noflm
commited on
Commit
•
578f0e2
1
Parent(s):
ea7fd5b
End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- runs/Dec27_09-55-14_srv/events.out.tfevents.1672216184.srv.1172111.2 +3 -0
- train_results.json +5 -5
- trainer_state.json +142 -181
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"eval_wer":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.02,
|
| 3 |
+
"eval_loss": 0.6532349586486816,
|
| 4 |
+
"eval_runtime": 1529.5324,
|
| 5 |
+
"eval_samples_per_second": 3.01,
|
| 6 |
+
"eval_steps_per_second": 0.188,
|
| 7 |
+
"eval_wer": 21.991788980318223,
|
| 8 |
+
"train_loss": 0.06371040197610855,
|
| 9 |
+
"train_runtime": 79589.3253,
|
| 10 |
+
"train_samples_per_second": 4.021,
|
| 11 |
+
"train_steps_per_second": 0.126
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"eval_wer":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.02,
|
| 3 |
+
"eval_loss": 0.6532349586486816,
|
| 4 |
+
"eval_runtime": 1529.5324,
|
| 5 |
+
"eval_samples_per_second": 3.01,
|
| 6 |
+
"eval_steps_per_second": 0.188,
|
| 7 |
+
"eval_wer": 21.991788980318223
|
| 8 |
}
|
runs/Dec27_09-55-14_srv/events.out.tfevents.1672216184.srv.1172111.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:376b9b587745cc14a971964a87d273e1eebf96fb6ea5d415eff9f0f00395a7a5
|
| 3 |
+
size 358
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 35.02,
|
| 3 |
+
"train_loss": 0.06371040197610855,
|
| 4 |
+
"train_runtime": 79589.3253,
|
| 5 |
+
"train_samples_per_second": 4.021,
|
| 6 |
+
"train_steps_per_second": 0.126
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,274 +1,235 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
-
"step":
|
| 15 |
-
},
|
| 16 |
-
{
|
| 17 |
-
"epoch": 0.05,
|
| 18 |
-
"learning_rate": 9.800000000000001e-06,
|
| 19 |
-
"loss": 0.5962,
|
| 20 |
-
"step": 50
|
| 21 |
-
},
|
| 22 |
-
{
|
| 23 |
-
"epoch": 0.07,
|
| 24 |
-
"learning_rate": 1e-05,
|
| 25 |
-
"loss": 0.4928,
|
| 26 |
-
"step": 75
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch": 0.1,
|
| 30 |
-
"learning_rate": 1e-05,
|
| 31 |
-
"loss": 0.5115,
|
| 32 |
-
"step": 100
|
| 33 |
-
},
|
| 34 |
-
{
|
| 35 |
-
"epoch": 0.12,
|
| 36 |
-
"learning_rate": 1e-05,
|
| 37 |
-
"loss": 0.4646,
|
| 38 |
-
"step": 125
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.15,
|
| 42 |
-
"learning_rate": 1e-05,
|
| 43 |
-
"loss": 0.5159,
|
| 44 |
-
"step": 150
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.17,
|
| 48 |
-
"learning_rate": 1e-05,
|
| 49 |
-
"loss": 0.4915,
|
| 50 |
-
"step": 175
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"epoch": 0.2,
|
| 54 |
-
"learning_rate": 1e-05,
|
| 55 |
-
"loss": 0.4671,
|
| 56 |
-
"step": 200
|
| 57 |
-
},
|
| 58 |
-
{
|
| 59 |
-
"epoch": 0.23,
|
| 60 |
-
"learning_rate": 1e-05,
|
| 61 |
-
"loss": 0.4107,
|
| 62 |
-
"step": 225
|
| 63 |
-
},
|
| 64 |
-
{
|
| 65 |
-
"epoch": 0.25,
|
| 66 |
-
"learning_rate": 1e-05,
|
| 67 |
-
"loss": 0.4238,
|
| 68 |
-
"step": 250
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
"learning_rate": 1e-05,
|
| 73 |
-
"loss": 0.
