Commit
•
75c7b10
1
Parent(s):
df33e28
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.18,
|
| 3 |
+
"eval_loss": 0.2325439453125,
|
| 4 |
+
"eval_runtime": 1395.717,
|
| 5 |
+
"eval_samples_per_second": 2.073,
|
| 6 |
+
"eval_steps_per_second": 0.13,
|
| 7 |
+
"eval_wer": 10.360772823001557,
|
| 8 |
+
"train_loss": 0.06760481643676758,
|
| 9 |
+
"train_runtime": 9362.2814,
|
| 10 |
+
"train_samples_per_second": 3.418,
|
| 11 |
+
"train_steps_per_second": 0.107
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.18,
|
| 3 |
+
"eval_loss": 0.2325439453125,
|
| 4 |
+
"eval_runtime": 1395.717,
|
| 5 |
+
"eval_samples_per_second": 2.073,
|
| 6 |
+
"eval_steps_per_second": 0.13,
|
| 7 |
+
"eval_wer": 10.360772823001557
|
| 8 |
+
}
|
runs/Dec17_22-06-35_129-146-105-103/events.out.tfevents.1671325735.129-146-105-103.4186467.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19a9e7ac27e588dbe03daf867ad6aa60f83051d92b4dba490778f3c6c063ec86
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.18,
|
| 3 |
+
"train_loss": 0.06760481643676758,
|
| 4 |
+
"train_runtime": 9362.2814,
|
| 5 |
+
"train_samples_per_second": 3.418,
|
| 6 |
+
"train_steps_per_second": 0.107
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.18,
|
| 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": 6.712113404111031e-06,
|
| 13 |
+
"loss": 0.3544,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 8.31378915840787e-06,
|
| 19 |
+
"loss": 0.1956,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 9.256291743595376e-06,
|
| 25 |
+
"loss": 0.1798,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 9.911356165197841e-06,
|
| 31 |
+
"loss": 0.1901,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 9.777777777777779e-06,
|
| 37 |
+
"loss": 0.1771,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 9.5e-06,
|
| 43 |
+
"loss": 0.151,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 9.222222222222224e-06,
|
| 49 |
+
"loss": 0.1219,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 8.944444444444446e-06,
|
| 55 |
+
"loss": 0.1307,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.02,
|
| 60 |
+
"learning_rate": 8.666666666666668e-06,
|
| 61 |
+
"loss": 0.1204,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.04,
|
| 66 |
+
"learning_rate": 8.38888888888889e-06,
|
| 67 |
+
"loss": 0.097,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.07,
|
| 72 |
+
"learning_rate": 8.111111111111112e-06,
|
| 73 |
+
"loss": 0.0844,
|
| 74 |
+
"step": 275
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.09,
|
| 78 |
+
"learning_rate": 7.833333333333333e-06,
|
| 79 |
+
"loss": 0.0889,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.12,
|
| 84 |
+
"learning_rate": 7.555555555555556e-06,
|
| 85 |
+
"loss": 0.0807,
|
| 86 |
+
"step": 325
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.15,
|
| 90 |
+
"learning_rate": 7.277777777777778e-06,
|
| 91 |
+
"loss": 0.072,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.17,
|
| 96 |
+
"learning_rate": 7e-06,
|
| 97 |
+
"loss": 0.0621,
|
| 98 |
+
"step": 375
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.2,
|
| 102 |
+
"learning_rate": 6.7222222222222235e-06,
|
| 103 |
+
"loss": 0.0598,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.02,
|
| 108 |
+
"learning_rate": 6.444444444444445e-06,
|
| 109 |
+
"loss": 0.0585,
|
| 110 |
+
"step": 425
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.04,
|
| 114 |
+
"learning_rate": 6.166666666666667e-06,
|
| 115 |
+
"loss": 0.0501,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.06,
|
| 120 |
+
"learning_rate": 5.9e-06,
|
| 121 |
+
"loss": 0.0446,
|
| 122 |
+
"step": 475
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.09,
|
| 126 |
+
"learning_rate": 5.622222222222222e-06,
|
| 127 |
+
"loss": 0.0395,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.12,
|
| 132 |
+
"learning_rate": 5.344444444444446e-06,
|
| 133 |
+
"loss": 0.0417,
|
| 134 |
+
"step": 525
