Commit
•
9d2871c
1
Parent(s):
f3b731c
End of training
Browse files- .gitattributes +1 -0
- all_results.json +11 -0
- eval_nbest_predictions.json +3 -0
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- runs/Aug09_08-32-25_58e64a916bd5/events.out.tfevents.1660054338.58e64a916bd5.366.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +373 -0
.gitattributes
CHANGED
|
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 81.32450331125828,
|
| 4 |
+
"eval_f1": 88.6687826376456,
|
| 5 |
+
"eval_samples": 10626,
|
| 6 |
+
"train_loss": 0.9686727332664389,
|
| 7 |
+
"train_runtime": 18778.1209,
|
| 8 |
+
"train_samples": 87714,
|
| 9 |
+
"train_samples_per_second": 9.342,
|
| 10 |
+
"train_steps_per_second": 1.557
|
| 11 |
+
}
|
eval_nbest_predictions.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17340e65a909f6222d992ed453ccce05879fa896b1b9938d84ce2c07af4a1278
|
| 3 |
+
size 49274776
|
eval_predictions.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_exact_match": 81.32450331125828,
|
| 4 |
+
"eval_f1": 88.6687826376456,
|
| 5 |
+
"eval_samples": 10626
|
| 6 |
+
}
|
runs/Aug09_08-32-25_58e64a916bd5/events.out.tfevents.1660054338.58e64a916bd5.366.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b434fa1a330bcd3e13b3dc8a61d5b3444d29b1ee9c98014cbce82d72bb82807
|
| 3 |
+
size 194
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 0.9686727332664389,
|
| 4 |
+
"train_runtime": 18778.1209,
|
| 5 |
+
"train_samples": 87714,
|
| 6 |
+
"train_samples_per_second": 9.342,
|
| 7 |
+
"train_steps_per_second": 1.557
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,373 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 29238,
|
| 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": 2.9486969012928382e-05,
|
| 13 |
+
"loss": 2.7395,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 2.8973938025856763e-05,
|
| 19 |
+
"loss": 1.725,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 2.8460907038785144e-05,
|
| 25 |
+
"loss": 1.4616,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.14,
|
| 30 |
+
"learning_rate": 2.7947876051713525e-05,
|
| 31 |
+
"loss": 1.4496,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 2.7434845064641902e-05,
|
| 37 |
+
"loss": 1.3397,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21,
|
| 42 |
+
"learning_rate": 2.6921814077570283e-05,
|
| 43 |
+
"loss": 1.3652,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"learning_rate": 2.6408783090498668e-05,
|
| 49 |
+
"loss": 1.2952,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"learning_rate": 2.589575210342705e-05,
|
| 55 |
+
"loss": 1.288,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.31,
|
| 60 |
+
"learning_rate": 2.538272111635543e-05,
|
| 61 |
+
"loss": 1.2415,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.34,
|
| 66 |
+
"learning_rate": 2.486969012928381e-05,
|
| 67 |
+
"loss": 1.2008,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.38,
|
| 72 |
+
"learning_rate": 2.435665914221219e-05,
|
| 73 |
+
"loss": 1.216,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.41,
|
| 78 |
+
"learning_rate": 2.3843628155140572e-05,
|
| 79 |
+
"loss": 1.2232,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.44,
|
| 84 |
+
"learning_rate": 2.3330597168068953e-05,
|
| 85 |
+
"loss": 1.2123,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.48,
|
| 90 |
+
"learning_rate": 2.281756618099733e-05,
|
| 91 |
+
"loss": 1.174,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.51,
|
| 96 |
+
"learning_rate": 2.2304535193925712e-05,
|
| 97 |
+
"loss": 1.1183,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.55,
|
| 102 |
+
"learning_rate": 2.1791504206854093e-05,
|
| 103 |
+
"loss": 1.1476,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.58,
|
| 108 |
+
"learning_rate": 2.1278473219782474e-05,
|
| 109 |
+
"loss": 1.121,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.62,
|
| 114 |
+
"learning_rate": 2.0765442232710855e-05,
|
| 115 |
+
"loss": 1.1595,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.65,
|
| 120 |
+
"learning_rate": 2.0252411245639236e-05,
|
| 121 |
+
"loss": 1.1104,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.68,
|
| 126 |
+
"learning_rate": 1.973938025856762e-05,
|
| 127 |
+
"loss": 1.0875,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.72,
|
| 132 |
+
"learning_rate": 1.9226349271496e-05,
|
| 133 |
+
"loss": 1.0816,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.75,
|
| 138 |
+
"learning_rate": 1.8713318284424382e-05,
|
| 139 |
+
"loss": 1.0924,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.79,
|
| 144 |
+
"learning_rate": 1.820028729735276e-05,
|
| 145 |
+
"loss": 1.0699,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"learning_rate": 1.768725631028114e-05,
|
| 151 |
+
"loss": 1.0639,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.86,
|
| 156 |
+
"learning_rate": 1.717422532320952e-05,
|
| 157 |
+
"loss": 1.0217,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.89,
|
| 162 |
+