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
|
|
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
"learning_rate": 1e-05,
|
| 85 |
-
"loss": 0.
|
| 86 |
-
"step":
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0
|
| 90 |
"learning_rate": 1e-05,
|
| 91 |
-
"loss": 0.
|
| 92 |
-
"step":
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0
|
| 96 |
-
"
|
| 97 |
-
"
|
| 98 |
-
"
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
"learning_rate": 1e-05,
|
| 103 |
-
"loss": 0.
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
"learning_rate": 1e-05,
|
| 109 |
-
"loss": 0.
|
| 110 |
-
"step":
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
|
|
|
|
|
|
|
|
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
"learning_rate": 1e-05,
|
| 121 |
-
"loss": 0.
|
| 122 |
-
"step":
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
"learning_rate": 1e-05,
|
| 127 |
-
"loss": 0.
|
| 128 |
-
"step":
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
|
|
|
|
|
|
|
|
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0
|
| 138 |
"learning_rate": 1e-05,
|
| 139 |
-
"loss": 0.
|
| 140 |
-
"step":
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
"learning_rate": 1e-05,
|
| 145 |
-
"loss": 0.
|
| 146 |
-
"step":
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
|
|
|
|
|
|
|
|
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
"learning_rate": 1e-05,
|
| 157 |
-
"loss": 0.
|
| 158 |
-
"step":
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
"learning_rate": 1e-05,
|
| 163 |
-
"loss": 0.
|
| 164 |
-
"step":
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"
|
| 169 |
-
"
|
| 170 |
-
"
|
|
|
|
|
|
|
|
|
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0
|
| 174 |
"learning_rate": 1e-05,
|
| 175 |
-
"loss": 0.
|
| 176 |
-
"step":
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
"learning_rate": 1e-05,
|
| 181 |
-
"loss": 0.
|
| 182 |
-
"step":
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"
|
| 187 |
-
"
|
| 188 |
-
"
|
| 189 |
-
|
| 190 |
-
|
| 191 |
-
"
|
| 192 |
-
"learning_rate": 1e-05,
|
| 193 |
-
"loss": 0.6284,
|
| 194 |
-
"step": 775
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
"learning_rate": 1e-05,
|
| 199 |
-
"loss": 0.
|
| 200 |
-
"step":
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
"learning_rate": 1e-05,
|
| 205 |
-
"loss": 0.
|
| 206 |
-
"step":
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
|
|
|
|
|
|
|
|
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
"learning_rate": 1e-05,
|
| 217 |
-
"loss": 0.
|
| 218 |
-
"step":
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0
|
| 222 |
"learning_rate": 1e-05,
|
| 223 |
-
"loss": 0.
|
| 224 |
-
"step":
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0
|
| 228 |
-
"
|
| 229 |
-
"
|
| 230 |
-
"
|
|
|
|
|
|
|
|
|
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
"learning_rate": 1e-05,
|
| 235 |
-
"loss": 0.
|
| 236 |
-
"step":
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
"learning_rate": 1e-05,
|
| 241 |
-
"loss": 0.
|
| 242 |
-
"step":
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
"
|
| 252 |
-
"eval_loss": 0.46010294556617737,
|
| 253 |
-
"eval_runtime": 1657.4757,
|
| 254 |
-
"eval_samples_per_second": 2.778,
|
| 255 |
-
"eval_steps_per_second": 0.348,
|
| 256 |
-
"eval_wer": 22.51334731203637,
|
| 257 |
-
"step": 1000
|
| 258 |
},
|
| 259 |
{
|
| 260 |
-
"epoch":
|
| 261 |
-
"step":
|
| 262 |
-
"total_flos":
|
| 263 |
-
"train_loss": 0.
|
| 264 |
-
"train_runtime":
|
| 265 |
-
"train_samples_per_second":
|
| 266 |
-
"train_steps_per_second": 0.
