Commit
·
ece26ca
1
Parent(s):
bd158a9
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4,
|
| 3 |
+
"eval_loss": 0.21794496476650238,
|
| 4 |
+
"eval_runtime": 2939.0002,
|
| 5 |
+
"eval_samples_per_second": 3.277,
|
| 6 |
+
"eval_steps_per_second": 0.205,
|
| 7 |
+
"eval_wer": 12.883608587437623,
|
| 8 |
+
"train_loss": 0.15691602289676665,
|
| 9 |
+
"train_runtime": 6554.2706,
|
| 10 |
+
"train_samples_per_second": 4.882,
|
| 11 |
+
"train_steps_per_second": 0.153
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4,
|
| 3 |
+
"eval_loss": 0.21794496476650238,
|
| 4 |
+
"eval_runtime": 2939.0002,
|
| 5 |
+
"eval_samples_per_second": 3.277,
|
| 6 |
+
"eval_steps_per_second": 0.205,
|
| 7 |
+
"eval_wer": 12.883608587437623
|
| 8 |
+
}
|
runs/Dec12_03-07-20_150-136-46-204/events.out.tfevents.1670823986.150-136-46-204.2773299.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1695e3ae3be9e2df5c6221d840910ff215f09be0939858f87cdc22630727cf6
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.4,
|
| 3 |
+
"train_loss": 0.15691602289676665,
|
| 4 |
+
"train_runtime": 6554.2706,
|
| 5 |
+
"train_samples_per_second": 4.882,
|
| 6 |
+
"train_steps_per_second": 0.153
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.3980000000000001,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.4e-06,
|
| 13 |
+
"loss": 0.6563,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 9.4e-06,
|
| 19 |
+
"loss": 0.303,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1e-05,
|
| 25 |
+
"loss": 0.2222,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 1e-05,
|
| 31 |
+
"loss": 0.2058,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 1e-05,
|
| 37 |
+
"loss": 0.2137,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.209,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 1e-05,
|
| 49 |
+
"loss": 0.1859,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 1e-05,
|
| 55 |
+
"loss": 0.1716,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 1e-05,
|
| 61 |
+
"loss": 0.1746,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 1e-05,
|
| 67 |
+
"loss": 0.1996,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.28,
|
| 72 |
+
"learning_rate": 1e-05,
|
| 73 |
+
"loss": 0.192,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.3,
|
| 78 |
+
"learning_rate": 1e-05,
|
| 79 |
+
"loss": 0.1707,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.33,
|
| 84 |
+
"learning_rate": 1e-05,
|
| 85 |
+
"loss": 0.1824,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.35,
|
| 90 |
+
"learning_rate": 1e-05,
|
| 91 |
+
"loss": 0.1671,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.38,
|
| 96 |
+
"learning_rate": 1e-05,
|
| 97 |
+
"loss": 0.1401,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.4,
|
| 102 |
+
"learning_rate": 1e-05,
|
| 103 |
+
"loss": 0.1568,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.42,
|
| 108 |
+
"learning_rate": 1e-05,
|
| 109 |
+
"loss": 0.1499,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.45,
|
| 114 |
+
"learning_rate": 1e-05,
|
| 115 |
+
"loss": 0.1665,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.47,
|
| 120 |
+
"learning_rate": 1e-05,
|
| 121 |
+
"loss": 0.1882,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.5,
|
| 126 |
+
"learning_rate": 1e-05,
|
| 127 |
+
"loss": 0.1995,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.53,
|
| 132 |
+
"learning_rate": 1e-05,
|
| 133 |
+
"loss": 0.1972,
|
| 134 |
+
"step": 525
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.55,
|
| 138 |
+
