Upload 10 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +176 -104
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2681380253
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7e9df408ca2438a9552a78c68d2e86f3adbe8740cc4804a95b7ca8f629c596f
|
| 3 |
size 2681380253
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340711725
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc0c0d6bac550fffbecbbb43f75c7e4426a1e156611b0ebaa47e933558d93888
|
| 3 |
size 1340711725
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15523
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:406b9393c993b3cb066618b85d5b99ae8ed0158a4135bd7e8ab5421523207788
|
| 3 |
size 15523
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9be1c2e449227164add711a419ee9d822a66d379ed17b9fb1f1d4d3df3b9d8aa
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -2,175 +2,247 @@
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 10.0,
|
| 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": 0.
|
| 12 |
-
"learning_rate": 1.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"
|
| 19 |
-
"eval_loss": 0.
|
| 20 |
-
"eval_runtime":
|
| 21 |
-
"eval_samples_per_second":
|
| 22 |
-
"eval_steps_per_second":
|
| 23 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.65,
|
| 27 |
-
"learning_rate": 1.
|
| 28 |
-
"loss": 0.
|
| 29 |
-
"step":
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
-
"
|
| 34 |
-
"eval_loss": 0.
|
| 35 |
-
"eval_runtime":
|
| 36 |
-
"eval_samples_per_second":
|
| 37 |
-
"eval_steps_per_second":
|
| 38 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 2.47,
|
| 42 |
-
"learning_rate": 1.
|
| 43 |
-
"loss": 0.
|
| 44 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 3.0,
|
| 48 |
-
"
|
| 49 |
-
"eval_loss": 0.
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second":
|
| 53 |
-
"step":
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 3.
|
| 57 |
-
"learning_rate": 1.
|
| 58 |
-
"loss": 0.
|
| 59 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 4.0,
|
| 63 |
-
"
|
| 64 |
-
"eval_loss": 0.
|
| 65 |
-
"eval_runtime":
|
| 66 |
-
"eval_samples_per_second":
|
| 67 |
-
"eval_steps_per_second":
|
| 68 |
-
"step":
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 4.12,
|
| 72 |
-
"learning_rate": 1.
|
| 73 |
-
"loss": 0.
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 4.
|
| 78 |
-
"learning_rate": 1.
|
| 79 |
-
"loss": 0.
|
| 80 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 5.0,
|
| 84 |
-
"
|
| 85 |
-
"eval_loss": 0.
|
| 86 |
-
"eval_runtime":
|
| 87 |
-
"eval_samples_per_second":
|
| 88 |
-
"eval_steps_per_second":
|
| 89 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 5.77,
|
| 93 |
-
"learning_rate": 8.
|
| 94 |
-
"loss": 0.
|
| 95 |
-
"step":
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 6.0,
|
| 99 |
-
"
|
| 100 |
-
"eval_loss": 0.
|
| 101 |
-
"eval_runtime":
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
-
"step":
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 6.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 7.0,
|
| 114 |
-
"
|
| 115 |
-
"eval_loss": 0.
|
| 116 |
-
"eval_runtime":
|
| 117 |
-
"eval_samples_per_second":
|
| 118 |
-
"eval_steps_per_second":
|
| 119 |
-
"step":
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"epoch": 7.
|
| 123 |
-
"learning_rate": 5.
|
| 124 |
-
"loss": 0.
|
| 125 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 8.0,
|
| 129 |
-
"
|
| 130 |
-
"eval_loss": 0.
|
| 131 |
-
"eval_runtime":
|
| 132 |
-
"eval_samples_per_second":
|
| 133 |
-
"eval_steps_per_second":
|
| 134 |
-
"step":
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 8.24,
|
| 138 |
-
"learning_rate": 3.
|
| 139 |
-
"loss": 0.
|
| 140 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 9.0,
|
| 144 |
-
"
|
| 145 |
-
"eval_loss": 0.
|
| 146 |
-
"eval_runtime":
|
| 147 |
-
"eval_samples_per_second":
|
| 148 |
-
"eval_steps_per_second":
|
| 149 |
-
"step":
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 9.
|
| 153 |
-
"learning_rate": 1.
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch": 9.