|
| 267 |
}
|
| 268 |
],
|
| 269 |
-
"max_steps":
|
| 270 |
"num_train_epochs": 9223372036854775807,
|
| 271 |
-
"total_flos":
|
| 272 |
"trial_name": null,
|
| 273 |
"trial_params": null
|
| 274 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 35.0165,
|
| 5 |
+
"global_step": 10000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 1.02,
|
| 12 |
+
"learning_rate": 9.960000000000001e-06,
|
| 13 |
+
"loss": 0.5615,
|
| 14 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 3.02,
|
| 18 |
"learning_rate": 1e-05,
|
| 19 |
+
"loss": 0.3273,
|
| 20 |
+
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 3.02,
|
| 24 |
+
"eval_loss": 0.4225325584411621,
|
| 25 |
+
"eval_runtime": 1489.9228,
|
| 26 |
+
"eval_samples_per_second": 3.09,
|
| 27 |
+
"eval_steps_per_second": 0.193,
|
| 28 |
+
"eval_wer": 20.82533081951615,
|
| 29 |
+
"step": 1000
|
| 30 |
},
|
| 31 |
{
|
| 32 |
+
"epoch": 5.01,
|
| 33 |
"learning_rate": 1e-05,
|
| 34 |
+
"loss": 0.1859,
|
| 35 |
+
"step": 1500
|
| 36 |
},
|
| 37 |
{
|
| 38 |
+
"epoch": 7.0,
|
| 39 |
"learning_rate": 1e-05,
|
| 40 |
+
"loss": 0.0923,
|
| 41 |
+
"step": 2000
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 7.0,
|
| 45 |
+
"eval_loss": 0.46434369683265686,
|
| 46 |
+
"eval_runtime": 1504.5618,
|
| 47 |
+
"eval_samples_per_second": 3.06,
|
| 48 |
+
"eval_steps_per_second": 0.191,
|
| 49 |
+
"eval_wer": 21.22002361108664,
|
| 50 |
+
"step": 2000
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 8.03,
|
| 54 |
"learning_rate": 1e-05,
|
| 55 |
+
"loss": 0.0369,
|
| 56 |
+
"step": 2500
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 10.02,
|
| 60 |
"learning_rate": 1e-05,
|
| 61 |
+
"loss": 0.0164,
|
| 62 |
+
"step": 3000
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 10.02,
|
| 66 |
+
"eval_loss": 0.5403426885604858,
|
| 67 |
+
"eval_runtime": 1504.7378,
|
| 68 |
+
"eval_samples_per_second": 3.06,
|
| 69 |
+
"eval_steps_per_second": 0.191,
|
| 70 |
+
"eval_wer": 22.962662766725987,
|
| 71 |
+
"step": 3000
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 12.01,
|
| 75 |
"learning_rate": 1e-05,
|
| 76 |
+
"loss": 0.0089,
|
| 77 |
+
"step": 3500
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 14.01,
|
| 81 |
"learning_rate": 1e-05,
|
| 82 |
+
"loss": 0.006,
|
| 83 |
+
"step": 4000
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 14.01,
|
| 87 |
+
"eval_loss": 0.5819889307022095,
|
| 88 |
+
"eval_runtime": 1478.853,
|
| 89 |
+
"eval_samples_per_second": 3.113,
|
| 90 |
+
"eval_steps_per_second": 0.195,
|
| 91 |
+
"eval_wer": 21.086109985375224,
|
| 92 |
+
"step": 4000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 16.0,
|
| 96 |
"learning_rate": 1e-05,
|
| 97 |
+
"loss": 0.0057,
|
| 98 |
+
"step": 4500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 17.02,
|
| 102 |
"learning_rate": 1e-05,
|
| 103 |
+
"loss": 0.0046,
|
| 104 |
+
"step": 5000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 17.02,
|
| 108 |
+
"eval_loss": 0.5851565003395081,
|
| 109 |
+
"eval_runtime": 1532.3442,
|
| 110 |
+
"eval_samples_per_second": 3.005,
|
| 111 |
+
"eval_steps_per_second": 0.188,
|
| 112 |
+
"eval_wer": 22.072841964301446,
|
| 113 |
+
"step": 5000
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 19.02,
|
| 117 |
"learning_rate": 1e-05,
|
| 118 |
+
"loss": 0.0042,
|
| 119 |
+
"step": 5500
