Upload 8 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +105 -3
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6192502837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c84df6dad1bbebe536721901b19df5684b5b61bd6504a7973c7784e2cd3d6906
|
| 3 |
size 6192502837
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3134031497
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e6f1358759d56ec7dd838051a9897376d5783b670a8aaa910a055f074e80ab8
|
| 3 |
size 3134031497
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b2ced2b38eecc35ed03eeaeb5c0a49167957bb55459f4813d83c507af091fc81
|
| 3 |
size 14503
|
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:fa9c592a1519044a351c3d8ea017a6bc5f46ea0bc295892e6ac3489a0ae5a94b
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 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,
|
|
@@ -84,11 +84,113 @@
|
|
| 84 |
"learning_rate": 4.791399229781772e-05,
|
| 85 |
"loss": 0.1452,
|
| 86 |
"step": 6500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 87 |
}
|
| 88 |
],
|
| 89 |
"max_steps": 155800,
|
| 90 |
"num_train_epochs": 100,
|
| 91 |
-
"total_flos":
|
| 92 |
"trial_name": null,
|
| 93 |
"trial_params": null
|
| 94 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.624639076034649,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 84 |
"learning_rate": 4.791399229781772e-05,
|
| 85 |
"loss": 0.1452,
|
| 86 |
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.49,
|
| 90 |
+
"learning_rate": 4.775353016688062e-05,
|
| 91 |
+
"loss": 0.1324,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.81,
|
| 96 |
+
"learning_rate": 4.759306803594352e-05,
|
| 97 |
+
"loss": 0.1362,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 5.13,
|
| 102 |
+
"learning_rate": 4.743260590500642e-05,
|
| 103 |
+
"loss": 0.1275,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.45,
|
| 108 |
+
"learning_rate": 4.727214377406932e-05,
|
| 109 |
+
"loss": 0.114,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.77,
|
| 114 |
+
"learning_rate": 4.711168164313222e-05,
|
| 115 |
+
"loss": 0.1171,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.1,
|
| 120 |
+
"learning_rate": 4.695121951219512e-05,
|
| 121 |
+
"loss": 0.1104,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.42,
|
| 126 |
+
"learning_rate": 4.679075738125803e-05,
|
| 127 |
+
"loss": 0.0965,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.74,
|
| 132 |
+
"learning_rate": 4.663029525032093e-05,
|
| 133 |
+
"loss": 0.0998,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 7.06,
|
| 138 |
+
"learning_rate": 4.646983311938383e-05,
|
| 139 |
+
"loss": 0.0983,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 7.38,
|
| 144 |
+
"learning_rate": 4.630937098844673e-05,
|
| 145 |
+
"loss": 0.0817,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 7.7,
|
| 150 |
+
"learning_rate": 4.614890885750963e-05,
|
| 151 |
+
"loss": 0.0854,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 8.02,
|
| 156 |
+
"learning_rate": 4.598844672657253e-05,
|
| 157 |
+
"loss": 0.0867,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.34,
|
| 162 |
+
"learning_rate": 4.582798459563543e-05,
|
| 163 |
+
"loss": 0.0698,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.66,
|
| 168 |
+
"learning_rate": 4.566752246469833e-05,
|
| 169 |
+
"loss": 0.0722,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.98,
|
| 174 |
+
"learning_rate": 4.550706033376124e-05,
|
| 175 |
+
"loss": 0.0752,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.3,
|
| 180 |
+
"learning_rate": 4.534659820282414e-05,
|
| 181 |
+
"loss": 0.0593,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 9.62,
|
| 186 |
+
"learning_rate": 4.518613607188704e-05,
|
| 187 |
+
"loss": 0.0617,
|
| 188 |
+
"step": 15000
|
| 189 |
}
|
| 190 |
],
|
| 191 |
"max_steps": 155800,
|
| 192 |
"num_train_epochs": 100,
|
| 193 |
+
"total_flos": 5.217329001215232e+17,
|
| 194 |
"trial_name": null,
|
| 195 |
"trial_params": null
|
| 196 |
}
|