"learning_rate": 1e-05,
|
| 139 |
+
"loss": 0.187,
|
| 140 |
+
"step": 550
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.57,
|
| 144 |
+
"learning_rate": 1e-05,
|
| 145 |
+
"loss": 0.1756,
|
| 146 |
+
"step": 575
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.6,
|
| 150 |
+
"learning_rate": 1e-05,
|
| 151 |
+
"loss": 0.1761,
|
| 152 |
+
"step": 600
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.02,
|
| 156 |
+
"learning_rate": 1e-05,
|
| 157 |
+
"loss": 0.1401,
|
| 158 |
+
"step": 625
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.05,
|
| 162 |
+
"learning_rate": 1e-05,
|
| 163 |
+
"loss": 0.117,
|
| 164 |
+
"step": 650
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.07,
|
| 168 |
+
"learning_rate": 1e-05,
|
| 169 |
+
"loss": 0.0835,
|
| 170 |
+
"step": 675
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.1,
|
| 174 |
+
"learning_rate": 1e-05,
|
| 175 |
+
"loss": 0.0784,
|
| 176 |
+
"step": 700
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.12,
|
| 180 |
+
"learning_rate": 1e-05,
|
| 181 |
+
"loss": 0.0861,
|
| 182 |
+
"step": 725
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.15,
|
| 186 |
+
"learning_rate": 1e-05,
|
| 187 |
+
"loss": 0.0844,
|
| 188 |
+
"step": 750
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.17,
|
| 192 |
+
"learning_rate": 1e-05,
|
| 193 |
+
"loss": 0.0691,
|
| 194 |
+
"step": 775
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.2,
|
| 198 |
+
"learning_rate": 1e-05,
|
| 199 |
+
"loss": 0.0685,
|
| 200 |
+
"step": 800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.22,
|
| 204 |
+
"learning_rate": 1e-05,
|
| 205 |
+
"loss": 0.0676,
|
| 206 |
+
"step": 825
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.25,
|
| 210 |
+
"learning_rate": 1e-05,
|
| 211 |
+
"loss": 0.0788,
|
| 212 |
+
"step": 850
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.27,
|
| 216 |
+
"learning_rate": 1e-05,
|
| 217 |
+
"loss": 0.076,
|
| 218 |
+
"step": 875
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.3,
|
| 222 |
+
"learning_rate": 1e-05,
|
| 223 |
+
"loss": 0.0715,
|
| 224 |
+
"step": 900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.32,
|
| 228 |
+
"learning_rate": 1e-05,
|
| 229 |
+
"loss": 0.0762,
|
| 230 |
+
"step": 925
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.35,
|
| 234 |
+
"learning_rate": 1e-05,
|
| 235 |
+
"loss": 0.0644,
|
| 236 |
+
"step": 950
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.37,
|
| 240 |
+
"learning_rate": 1e-05,
|
| 241 |
+
"loss": 0.0605,
|
| 242 |
+
"step": 975
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.4,
|
| 246 |
+
"learning_rate": 1e-05,
|
| 247 |
+
"loss": 0.0637,
|
| 248 |
+
"step": 1000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.4,
|
| 252 |
+
"eval_loss": 0.21794496476650238,
|
| 253 |
+
"eval_runtime": 2944.9179,
|
| 254 |
+
"eval_samples_per_second": 3.27,
|
| 255 |
+
"eval_steps_per_second": 0.204,
|
| 256 |
+
"eval_wer": 12.883608587437623,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.4,
|
| 261 |
+
"step": 1000,
|
| 262 |
+
"total_flos": 9.23300129783808e+18,
|
| 263 |
+
"train_loss": 0.15691602289676665,
|
| 264 |
+
"train_runtime": 6554.2706,
|
| 265 |
+
"train_samples_per_second": 4.882,
|
| 266 |
+
"train_steps_per_second": 0.153
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"max_steps": 1000,
|
| 270 |
+
"num_train_epochs": 9223372036854775807,
|
| 271 |
+
"total_flos": 9.23300129783808e+18,
|
| 272 |
+
"trial_name": null,
|
| 273 |
+
"trial_params": null
|
| 274 |
+
}
|