Commit
•
80ce11b
1
Parent(s):
4b574e3
End of training
Browse files- all_results.json +22 -0
- eval_results.json +10 -0
- generated_predictions.txt +0 -0
- generation_config.json +0 -1
- predict_results.json +9 -0
- runs/May12_08-16-47_2a8fe28c8a8c/events.out.tfevents.1683888003.2a8fe28c8a8c.266.4 +3 -0
- train_results.json +8 -0
- trainer_state.json +265 -0
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.07766503820618816,
|
| 4 |
+
"eval_f1": 0.050057538932255674,
|
| 5 |
+
"eval_loss": 1.0055056810379028,
|
| 6 |
+
"eval_runtime": 127.6389,
|
| 7 |
+
"eval_samples": 7983,
|
| 8 |
+
"eval_samples_per_second": 62.544,
|
| 9 |
+
"eval_steps_per_second": 1.959,
|
| 10 |
+
"predict_accuracy": 0.07766503820618816,
|
| 11 |
+
"predict_f1": 0.050057538932255674,
|
| 12 |
+
"predict_loss": 1.0055056810379028,
|
| 13 |
+
"predict_runtime": 124.2225,
|
| 14 |
+
"predict_samples": 7983,
|
| 15 |
+
"predict_samples_per_second": 64.264,
|
| 16 |
+
"predict_steps_per_second": 2.013,
|
| 17 |
+
"train_loss": 1.2059516395565477,
|
| 18 |
+
"train_runtime": 8228.1791,
|
| 19 |
+
"train_samples": 108647,
|
| 20 |
+
"train_samples_per_second": 39.613,
|
| 21 |
+
"train_steps_per_second": 2.476
|
| 22 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.07766503820618816,
|
| 4 |
+
"eval_f1": 0.050057538932255674,
|
| 5 |
+
"eval_loss": 1.0055056810379028,
|
| 6 |
+
"eval_runtime": 127.6389,
|
| 7 |
+
"eval_samples": 7983,
|
| 8 |
+
"eval_samples_per_second": 62.544,
|
| 9 |
+
"eval_steps_per_second": 1.959
|
| 10 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_accuracy": 0.07766503820618816,
|
| 3 |
+
"predict_f1": 0.050057538932255674,
|
| 4 |
+
"predict_loss": 1.0055056810379028,
|
| 5 |
+
"predict_runtime": 124.2225,
|
| 6 |
+
"predict_samples": 7983,
|
| 7 |
+
"predict_samples_per_second": 64.264,
|
| 8 |
+
"predict_steps_per_second": 2.013
|
| 9 |
+
}
|
runs/May12_08-16-47_2a8fe28c8a8c/events.out.tfevents.1683888003.2a8fe28c8a8c.266.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82e07e445c431433937581df8341e26d12052d803a7a6ec11c2ec330808eba02
|
| 3 |
+
size 416
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 1.2059516395565477,
|
| 4 |
+
"train_runtime": 8228.1791,
|
| 5 |
+
"train_samples": 108647,
|
| 6 |
+
"train_samples_per_second": 39.613,
|
| 7 |
+
"train_steps_per_second": 2.476
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,265 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 20373,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.882079900826349e-05,
|
| 13 |
+
"loss": 1.4754,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 4.539443723136697e-05,
|
| 19 |
+
"loss": 1.3547,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.22,
|
| 24 |
+
"learning_rate": 4.004414420573958e-05,
|
| 25 |
+
"loss": 1.3184,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.29,
|
| 30 |
+
"learning_rate": 3.3274645598733375e-05,
|
| 31 |
+
"loss": 1.3174,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.37,
|
| 36 |
+
"learning_rate": 2.5724549368023616e-05,
|
| 37 |
+
"loss": 1.2904,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.44,
|
| 42 |
+
"learning_rate": 1.8106101990647016e-05,
|
| 43 |
+
"loss": 1.2746,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.52,
|
| 48 |
+
"learning_rate": 1.1137997922835163e-05,
|
| 49 |
+
"loss": 1.2553,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.59,
|
| 54 |
+
"learning_rate": 5.477580782771013e-06,
|
| 55 |
+
"loss": 1.2449,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.66,
|
| 60 |
+
"learning_rate": 1.6588321308710408e-06,
|
| 61 |
+
"loss": 1.2664,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.74,
|
| 66 |
+
"learning_rate": 4.1997742936272785e-08,
|
| 67 |
+
"loss": 1.2583,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.81,
|
| 72 |
+
"learning_rate": 7.796034360648269e-07,
|
| 73 |
+
"loss": 1.2692,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.88,
|
| 78 |
+
"learning_rate": 3.802066381068883e-06,
|
| 79 |
+
"loss": 1.2549,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.96,
|
| 84 |
+
"learning_rate": 8.8242592737696e-06,
|
| 85 |
+
"loss": 1.2621,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.03,
