Commit
•
c880182
1
Parent(s):
7580938
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +361 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.5755836367607117,
|
| 4 |
+
"eval_runtime": 6.8487,
|
| 5 |
+
"eval_samples": 149,
|
| 6 |
+
"eval_samples_per_second": 21.756,
|
| 7 |
+
"eval_steps_per_second": 0.73,
|
| 8 |
+
"eval_wer": 0.6013686911890505,
|
| 9 |
+
"train_loss": 1.4620501448891379,
|
| 10 |
+
"train_runtime": 7639.7148,
|
| 11 |
+
"train_samples": 1386,
|
| 12 |
+
"train_samples_per_second": 18.142,
|
| 13 |
+
"train_steps_per_second": 0.576
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.5755836367607117,
|
| 4 |
+
"eval_runtime": 6.8487,
|
| 5 |
+
"eval_samples": 149,
|
| 6 |
+
"eval_samples_per_second": 21.756,
|
| 7 |
+
"eval_steps_per_second": 0.73,
|
| 8 |
+
"eval_wer": 0.6013686911890505
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262075377
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13f646aa1d30d9e3683f03159276d655496bd939e50b2b3a6fc608d538879b92
|
| 3 |
size 1262075377
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"train_loss": 1.4620501448891379,
|
| 4 |
+
"train_runtime": 7639.7148,
|
| 5 |
+
"train_samples": 1386,
|
| 6 |
+
"train_samples_per_second": 18.142,
|
| 7 |
+
"train_steps_per_second": 0.576
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 100.0,
|
| 5 |
+
"global_step": 4400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 2.27,
|
| 12 |
+
"learning_rate": 1.3579999999999999e-05,
|
| 13 |
+
"loss": 11.686,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 4.55,
|
| 18 |
+
"learning_rate": 2.758e-05,
|
| 19 |
+
"loss": 4.1183,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 6.82,
|
| 24 |
+
"learning_rate": 4.157999999999999e-05,
|
| 25 |
+
"loss": 3.0783,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 9.09,
|
| 30 |
+
"learning_rate": 5.558e-05,
|
| 31 |
+
"loss": 2.7958,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 11.36,
|
| 36 |
+
"learning_rate": 6.958e-05,
|
| 37 |
+
"loss": 2.7064,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 11.36,
|
| 42 |
+
"eval_loss": 2.711225986480713,
|
| 43 |
+
"eval_runtime": 6.87,
|
| 44 |
+
"eval_samples_per_second": 21.689,
|
| 45 |
+
"eval_steps_per_second": 0.728,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 13.64,
|
| 51 |
+
"learning_rate": 6.825897435897435e-05,
|
| 52 |
+
"loss": 2.6552,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 15.91,
|
| 57 |
+
"learning_rate": 6.646410256410256e-05,
|
| 58 |
+
"loss": 2.5236,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 18.18,
|
| 63 |
+
"learning_rate": 6.466923076923076e-05,
|
| 64 |
+
"loss": 1.8116,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 20.45,
|
| 69 |
+
"learning_rate": 6.287435897435897e-05,
|
| 70 |
+
"loss": 1.4245,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 22.73,
|
| 75 |
+
"learning_rate": 6.107948717948717e-05,
|
| 76 |
+
"loss": 1.3079,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 22.73,
|
| 81 |
+
"eval_loss": 0.7336559891700745,
|
| 82 |
+
"eval_runtime": 6.7043,
|
| 83 |
+
"eval_samples_per_second": 22.225,
|
| 84 |
+
"eval_steps_per_second": 0.746,
|
| 85 |
+
"eval_wer": 0.7775876817792986,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 25.0,
|
| 90 |
+
"learning_rate": 5.928461538461538e-05,
|
| 91 |
+
"loss": 1.2335,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 27.27,
|
| 96 |
+
"learning_rate": 5.748974358974358e-05,
|
| 97 |
+
"loss": 1.1818,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 29.55,