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 21.01,
|
| 123 |
"learning_rate": 1e-05,
|
| 124 |
+
"loss": 0.0034,
|
| 125 |
+
"step": 6000
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 21.01,
|
| 129 |
+
"eval_loss": 0.6112661361694336,
|
| 130 |
+
"eval_runtime": 1497.7325,
|
| 131 |
+
"eval_samples_per_second": 3.074,
|
| 132 |
+
"eval_steps_per_second": 0.192,
|
| 133 |
+
"eval_wer": 21.6622909802125,
|
| 134 |
+
"step": 6000
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 23.0,
|
| 138 |
"learning_rate": 1e-05,
|
| 139 |
+
"loss": 0.004,
|
| 140 |
+
"step": 6500
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 24.03,
|
| 144 |
"learning_rate": 1e-05,
|
| 145 |
+
"loss": 0.0028,
|
| 146 |
+
"step": 7000
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 24.03,
|
| 150 |
+
"eval_loss": 0.6582160592079163,
|
| 151 |
+
"eval_runtime": 1517.5965,
|
| 152 |
+
"eval_samples_per_second": 3.034,
|
| 153 |
+
"eval_steps_per_second": 0.19,
|
| 154 |
+
"eval_wer": 22.326573044596763,
|
| 155 |
+
"step": 7000
|
|
|
|
|
|
|
|
|
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 26.02,
|
| 159 |
"learning_rate": 1e-05,
|
| 160 |
+
"loss": 0.0027,
|
| 161 |
+
"step": 7500
|
| 162 |
},
|
| 163 |
{
|
| 164 |
+
"epoch": 28.01,
|
| 165 |
"learning_rate": 1e-05,
|
| 166 |
+
"loss": 0.0025,
|
| 167 |
+
"step": 8000
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 28.01,
|
| 171 |
+
"eval_loss": 0.6349595785140991,
|
| 172 |
+
"eval_runtime": 1539.4689,
|
| 173 |
+
"eval_samples_per_second": 2.991,
|
| 174 |
+
"eval_steps_per_second": 0.187,
|
| 175 |
+
"eval_wer": 22.23318591087696,
|
| 176 |
+
"step": 8000
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 30.01,
|
| 180 |
"learning_rate": 1e-05,
|
| 181 |
+
"loss": 0.0027,
|
| 182 |
+
"step": 8500
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 32.0,
|
| 186 |
"learning_rate": 1e-05,
|
| 187 |
+
"loss": 0.0029,
|
| 188 |
+
"step": 9000
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 32.0,
|
| 192 |
+
"eval_loss": 0.646816074848175,
|
| 193 |
+
"eval_runtime": 1531.6588,
|
| 194 |
+
"eval_samples_per_second": 3.006,
|
| 195 |
+
"eval_steps_per_second": 0.188,
|
| 196 |
+
"eval_wer": 22.10984441351118,
|
| 197 |
+
"step": 9000
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 33.02,
|
| 201 |
"learning_rate": 1e-05,
|
| 202 |
+
"loss": 0.0021,
|
| 203 |
+
"step": 9500
|
| 204 |
},
|
| 205 |
{
|
| 206 |
+
"epoch": 35.02,
|
| 207 |
"learning_rate": 1e-05,
|
| 208 |
+
"loss": 0.0014,
|
| 209 |
+
"step": 10000
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 35.02,
|
| 213 |
+
"eval_loss": 0.6532349586486816,
|
| 214 |
+
"eval_runtime": 1526.2981,
|
| 215 |
+
"eval_samples_per_second": 3.016,
|
| 216 |
+
"eval_steps_per_second": 0.189,
|
| 217 |
+
"eval_wer": 21.991788980318223,
|
| 218 |
+
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 35.02,
|
| 222 |
+
"step": 10000,
|
| 223 |
+
"total_flos": 2.07052565741568e+19,
|
| 224 |
+
"train_loss": 0.06371040197610855,
|
| 225 |
+
"train_runtime": 79589.3253,
|
| 226 |
+
"train_samples_per_second": 4.021,
|
| 227 |
+
"train_steps_per_second": 0.126
|
| 228 |
}
|
| 229 |
],
|
| 230 |
+
"max_steps": 10000,
|
| 231 |
"num_train_epochs": 9223372036854775807,
|
| 232 |
+
"total_flos": 2.07052565741568e+19,
|
| 233 |
"trial_name": null,
|
| 234 |
"trial_params": null
|
| 235 |
}
|