 312.548,
|
| 7 |
+
"eval_steps_per_second": 1.241,
|
| 8 |
+
"train_loss": 1.1438689880371093,
|
| 9 |
+
"train_runtime": 2860.7533,
|
| 10 |
+
"train_samples_per_second": 178.603,
|
| 11 |
+
"train_steps_per_second": 0.175
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.6685789938217123,
|
| 4 |
+
"eval_loss": 1.0471274852752686,
|
| 5 |
+
"eval_runtime": 21.7503,
|
| 6 |
+
"eval_samples_per_second": 312.548,
|
| 7 |
+
"eval_steps_per_second": 1.241
|
| 8 |
+
}
|
runs/Aug16_05-14-19_e12ecbd07f82/events.out.tfevents.1660629880.e12ecbd07f82.23426.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e58e20866c9d6973b33c0da1a16b1b98408e2633170b1eab17702ca1a14756
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.1438689880371093,
|
| 4 |
+
"train_runtime": 2860.7533,
|
| 5 |
+
"train_samples_per_second": 178.603,
|
| 6 |
+
"train_steps_per_second": 0.175
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,415 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6685789938217123,
|
| 3 |
+
"best_model_checkpoint": "wav2vec2-base-ks-linear_lrX10/checkpoint-500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.2,
|
| 12 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 13 |
+
"loss": 2.4812,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.4,
|
| 18 |
+
"learning_rate": 0.00011999999999999999,
|
| 19 |
+
"loss": 2.3934,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.6,
|
| 24 |
+
"learning_rate": 0.00017999999999999998,
|
| 25 |
+
"loss": 2.2123,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.8,
|
| 30 |
+
"learning_rate": 0.00023999999999999998,
|
| 31 |
+
"loss": 1.9247,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"learning_rate": 0.0003,
|
| 37 |
+
"loss": 1.6226,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_accuracy": 0.6209179170344219,
|
| 43 |
+
"eval_loss": 1.7588366270065308,
|
| 44 |
+
"eval_runtime": 21.5252,
|
| 45 |
+
"eval_samples_per_second": 315.815,
|
| 46 |
+
"eval_steps_per_second": 1.254,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.2,
|
| 51 |
+
"learning_rate": 0.00029333333333333327,
|
| 52 |
+
"loss": 1.5341,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.4,
|
| 57 |
+
"learning_rate": 0.0002866666666666667,
|
| 58 |
+
"loss": 1.4827,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.6,
|
| 63 |
+
"learning_rate": 0.00028,
|
| 64 |
+
"loss": 1.4304,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.8,
|
| 69 |
+
"learning_rate": 0.00027333333333333333,
|
| 70 |
+
"loss": 1.4002,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.0,
|
| 75 |
+
"learning_rate": 0.0002666666666666666,
|
| 76 |
+
"loss": 1.382,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.0,
|
| 81 |
+
"eval_accuracy": 0.6209179170344219,
|
| 82 |
+
"eval_loss": 1.5695877075195312,
|
| 83 |
+
"eval_runtime": 21.5764,
|
| 84 |
+
"eval_samples_per_second": 315.067,
|
| 85 |
+
"eval_steps_per_second": 1.251,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.2,
|
| 90 |
+
"learning_rate": 0.00026,
|
| 91 |
+
"loss": 1.3576,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.4,
|
| 96 |
+
"learning_rate": 0.00025333333333333333,
|
| 97 |
+
"loss": 1.311,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.6,
|
| 102 |
+
"learning_rate": 0.0002466666666666666,
|
| 103 |
+
"loss": 1.2804,
|
| 104 |
+
"step": 130
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.8,
|
| 108 |
+
"learning_rate": 0.00023999999999999998,
|
| 109 |
+
"loss": 1.2763,
|
| 110 |
+
"step": 140
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.0,
|
| 114 |
+
"learning_rate": 0.0002333333333333333,
|
| 115 |
+
"loss": 1.2373,
|
| 116 |
+
"step": 150
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_accuracy": 0.6212121212121212,
|
| 121 |
+
"eval_loss": 1.3818469047546387,
|
| 122 |
+
"eval_runtime": 21.615,
|
| 123 |
+
"eval_samples_per_second": 314.503,
|
| 124 |
+
"eval_steps_per_second": 1.249,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.2,
|
| 129 |
+
"learning_rate": 0.00022666666666666663,