|
| 102 |
+
"learning_rate": 5.569487179487179e-05,
|
| 103 |
+
"loss": 1.1441,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 31.82,
|
| 108 |
+
"learning_rate": 5.3899999999999996e-05,
|
| 109 |
+
"loss": 1.1166,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 34.09,
|
| 114 |
+
"learning_rate": 5.21051282051282e-05,
|
| 115 |
+
"loss": 1.0919,
|
| 116 |
+
"step": 1500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 34.09,
|
| 120 |
+
"eval_loss": 0.5937860608100891,
|
| 121 |
+
"eval_runtime": 6.763,
|
| 122 |
+
"eval_samples_per_second": 22.032,
|
| 123 |
+
"eval_steps_per_second": 0.739,
|
| 124 |
+
"eval_wer": 0.7023096663815227,
|
| 125 |
+
"step": 1500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 36.36,
|
| 129 |
+
"learning_rate": 5.03102564102564e-05,
|
| 130 |
+
"loss": 1.0684,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 38.64,
|
| 135 |
+
"learning_rate": 4.853333333333333e-05,
|
| 136 |
+
"loss": 1.0238,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 40.91,
|
| 141 |
+
"learning_rate": 4.6738461538461535e-05,
|
| 142 |
+
"loss": 1.0182,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 43.18,
|
| 147 |
+
"learning_rate": 4.494358974358974e-05,
|
| 148 |
+
"loss": 0.9795,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 45.45,
|
| 153 |
+
"learning_rate": 4.314871794871794e-05,
|
| 154 |
+
"loss": 0.9546,
|
| 155 |
+
"step": 2000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 45.45,
|
| 159 |
+
"eval_loss": 0.5698409080505371,
|
| 160 |
+
"eval_runtime": 6.6992,
|
| 161 |
+
"eval_samples_per_second": 22.241,
|
| 162 |
+
"eval_steps_per_second": 0.746,
|
| 163 |
+
"eval_wer": 0.613344739093242,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 47.73,
|
| 168 |
+
"learning_rate": 4.135384615384616e-05,
|
| 169 |
+
"loss": 0.9478,
|
| 170 |
+
"step": 2100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 50.0,
|
| 174 |
+
"learning_rate": 3.955897435897436e-05,
|
| 175 |
+
"loss": 0.9329,
|
| 176 |
+
"step": 2200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 52.27,
|
| 180 |
+
"learning_rate": 3.776410256410256e-05,
|
| 181 |
+
"loss": 0.9001,
|
| 182 |
+
"step": 2300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 54.55,
|
| 186 |
+
"learning_rate": 3.5969230769230765e-05,
|
| 187 |
+
"loss": 0.8957,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 56.82,
|
| 192 |
+
"learning_rate": 3.417435897435897e-05,
|
| 193 |
+
"loss": 0.8895,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 56.82,
|
| 198 |
+
"eval_loss": 0.5738843083381653,
|
| 199 |
+
"eval_runtime": 6.762,
|
| 200 |
+
"eval_samples_per_second": 22.035,
|
| 201 |
+
"eval_steps_per_second": 0.739,
|
| 202 |
+
"eval_wer": 0.6142001710863987,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 59.09,
|
| 207 |
+
"learning_rate": 3.237948717948718e-05,
|
| 208 |
+
"loss": 0.8718,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 61.36,
|
| 213 |
+
"learning_rate": 3.058461538461538e-05,
|
| 214 |
+
"loss": 0.8642,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 63.64,
|
| 219 |
+
"learning_rate": 2.878974358974359e-05,
|
| 220 |
+
"loss": 0.8443,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 65.91,
|
| 225 |
+
"learning_rate": 2.6994871794871793e-05,
|
| 226 |
+
"loss": 0.8272,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 68.18,
|
| 231 |
+
"learning_rate": 2.5199999999999996e-05,
|
| 232 |
+
"loss": 0.8152,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 68.18,