"learning_rate": 1.6661194336137902e-05,
|
| 163 |
+
"loss": 1.0369,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.92,
|
| 168 |
+
"learning_rate": 1.6148163349066283e-05,
|
| 169 |
+
"loss": 1.0832,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"learning_rate": 1.5635132361994664e-05,
|
| 175 |
+
"loss": 1.0152,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.99,
|
| 180 |
+
"learning_rate": 1.5122101374923047e-05,
|
| 181 |
+
"loss": 1.0104,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.03,
|
| 186 |
+
"learning_rate": 1.4609070387851426e-05,
|
| 187 |
+
"loss": 0.7741,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.06,
|
| 192 |
+
"learning_rate": 1.4096039400779807e-05,
|
| 193 |
+
"loss": 0.7154,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.09,
|
| 198 |
+
"learning_rate": 1.3583008413708188e-05,
|
| 199 |
+
"loss": 0.7412,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.13,
|
| 204 |
+
"learning_rate": 1.306997742663657e-05,
|
| 205 |
+
"loss": 0.7439,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.16,
|
| 210 |
+
"learning_rate": 1.255694643956495e-05,
|
| 211 |
+
"loss": 0.6894,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2,
|
| 216 |
+
"learning_rate": 1.2043915452493331e-05,
|
| 217 |
+
"loss": 0.6848,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.23,
|
| 222 |
+
"learning_rate": 1.1530884465421712e-05,
|
| 223 |
+
"loss": 0.7217,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.27,
|
| 228 |
+
"learning_rate": 1.1017853478350093e-05,
|
| 229 |
+
"loss": 0.7294,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.3,
|
| 234 |
+
"learning_rate": 1.0504822491278474e-05,
|
| 235 |
+
"loss": 0.7065,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.33,
|
| 240 |
+
"learning_rate": 9.991791504206853e-06,
|
| 241 |
+
"loss": 0.704,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.37,
|
| 246 |
+
"learning_rate": 9.478760517135234e-06,
|
| 247 |
+
"loss": 0.7225,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.4,
|
| 252 |
+
"learning_rate": 8.965729530063615e-06,
|
| 253 |
+
"loss": 0.6821,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.44,
|
| 258 |
+
"learning_rate": 8.452698542991998e-06,
|
| 259 |
+
"loss": 0.6722,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.47,
|
| 264 |
+
"learning_rate": 7.939667555920379e-06,
|
| 265 |
+
"loss": 0.7089,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.5,
|
| 270 |
+
"learning_rate": 7.426636568848759e-06,
|
| 271 |
+
"loss": 0.71,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.54,
|
| 276 |
+
"learning_rate": 6.913605581777139e-06,
|
| 277 |
+
"loss": 0.7121,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.57,
|
| 282 |
+
"learning_rate": 6.40057459470552e-06,
|
| 283 |
+
"loss": 0.7063,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.61,
|
| 288 |
+
"learning_rate": 5.887543607633901e-06,
|
| 289 |
+
"loss": 0.7064,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.64,
|
| 294 |
+
"learning_rate": 5.374512620562282e-06,
|
| 295 |
+
"loss": 0.7128,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.68,
|
| 300 |
+
"learning_rate": 4.861481633490662e-06,
|
| 301 |
+
"loss": 0.6573,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.71,
|
| 306 |
+
"learning_rate": 4.348450646419044e-06,
|
| 307 |
+
"loss": 0.6695,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.74,
|
| 312 |
+
"learning_rate": 3.835419659347425e-06,
|
| 313 |
+
"loss": 0.6928,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.78,
|
| 318 |
+
"learning_rate": 3.3223886722758055e-06,
|
| 319 |
+
"loss": 0.6625,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.81,
|
| 324 |
+
"learning_rate": 2.809357685204186e-06,
|
| 325 |
+
"loss": 0.6704,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.85,
|
| 330 |
+
"learning_rate": 2.2963266981325674e-06,
|
| 331 |
+
"loss": 0.6487,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.88,
|
| 336 |
+
"learning_rate": 1.783295711060948e-06,
|
| 337 |
+
"loss": 0.6707,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.92,
|
| 342 |
+
"learning_rate": 1.270264723989329e-06,
|
| 343 |
+
"loss": 0.6782,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.95,
|
| 348 |
+
"learning_rate": 7.572337369177098e-07,
|
| 349 |
+
"loss": 0.6796,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.98,
|
| 354 |
+
"learning_rate": 2.442027498460907e-07,
|
| 355 |
+
"loss": 0.6222,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.0,
|
| 360 |
+
"step": 29238,
|
| 361 |
+
"total_flos": 4.583876744068301e+16,
|
| 362 |
+
"train_loss": 0.9686727332664389,
|
| 363 |
+
"train_runtime": 18778.1209,
|
| 364 |
+
"train_samples_per_second": 9.342,
|
| 365 |
+
"train_steps_per_second": 1.557
|
| 366 |
+
}
|
| 367 |
+
],
|
| 368 |
+
"max_steps": 29238,
|
| 369 |
+
"num_train_epochs": 2,
|
| 370 |
+
"total_flos": 4.583876744068301e+16,
|
| 371 |
+
"trial_name": null,
|
| 372 |
+
"trial_params": null
|
| 373 |
+
}
|