|
| 90 |
+
"learning_rate": 1.5372408126985777e-05,
|
| 91 |
+
"loss": 1.2511,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.1,
|
| 96 |
+
"learning_rate": 2.282878625097739e-05,
|
| 97 |
+
"loss": 1.2055,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.18,
|
| 102 |
+
"learning_rate": 3.0489988167458534e-05,
|
| 103 |
+
"loss": 1.2219,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.25,
|
| 108 |
+
"learning_rate": 3.76332861246046e-05,
|
| 109 |
+
"loss": 1.2093,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.33,
|
| 114 |
+
"learning_rate": 4.3584809399588655e-05,
|
| 115 |
+
"loss": 1.2115,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.4,
|
| 120 |
+
"learning_rate": 4.778311462055443e-05,
|
| 121 |
+
"loss": 1.2122,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.47,
|
| 126 |
+
"learning_rate": 4.983215013308785e-05,
|
| 127 |
+
"loss": 1.1913,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.55,
|
| 132 |
+
"learning_rate": 4.953861796051032e-05,
|
| 133 |
+
"loss": 1.1973,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.62,
|
| 138 |
+
"learning_rate": 4.6930208777142614e-05,
|
| 139 |
+
"loss": 1.2112,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.69,
|
| 144 |
+
"learning_rate": 4.225298967865532e-05,
|
| 145 |
+
"loss": 1.1787,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.77,
|
| 150 |
+
"learning_rate": 3.59481911770088e-05,
|
| 151 |
+
"loss": 1.2036,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.84,
|
| 156 |
+
"learning_rate": 2.8610583243870337e-05,
|
| 157 |
+
"loss": 1.1818,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.91,
|
| 162 |
+
"learning_rate": 2.09323670433783e-05,
|
| 163 |
+
"loss": 1.1674,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.99,
|
| 168 |
+
"learning_rate": 1.363787538820378e-05,
|
| 169 |
+
"loss": 1.1715,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.06,
|
| 174 |
+
"learning_rate": 7.4152420218663585e-06,
|
| 175 |
+
"loss": 1.122,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.14,
|
| 180 |
+
"learning_rate": 2.8514857793098454e-06,
|
| 181 |
+
"loss": 1.0968,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.21,
|
| 186 |
+
"learning_rate": 3.771335315155861e-07,
|
| 187 |
+
"loss": 1.1392,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.28,
|
| 192 |
+
"learning_rate": 2.2560596844390935e-07,
|
| 193 |
+
"loss": 1.1046,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.36,
|
| 198 |
+
"learning_rate": 2.4111976063067728e-06,
|
| 199 |
+
"loss": 1.15,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.43,
|
| 204 |
+
"learning_rate": 6.727728298952271e-06,
|
| 205 |
+
"loss": 1.1218,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.5,
|
| 210 |
+
"learning_rate": 1.2767993464490152e-05,
|
| 211 |
+
"loss": 1.1315,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.58,
|
| 216 |
+
"learning_rate": 1.9962178169036043e-05,
|
| 217 |
+
"loss": 1.119,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.65,
|
| 222 |
+
"learning_rate": 2.7631611233523096e-05,
|
| 223 |
+
"loss": 1.1307,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.72,
|
| 228 |
+
"learning_rate": 3.505278841189536e-05,
|
| 229 |
+
"loss": 1.144,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.8,
|
| 234 |
+
"learning_rate": 4.152562494506565e-05,
|
| 235 |
+
"loss": 1.1165,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.87,
|
| 240 |
+
"learning_rate": 4.643949881229301e-05,
|
| 241 |
+
"loss": 1.1387,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.95,
|
| 246 |
+
"learning_rate": 4.933085441857718e-05,
|
| 247 |
+
"loss": 1.1241,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.0,
|
| 252 |
+
"step": 20373,
|
| 253 |
+
"total_flos": 5.063263464534835e+16,
|
| 254 |
+
"train_loss": 1.2059516395565477,
|
| 255 |
+
"train_runtime": 8228.1791,
|
| 256 |
+
"train_samples_per_second": 39.613,
|
| 257 |
+
"train_steps_per_second": 2.476
|
| 258 |
+
}
|
| 259 |
+
],
|
| 260 |
+
"max_steps": 20373,
|
| 261 |
+
"num_train_epochs": 3,
|
| 262 |
+
"total_flos": 5.063263464534835e+16,
|
| 263 |
+
"trial_name": null,
|
| 264 |
+
"trial_params": null
|
| 265 |
+
}
|