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.14,
|
| 138 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 139 |
+
"loss": 0.0359,
|
| 140 |
+
"step": 550
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.17,
|
| 144 |
+
"learning_rate": 4.7888888888888894e-06,
|
| 145 |
+
"loss": 0.0319,
|
| 146 |
+
"step": 575
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.19,
|
| 150 |
+
"learning_rate": 4.511111111111111e-06,
|
| 151 |
+
"loss": 0.0304,
|
| 152 |
+
"step": 600
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.01,
|
| 156 |
+
"learning_rate": 4.233333333333334e-06,
|
| 157 |
+
"loss": 0.0287,
|
| 158 |
+
"step": 625
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.04,
|
| 162 |
+
"learning_rate": 3.955555555555556e-06,
|
| 163 |
+
"loss": 0.0242,
|
| 164 |
+
"step": 650
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.06,
|
| 168 |
+
"learning_rate": 3.6777777777777778e-06,
|
| 169 |
+
"loss": 0.0198,
|
| 170 |
+
"step": 675
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.08,
|
| 174 |
+
"learning_rate": 3.4000000000000005e-06,
|
| 175 |
+
"loss": 0.0182,
|
| 176 |
+
"step": 700
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.11,
|
| 180 |
+
"learning_rate": 3.1222222222222228e-06,
|
| 181 |
+
"loss": 0.018,
|
| 182 |
+
"step": 725
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.13,
|
| 186 |
+
"learning_rate": 2.8444444444444446e-06,
|
| 187 |
+
"loss": 0.0154,
|
| 188 |
+
"step": 750
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.16,
|
| 192 |
+
"learning_rate": 2.566666666666667e-06,
|
| 193 |
+
"loss": 0.0129,
|
| 194 |
+
"step": 775
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.19,
|
| 198 |
+
"learning_rate": 2.2888888888888892e-06,
|
| 199 |
+
"loss": 0.0134,
|
| 200 |
+
"step": 800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.0,
|
| 204 |
+
"learning_rate": 2.011111111111111e-06,
|
| 205 |
+
"loss": 0.0128,
|
| 206 |
+
"step": 825
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.03,
|
| 210 |
+
"learning_rate": 1.7333333333333336e-06,
|
| 211 |
+
"loss": 0.0074,
|
| 212 |
+
"step": 850
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.05,
|
| 216 |
+
"learning_rate": 1.4555555555555557e-06,
|
| 217 |
+
"loss": 0.0063,
|
| 218 |
+
"step": 875
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.08,
|
| 222 |
+
"learning_rate": 1.1777777777777778e-06,
|
| 223 |
+
"loss": 0.0044,
|
| 224 |
+
"step": 900
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.11,
|
| 228 |
+
"learning_rate": 9.000000000000001e-07,
|
| 229 |
+
"loss": 0.0049,
|
| 230 |
+
"step": 925
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.13,
|
| 234 |
+
"learning_rate": 6.222222222222223e-07,
|
| 235 |
+
"loss": 0.0056,
|
| 236 |
+
"step": 950
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.16,
|
| 240 |
+
"learning_rate": 3.444444444444445e-07,
|
| 241 |
+
"loss": 0.0068,
|
| 242 |
+
"step": 975
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.18,
|
| 246 |
+
"learning_rate": 6.666666666666668e-08,
|
| 247 |
+
"loss": 0.0067,
|
| 248 |
+
"step": 1000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.18,
|
| 252 |
+
"eval_loss": 0.2325439453125,
|
| 253 |
+
"eval_runtime": 1399.9283,
|
| 254 |
+
"eval_samples_per_second": 2.067,
|
| 255 |
+
"eval_steps_per_second": 0.129,
|
| 256 |
+
"eval_wer": 10.360772823001557,
|
| 257 |
+
"step": 1000
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 4.18,
|
| 261 |
+
"step": 1000,
|
| 262 |
+
"total_flos": 6.777161964753152e+19,
|
| 263 |
+
"train_loss": 0.06760481643676758,
|
| 264 |
+
"train_runtime": 9362.2814,
|
| 265 |
+
"train_samples_per_second": 3.418,
|
| 266 |
+
"train_steps_per_second": 0.107
|
| 267 |
+
}
|
| 268 |
+
],
|
| 269 |
+
"max_steps": 1000,
|
| 270 |
+
"num_train_epochs": 9223372036854775807,
|
| 271 |
+
"total_flos": 6.777161964753152e+19,
|
| 272 |
+
"trial_name": null,
|
| 273 |
+
"trial_params": null
|
| 274 |
+
}
|