|
| 237 |
+
"eval_loss": 0.5578901171684265,
|
| 238 |
+
"eval_runtime": 6.7178,
|
| 239 |
+
"eval_samples_per_second": 22.18,
|
| 240 |
+
"eval_steps_per_second": 0.744,
|
| 241 |
+
"eval_wer": 0.6090675791274593,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 70.45,
|
| 246 |
+
"learning_rate": 2.3405128205128206e-05,
|
| 247 |
+
"loss": 0.8141,
|
| 248 |
+
"step": 3100
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 72.73,
|
| 252 |
+
"learning_rate": 2.161025641025641e-05,
|
| 253 |
+
"loss": 0.8087,
|
| 254 |
+
"step": 3200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 75.0,
|
| 258 |
+
"learning_rate": 1.9833333333333332e-05,
|
| 259 |
+
"loss": 0.7897,
|
| 260 |
+
"step": 3300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 77.27,
|
| 264 |
+
"learning_rate": 1.8038461538461535e-05,
|
| 265 |
+
"loss": 0.7837,
|
| 266 |
+
"step": 3400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 79.55,
|
| 270 |
+
"learning_rate": 1.624358974358974e-05,
|
| 271 |
+
"loss": 0.7703,
|
| 272 |
+
"step": 3500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 79.55,
|
| 276 |
+
"eval_loss": 0.5813038349151611,
|
| 277 |
+
"eval_runtime": 6.7449,
|
| 278 |
+
"eval_samples_per_second": 22.091,
|
| 279 |
+
"eval_steps_per_second": 0.741,
|
| 280 |
+
"eval_wer": 0.621043627031651,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 81.82,
|
| 285 |
+
"learning_rate": 1.4448717948717947e-05,
|
| 286 |
+
"loss": 0.7612,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 84.09,
|
| 291 |
+
"learning_rate": 1.2653846153846152e-05,
|
| 292 |
+
"loss": 0.7575,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 86.36,
|
| 297 |
+
"learning_rate": 1.0858974358974358e-05,
|
| 298 |
+
"loss": 0.7483,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 88.64,
|
| 303 |
+
"learning_rate": 9.064102564102564e-06,
|
| 304 |
+
"loss": 0.7496,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 90.91,
|
| 309 |
+
"learning_rate": 7.269230769230769e-06,
|
| 310 |
+
"loss": 0.732,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 90.91,
|
| 315 |
+
"eval_loss": 0.5756056308746338,
|
| 316 |
+
"eval_runtime": 6.9674,
|
| 317 |
+
"eval_samples_per_second": 21.385,
|
| 318 |
+
"eval_steps_per_second": 0.718,
|
| 319 |
+
"eval_wer": 0.5859709153122327,
|
| 320 |
+
"step": 4000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 93.18,
|
| 324 |
+
"learning_rate": 5.4743589743589735e-06,
|
| 325 |
+
"loss": 0.7262,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 95.45,
|
| 330 |
+
"learning_rate": 3.6794871794871793e-06,
|
| 331 |
+
"loss": 0.7307,
|
| 332 |
+
"step": 4200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 97.73,
|
| 336 |
+
"learning_rate": 1.8846153846153845e-06,
|
| 337 |
+
"loss": 0.7265,
|
| 338 |
+
"step": 4300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 100.0,
|
| 342 |
+
"learning_rate": 1.0769230769230769e-07,
|
| 343 |
+
"loss": 0.7226,
|
| 344 |
+
"step": 4400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 100.0,
|
| 348 |
+
"step": 4400,
|
| 349 |
+
"total_flos": 1.9662171121467834e+19,
|
| 350 |
+
"train_loss": 1.4620501448891379,
|
| 351 |
+
"train_runtime": 7639.7148,
|
| 352 |
+
"train_samples_per_second": 18.142,
|
| 353 |
+
"train_steps_per_second": 0.576
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"max_steps": 4400,
|
| 357 |
+
"num_train_epochs": 100,
|
| 358 |
+
"total_flos": 1.9662171121467834e+19,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|