Training in progress, step 100000
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:d78af7cfd1d88085a1ccf60dc6d4cec261f96863bcbc84f478cc5c3f0d90532b
|
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:ba71463a9d2a51aabd38319496d9f1d2901de8a7253a522ccad9877a044e0db0
|
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:cddf50a261b74b5aed60e5ada33af74ecf1ad13ca33db42ba0282b8209958d2e
|
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:b46697141d9e273624a3e0eb1ae0137c43929b72e01e18fd5383e9cd1eab5083
|
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:f1dfb335dd0c8f788eec17fae022cc5c997eff0e40a083ae824a1683bd77948a
|
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:d9e07f409fabb71d925bf2c127177a5a463dbeed21221f7026cb8cae34d23cb1
|
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:ef91fc55d3c649f341dc4e4fd1bfc6c1731bb3a15a2219e5976cdb46ec957ede
|
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:d7777faf81f544c5d8594c8e24de11548d9f44dc6f6bb6a05cdfabc0ba56f6dc
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1146,6 +1146,66 @@
|
|
1146 |
"learning_rate": 0.00013790552705787178,
|
1147 |
"loss": 0.353,
|
1148 |
"step": 95000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1149 |
}
|
1150 |
],
|
1151 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.7021216840707738,
|
5 |
+
"global_step": 100000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1146 |
"learning_rate": 0.00013790552705787178,
|
1147 |
"loss": 0.353,
|
1148 |
"step": 95000
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 1.63,
|
1152 |
+
"learning_rate": 0.0001377816786347662,
|
1153 |
+
"loss": 0.3526,
|
1154 |
+
"step": 95500
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 1.63,
|
1158 |
+
"learning_rate": 0.00013765725992981992,
|
1159 |
+
"loss": 0.3527,
|
1160 |
+
"step": 96000
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 1.64,
|
1164 |
+
"learning_rate": 0.00013753227217099532,
|
1165 |
+
"loss": 0.3528,
|
1166 |
+
"step": 96500
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 1.65,
|
1170 |
+
"learning_rate": 0.0001374067165918711,
|
1171 |
+
"loss": 0.3524,
|
1172 |
+
"step": 97000
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 1.66,
|
1176 |
+
"learning_rate": 0.00013728059443163013,
|
1177 |
+
"loss": 0.352,
|
1178 |
+
"step": 97500
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.67,
|
1182 |
+
"learning_rate": 0.00013715390693504724,
|
1183 |
+
"loss": 0.3519,
|
1184 |
+
"step": 98000
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 1.68,
|
1188 |
+
"learning_rate": 0.00013702665535247687,
|
1189 |
+
"loss": 0.3519,
|
1190 |
+
"step": 98500
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 1.69,
|
1194 |
+
"learning_rate": 0.00013689884093984076,
|
1195 |
+
"loss": 0.3519,
|
1196 |
+
"step": 99000
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 1.69,
|
1200 |
+
"learning_rate": 0.00013677072227018223,
|
1201 |
+
"loss": 0.3526,
|
1202 |
+
"step": 99500
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 1.7,
|
1206 |
+
"learning_rate": 0.00013664178710672204,
|
1207 |
+
"loss": 0.3517,
|
1208 |
+
"step": 100000
|
1209 |
}
|
1210 |
],
|
1211 |
"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:ba71463a9d2a51aabd38319496d9f1d2901de8a7253a522ccad9877a044e0db0
|
3 |
size 201355195
|