|
| 130 |
+
"loss": 1.2093,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 3.4,
|
| 135 |
+
"learning_rate": 0.00021999999999999995,
|
| 136 |
+
"loss": 1.1755,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.6,
|
| 141 |
+
"learning_rate": 0.00021333333333333333,
|
| 142 |
+
"loss": 1.1348,
|
| 143 |
+
"step": 180
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.8,
|
| 147 |
+
"learning_rate": 0.00020666666666666666,
|
| 148 |
+
"loss": 1.1384,
|
| 149 |
+
"step": 190
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.0,
|
| 153 |
+
"learning_rate": 0.00019999999999999998,
|
| 154 |
+
"loss": 1.1019,
|
| 155 |
+
"step": 200
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 4.0,
|
| 159 |
+
"eval_accuracy": 0.6228302441894675,
|
| 160 |
+
"eval_loss": 1.2576569318771362,
|
| 161 |
+
"eval_runtime": 21.6992,
|
| 162 |
+
"eval_samples_per_second": 313.284,
|
| 163 |
+
"eval_steps_per_second": 1.244,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.2,
|
| 168 |
+
"learning_rate": 0.00019333333333333333,
|
| 169 |
+
"loss": 1.0917,
|
| 170 |
+
"step": 210
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 4.4,
|
| 174 |
+
"learning_rate": 0.00018666666666666666,
|
| 175 |
+
"loss": 1.0561,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 4.6,
|
| 180 |
+
"learning_rate": 0.00017999999999999998,
|
| 181 |
+
"loss": 1.0332,
|
| 182 |
+
"step": 230
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 4.8,
|
| 186 |
+
"learning_rate": 0.0001733333333333333,
|
| 187 |
+
"loss": 1.0284,
|
| 188 |
+
"step": 240
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.0,
|
| 192 |
+
"learning_rate": 0.00016666666666666666,
|
| 193 |
+
"loss": 0.9831,
|
| 194 |
+
"step": 250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.0,
|
| 198 |
+
"eval_accuracy": 0.6331273904089438,
|
| 199 |
+
"eval_loss": 1.182599663734436,
|
| 200 |
+
"eval_runtime": 21.7405,
|
| 201 |
+
"eval_samples_per_second": 312.688,
|
| 202 |
+
"eval_steps_per_second": 1.242,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.2,
|
| 207 |
+
"learning_rate": 0.00015999999999999999,
|
| 208 |
+
"loss": 0.9864,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.4,
|
| 213 |
+
"learning_rate": 0.0001533333333333333,
|
| 214 |
+
"loss": 0.9584,
|
| 215 |
+
"step": 270
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.6,
|
| 219 |
+
"learning_rate": 0.00014666666666666664,
|
| 220 |
+
"loss": 0.978,
|
| 221 |
+
"step": 280
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 5.8,
|
| 225 |
+
"learning_rate": 0.00014,
|
| 226 |
+
"loss": 0.9272,
|
| 227 |
+
"step": 290
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 6.0,
|
| 231 |
+
"learning_rate": 0.0001333333333333333,
|
| 232 |
+
"loss": 0.9241,
|
| 233 |
+
"step": 300
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.0,
|
| 237 |
+
"eval_accuracy": 0.6481318034716093,
|
| 238 |
+
"eval_loss": 1.120007038116455,
|
| 239 |
+
"eval_runtime": 21.7093,
|
| 240 |
+
"eval_samples_per_second": 313.138,
|
| 241 |
+
"eval_steps_per_second": 1.244,
|
| 242 |
+
"step": 300
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 6.2,
|
| 246 |
+
"learning_rate": 0.00012666666666666666,
|
| 247 |
+
"loss": 0.9326,
|
| 248 |
+
"step": 310
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.4,
|
| 252 |
+
"learning_rate": 0.00011999999999999999,
|
| 253 |
+
"loss": 0.9032,
|
| 254 |
+
"step": 320
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.6,
|
| 258 |
+
"learning_rate": 0.00011333333333333331,
|
| 259 |
+
"loss": 0.8962,
|
| 260 |
+
"step": 330
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 6.8,
|
| 264 |
+
"learning_rate": 0.00010666666666666667,
|
| 265 |
+
"loss": 0.8878,
|
| 266 |
+
"step": 340
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 7.0,
|
| 270 |
+
"learning_rate": 9.999999999999999e-05,
|
| 271 |
+
"loss": 0.8695,
|
| 272 |
+
"step": 350
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 7.0,
|
| 276 |
+
"eval_accuracy": 0.6581347455133862,
|
| 277 |
+