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 10.0,
|
| 165 |
-
"
|
| 166 |
-
"eval_loss": 0.
|
| 167 |
-
"eval_runtime":
|
| 168 |
-
"eval_samples_per_second":
|
| 169 |
-
"eval_steps_per_second":
|
| 170 |
-
"step":
|
| 171 |
}
|
| 172 |
],
|
| 173 |
-
"max_steps":
|
| 174 |
"num_train_epochs": 10,
|
| 175 |
"total_flos": 1.8083196174016512e+17,
|
| 176 |
"trial_name": null,
|
|
|
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 10.0,
|
| 5 |
+
"global_step": 12130,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.41,
|
| 12 |
+
"learning_rate": 1.9175597691673537e-05,
|
| 13 |
+
"loss": 0.2206,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.82,
|
| 18 |
+
"learning_rate": 1.8351195383347076e-05,
|
| 19 |
+
"loss": 0.1699,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
{
|
| 23 |
"epoch": 1.0,
|
| 24 |
+
"eval_accuracy": 0.9739486703772418,
|
| 25 |
+
"eval_loss": 0.07855913788080215,
|
| 26 |
+
"eval_runtime": 265.3419,
|
| 27 |
+
"eval_samples_per_second": 292.513,
|
| 28 |
+
"eval_steps_per_second": 4.571,
|
| 29 |
+
"step": 1213
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.24,
|
| 33 |
+
"learning_rate": 1.752679307502061e-05,
|
| 34 |
+
"loss": 0.118,
|
| 35 |
+
"step": 1500
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 1.65,
|
| 39 |
+
"learning_rate": 1.6702390766694146e-05,
|
| 40 |
+
"loss": 0.0991,
|
| 41 |
+
"step": 2000
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 2.0,
|
| 45 |
+
"eval_accuracy": 0.9866393527107813,
|
| 46 |
+
"eval_loss": 0.04234647750854492,
|
| 47 |
+
"eval_runtime": 267.207,
|
| 48 |
+
"eval_samples_per_second": 290.471,
|
| 49 |
+
"eval_steps_per_second": 4.54,
|
| 50 |
+
"step": 2426
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.06,
|
| 54 |
+
"learning_rate": 1.5877988458367685e-05,
|
| 55 |
+
"loss": 0.0979,
|
| 56 |
+
"step": 2500
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 2.47,
|
| 60 |
+
"learning_rate": 1.5053586150041222e-05,
|
| 61 |
+
"loss": 0.0573,
|
| 62 |
+
"step": 3000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.89,
|
| 66 |
+
"learning_rate": 1.4229183841714757e-05,
|
| 67 |
+
"loss": 0.0653,
|
| 68 |
+
"step": 3500
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 3.0,
|
| 72 |
+
"eval_accuracy": 0.9903241599670171,
|
| 73 |
+
"eval_loss": 0.029069583863019943,
|
| 74 |
+
"eval_runtime": 266.0985,
|
| 75 |
+
"eval_samples_per_second": 291.681,
|
| 76 |
+
"eval_steps_per_second": 4.558,
|
| 77 |
+
"step": 3639
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 3.3,
|
| 81 |
+
"learning_rate": 1.3404781533388294e-05,
|
| 82 |
+
"loss": 0.0492,
|
| 83 |
+
"step": 4000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.71,
|
| 87 |
+
"learning_rate": 1.2580379225061831e-05,
|
| 88 |
+
"loss": 0.0442,
|
| 89 |
+
"step": 4500
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 4.0,
|
| 93 |
+
"eval_accuracy": 0.9942151102865389,
|
| 94 |
+
"eval_loss": 0.01643509231507778,
|
| 95 |
+
"eval_runtime": 266.3375,
|
| 96 |
+
"eval_samples_per_second": 291.42,
|
| 97 |
+
"eval_steps_per_second": 4.554,
|
| 98 |
+
"step": 4852
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 4.12,
|
| 102 |
+
"learning_rate": 1.1755976916735368e-05,
|
| 103 |
+
"loss": 0.0361,
|
| 104 |
+
"step": 5000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 4.53,
|
| 108 |
+
"learning_rate": 1.0931574608408903e-05,
|
| 109 |
+
"loss": 0.0296,
|
| 110 |
+
"step": 5500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.95,
|
| 114 |
+
"learning_rate": 1.0107172300082442e-05,
|
| 115 |
+
"loss": 0.0315,
|
| 116 |
+
"step": 6000
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 5.0,
|
| 120 |
+
"eval_accuracy": 0.9958256029684601,
|
| 121 |
+
"eval_loss": 0.010281954891979694,
|
| 122 |
+
"eval_runtime": 266.335,
|
| 123 |
+
"eval_samples_per_second": 291.422,
|
| 124 |
+
