Training in progress, step 185000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +62 -2
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 402588883
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:229352383c7cde90a65c21692c2128f1c8f8c3bb6f1e9f91686274b5bcf4b171
|
3 |
size 402588883
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6317c3cd012f0729e4711bf7161363ea7dc1733f5b07a291a37c9271e90ddba
|
3 |
size 201355195
|
last-checkpoint/rng_state_0.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:b57ddf743a4e282eaef4cdd8f8757bc04e131d94d9efdd22ab4a819f66275ead
|
3 |
size 14503
|
last-checkpoint/rng_state_1.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 sha256:9e0f810052d368ca06887b3fe03cfb2d1181b282ef3a7040b1eec6960cc16b74
|
3 |
size 14503
|
last-checkpoint/rng_state_2.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 sha256:1b436664e5fefa47b0db00f7183e4b9fdfbd0234b8e1cfd2a46018b6725a160c
|
3 |
size 14503
|
last-checkpoint/rng_state_3.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 sha256:6520bae9625d2abe5826b5af16ea4a3c098104ffd6f54199c949feb7fa9be6d1
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:803427c23daba4c210b9c9fff7cc834a7256ef5f4b3188312c1c88f78b16ad3c
|
3 |
size 559
|
last-checkpoint/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 sha256:1941234b7a3c30ddd974eb5f1ff2e108094e196c5323caf8c5cf8f689b6977a6
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -2166,6 +2166,66 @@
|
|
2166 |
"learning_rate": 0.00010983399650235882,
|
2167 |
"loss": 0.3384,
|
2168 |
"step": 180000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2169 |
}
|
2170 |
],
|
2171 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.1489349026816793,
|
5 |
+
"global_step": 185000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
2166 |
"learning_rate": 0.00010983399650235882,
|
2167 |
"loss": 0.3384,
|
2168 |
"step": 180000
|
2169 |
+
},
|
2170 |
+
{
|
2171 |
+
"epoch": 3.07,
|
2172 |
+
"learning_rate": 0.00010963491130044959,
|
2173 |
+
"loss": 0.3385,
|
2174 |
+
"step": 180500
|
2175 |
+
},
|
2176 |
+
{
|
2177 |
+
"epoch": 3.08,
|
2178 |
+
"learning_rate": 0.00010943553361392991,
|
2179 |
+
"loss": 0.339,
|
2180 |
+
"step": 181000
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 3.09,
|
2184 |
+
"learning_rate": 0.00010923586541057708,
|
2185 |
+
"loss": 0.3388,
|
2186 |
+
"step": 181500
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 3.1,
|
2190 |
+
"learning_rate": 0.00010903590866103563,
|
2191 |
+
"loss": 0.3386,
|
2192 |
+
"step": 182000
|
2193 |
+
},
|
2194 |
+
{
|
2195 |
+
"epoch": 3.11,
|
2196 |
+
"learning_rate": 0.00010883606611012889,
|
2197 |
+
"loss": 0.3387,
|
2198 |
+
"step": 182500
|
2199 |
+
},
|
2200 |
+
{
|
2201 |
+
"epoch": 3.11,
|
2202 |
+
"learning_rate": 0.00010863553875873429,
|
2203 |
+
"loss": 0.3383,
|
2204 |
+
"step": 183000
|
2205 |
+
},
|
2206 |
+
{
|
2207 |
+
"epoch": 3.12,
|
2208 |
+
"learning_rate": 0.00010843472878613276,
|
2209 |
+
"loss": 0.3387,
|
2210 |
+
"step": 183500
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 3.13,
|
2214 |
+
"learning_rate": 0.0001082336381742377,
|
2215 |
+
"loss": 0.3381,
|
2216 |
+
"step": 184000
|
2217 |
+
},
|
2218 |
+
{
|
2219 |
+
"epoch": 3.14,
|
2220 |
+
"learning_rate": 0.00010803226890773223,
|
2221 |
+
"loss": 0.3381,
|
2222 |
+
"step": 184500
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 3.15,
|
2226 |
+
"learning_rate": 0.00010783062297404974,
|
2227 |
+
"loss": 0.338,
|
2228 |
+
"step": 185000
|
2229 |
}
|
2230 |
],
|
2231 |
"max_steps": 500000,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201355195
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6317c3cd012f0729e4711bf7161363ea7dc1733f5b07a291a37c9271e90ddba
|
3 |
size 201355195
|