"eval_loss": 1.0821330547332764,
|
| 278 |
+
"eval_runtime": 21.7517,
|
| 279 |
+
"eval_samples_per_second": 312.527,
|
| 280 |
+
"eval_steps_per_second": 1.241,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.2,
|
| 285 |
+
"learning_rate": 9.333333333333333e-05,
|
| 286 |
+
"loss": 0.8749,
|
| 287 |
+
"step": 360
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.4,
|
| 291 |
+
"learning_rate": 8.666666666666665e-05,
|
| 292 |
+
"loss": 0.8742,
|
| 293 |
+
"step": 370
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 7.6,
|
| 297 |
+
"learning_rate": 7.999999999999999e-05,
|
| 298 |
+
"loss": 0.8536,
|
| 299 |
+
"step": 380
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 7.8,
|
| 303 |
+
"learning_rate": 7.333333333333332e-05,
|
| 304 |
+
"loss": 0.8575,
|
| 305 |
+
"step": 390
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 8.0,
|
| 309 |
+
"learning_rate": 6.666666666666666e-05,
|
| 310 |
+
"loss": 0.8529,
|
| 311 |
+
"step": 400
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 8.0,
|
| 315 |
+
"eval_accuracy": 0.66519564577817,
|
| 316 |
+
"eval_loss": 1.0631604194641113,
|
| 317 |
+
"eval_runtime": 21.7691,
|
| 318 |
+
"eval_samples_per_second": 312.277,
|
| 319 |
+
"eval_steps_per_second": 1.24,
|
| 320 |
+
"step": 400
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 8.2,
|
| 324 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 325 |
+
"loss": 0.8466,
|
| 326 |
+
"step": 410
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 8.4,
|
| 330 |
+
"learning_rate": 5.333333333333333e-05,
|
| 331 |
+
"loss": 0.8515,
|
| 332 |
+
"step": 420
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 8.6,
|
| 336 |
+
"learning_rate": 4.6666666666666665e-05,
|
| 337 |
+
"loss": 0.8432,
|
| 338 |
+
"step": 430
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 8.8,
|
| 342 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 343 |
+
"loss": 0.823,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 9.0,
|
| 348 |
+
"learning_rate": 3.333333333333333e-05,
|
| 349 |
+
"loss": 0.8385,
|
| 350 |
+
"step": 450
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 9.0,
|
| 354 |
+
"eval_accuracy": 0.6676963812886143,
|
| 355 |
+
"eval_loss": 1.0494288206100464,
|
| 356 |
+
"eval_runtime": 21.67,
|
| 357 |
+
"eval_samples_per_second": 313.706,
|
| 358 |
+
"eval_steps_per_second": 1.246,
|
| 359 |
+
"step": 450
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.2,
|
| 363 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 364 |
+
"loss": 0.842,
|
| 365 |
+
"step": 460
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 9.4,
|
| 369 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 370 |
+
"loss": 0.8235,
|
| 371 |
+
"step": 470
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 9.6,
|
| 375 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 376 |
+
"loss": 0.8233,
|
| 377 |
+
"step": 480
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 9.8,
|
| 381 |
+
"learning_rate": 6.666666666666667e-06,
|
| 382 |
+
"loss": 0.8304,
|
| 383 |
+
"step": 490
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 10.0,
|
| 387 |
+
"learning_rate": 0.0,
|
| 388 |
+
"loss": 0.8162,
|
| 389 |
+
"step": 500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 10.0,
|
| 393 |
+
"eval_accuracy": 0.6685789938217123,
|
| 394 |
+
"eval_loss": 1.0471274852752686,
|
| 395 |
+
"eval_runtime": 21.6937,
|
| 396 |
+
"eval_samples_per_second": 313.363,
|
| 397 |
+
"eval_steps_per_second": 1.245,
|
| 398 |
+
"step": 500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 10.0,
|
| 402 |
+
"step": 500,
|
| 403 |
+
"total_flos": 4.6387626201984e+18,
|
| 404 |
+
"train_loss": 1.1438689880371093,
|
| 405 |
+
"train_runtime": 2860.7533,
|
| 406 |
+
"train_samples_per_second": 178.603,
|
| 407 |
+
"train_steps_per_second": 0.175
|
| 408 |
+
}
|
| 409 |
+
],
|
| 410 |
+
"max_steps": 500,
|
| 411 |
+
"num_train_epochs": 10,
|
| 412 |
+
"total_flos": 4.6387626201984e+18,
|
| 413 |
+
"trial_name": null,
|
| 414 |
+
"trial_params": null
|
| 415 |
+
}
|