Training in progress, step 100000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- pytorch_model.bin +1 -1
- runs/May15_17-32-55_19599b9fb4f0/events.out.tfevents.1684173637.19599b9fb4f0.1168.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d082cb4b72cfdb4254a34e305011b454d31bb30dbd27c42aa24b574147c540e9
|
3 |
size 3871544599
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cdaa8da95e94cc1e97cd08cfc56ef217e59ee59f7687ac8419775c4bc80984
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7953899316608ec70beb2202d2f7cbae5152dd2b0e53df4aac9eef077d77e70d
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12799c4bd0d2d9858c0d7696e12e998a91a87a7a92ec0bf0a40a0e286e746cf8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1158,11 +1158,59 @@
|
|
1158 |
"learning_rate": 4.943485406239044e-06,
|
1159 |
"loss": 1.5726,
|
1160 |
"step": 96000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1161 |
}
|
1162 |
],
|
1163 |
"max_steps": 1415120,
|
1164 |
"num_train_epochs": 10,
|
1165 |
-
"total_flos": 4.
|
1166 |
"trial_name": null,
|
1167 |
"trial_params": null
|
1168 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7066538526768048,
|
5 |
+
"global_step": 100000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1158 |
"learning_rate": 4.943485406239044e-06,
|
1159 |
"loss": 1.5726,
|
1160 |
"step": 96000
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 0.68,
|
1164 |
+
"learning_rate": 4.942897190956574e-06,
|
1165 |
+
"loss": 1.5713,
|
1166 |
+
"step": 96500
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.69,
|
1170 |
+
"learning_rate": 4.9423059657304774e-06,
|
1171 |
+
"loss": 1.5863,
|
1172 |
+
"step": 97000
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.69,
|
1176 |
+
"learning_rate": 4.941711731289216e-06,
|
1177 |
+
"loss": 1.6008,
|
1178 |
+
"step": 97500
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.69,
|
1182 |
+
"learning_rate": 4.941115685852782e-06,
|
1183 |
+
"loss": 1.609,
|
1184 |
+
"step": 98000
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 0.7,
|
1188 |
+
"learning_rate": 4.9405154411961575e-06,
|
1189 |
+
"loss": 1.6016,
|
1190 |
+
"step": 98500
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 0.7,
|
1194 |
+
"learning_rate": 4.939913399034342e-06,
|
1195 |
+
"loss": 1.5992,
|
1196 |
+
"step": 99000
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 0.7,
|
1200 |
+
"learning_rate": 4.939307147114736e-06,
|
1201 |
+
"loss": 1.6742,
|
1202 |
+
"step": 99500
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.71,
|
1206 |
+
"learning_rate": 4.938697889674869e-06,
|
1207 |
+
"loss": 1.689,
|
1208 |
+
"step": 100000
|
1209 |
}
|
1210 |
],
|
1211 |
"max_steps": 1415120,
|
1212 |
"num_train_epochs": 10,
|
1213 |
+
"total_flos": 4.83002072753111e+16,
|
1214 |
"trial_name": null,
|
1215 |
"trial_params": null
|
1216 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:112a525385ef4b2920ca2e4ee2218f98e8c63380cb36d3d525690ca7a1c7da52
|
3 |
size 1944201353
|
runs/May15_17-32-55_19599b9fb4f0/events.out.tfevents.1684173637.19599b9fb4f0.1168.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef30ab0bad199cc307dca07844477268dc4ed31ab93798a295ba8e4bfd265751
|
3 |
+
size 9583
|