"eval_steps_per_second": 4.554,
|
| 125 |
+
"step": 6065
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.36,
|
| 129 |
+
"learning_rate": 9.282769991755977e-06,
|
| 130 |
+
"loss": 0.0189,
|
| 131 |
+
"step": 6500
|
| 132 |
},
|
| 133 |
{
|
| 134 |
"epoch": 5.77,
|
| 135 |
+
"learning_rate": 8.458367683429514e-06,
|
| 136 |
+
"loss": 0.0207,
|
| 137 |
+
"step": 7000
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 6.0,
|
| 141 |
+
"eval_accuracy": 0.9973587920016491,
|
| 142 |
+
"eval_loss": 0.0071565331891179085,
|
| 143 |
+
"eval_runtime": 266.5437,
|
| 144 |
+
"eval_samples_per_second": 291.194,
|
| 145 |
+
"eval_steps_per_second": 4.551,
|
| 146 |
+
"step": 7278
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 6.18,
|
| 150 |
+
"learning_rate": 7.633965375103051e-06,
|
| 151 |
+
"loss": 0.0171,
|
| 152 |
+
"step": 7500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.6,
|
| 156 |
+
"learning_rate": 6.809563066776587e-06,
|
| 157 |
+
"loss": 0.0133,
|
| 158 |
+
"step": 8000
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 7.0,
|
| 162 |
+
"eval_accuracy": 0.9979514533085961,
|
| 163 |
+
"eval_loss": 0.004438882227987051,
|
| 164 |
+
"eval_runtime": 266.6565,
|
| 165 |
+
"eval_samples_per_second": 291.071,
|
| 166 |
+
"eval_steps_per_second": 4.549,
|
| 167 |
+
"step": 8491
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 7.01,
|
| 171 |
+
"learning_rate": 5.9851607584501235e-06,
|
| 172 |
+
"loss": 0.0152,
|
| 173 |
+
"step": 8500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 7.42,
|
| 177 |
+
"learning_rate": 5.1607584501236605e-06,
|
| 178 |
+
"loss": 0.0082,
|
| 179 |
+
"step": 9000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 7.83,
|
| 183 |
+
"learning_rate": 4.3363561417971975e-06,
|
| 184 |
+
"loss": 0.0109,
|
| 185 |
+
"step": 9500
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 8.0,
|
| 189 |
+
"eval_accuracy": 0.9985183467326324,
|
| 190 |
+
"eval_loss": 0.0034066857770085335,
|
| 191 |
+
"eval_runtime": 266.0238,
|
| 192 |
+
"eval_samples_per_second": 291.763,
|
| 193 |
+
"eval_steps_per_second": 4.56,
|
| 194 |
+
"step": 9704
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 8.24,
|
| 198 |
+
"learning_rate": 3.5119538334707345e-06,
|
| 199 |
+
"loss": 0.0077,
|
| 200 |
+
"step": 10000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.66,
|
| 204 |
+
"learning_rate": 2.6875515251442706e-06,
|
| 205 |
+
"loss": 0.0059,
|
| 206 |
+
"step": 10500
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 9.0,
|
| 210 |
+
"eval_accuracy": 0.9989177489177489,
|
| 211 |
+
"eval_loss": 0.0024579998571425676,
|
| 212 |
+
"eval_runtime": 264.7367,
|
| 213 |
+
"eval_samples_per_second": 293.182,
|
| 214 |
+
"eval_steps_per_second": 4.582,
|
| 215 |
+
"step": 10917
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 9.07,
|
| 219 |
+
"learning_rate": 1.8631492168178072e-06,
|
| 220 |
+
"loss": 0.0077,
|
| 221 |
+
"step": 11000
|
| 222 |
},
|
| 223 |
{
|
| 224 |
+
"epoch": 9.48,
|
| 225 |
+
"learning_rate": 1.038746908491344e-06,
|
| 226 |
+
"loss": 0.0033,
|
| 227 |
+
"step": 11500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 9.89,
|
| 231 |
+
"learning_rate": 2.1434460016488048e-07,
|
| 232 |
+
"loss": 0.0043,
|
| 233 |
+
"step": 12000
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 10.0,
|
| 237 |
+
"eval_accuracy": 0.9992398474541332,
|
| 238 |
+
"eval_loss": 0.0018210469279438257,
|
| 239 |
+
"eval_runtime": 264.6034,
|
| 240 |
+
"eval_samples_per_second": 293.33,
|
| 241 |
+
"eval_steps_per_second": 4.584,
|
| 242 |
+
"step": 12130
|
| 243 |
}
|
| 244 |
],
|
| 245 |
+
"max_steps": 12130,
|
| 246 |
"num_train_epochs": 10,
|
| 247 |
"total_flos": 1.8083196174016512e+17,
|
| 248 |
"trial_name": null,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:767854cf2766e62aff85fa5b0170bb26f740c4b5f2388312badb7574061ef623
|
| 3 |
size 3439
|