Training in progress, step 104000
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 sha256:5b6b72e44546364141ee724a3720f7fcd3e0187baca4188905097793e58f73cf
|
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 sha256:06e0f8fd34ad9689e90c51a6ce416bb3efe00164a6779e3a86f8096cf6b0c3e6
|
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 sha256:406220ea58b0ef58e4c479dbacbea0d151a94a8fec8c33f3207fb059c4aaf735
|
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:c168c2a8f00ea281d9279e79fc22bf9baa2663e805bc63f10cd023cb5f2adac6
|
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 sha256:92c4f8cd51d2e8c9949ea38c90ce4eb9bc18b9068fc7636cfea38097eac939ad
|
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,
|
@@ -1206,11 +1206,59 @@
|
|
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.
|
1214 |
"trial_name": null,
|
1215 |
"trial_params": null
|
1216 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.734920006783877,
|
5 |
+
"global_step": 104000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1206 |
"learning_rate": 4.938697889674869e-06,
|
1207 |
"loss": 1.689,
|
1208 |
"step": 100000
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 0.71,
|
1212 |
+
"learning_rate": 4.938085627465422e-06,
|
1213 |
+
"loss": 1.6779,
|
1214 |
+
"step": 100500
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.71,
|
1218 |
+
"learning_rate": 4.937470361240773e-06,
|
1219 |
+
"loss": 1.694,
|
1220 |
+
"step": 101000
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.72,
|
1224 |
+
"learning_rate": 4.936852091759006e-06,
|
1225 |
+
"loss": 1.6757,
|
1226 |
+
"step": 101500
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.72,
|
1230 |
+
"learning_rate": 4.936230819781902e-06,
|
1231 |
+
"loss": 1.7025,
|
1232 |
+
"step": 102000
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 0.72,
|
1236 |
+
"learning_rate": 4.935606546074945e-06,
|
1237 |
+
"loss": 1.6897,
|
1238 |
+
"step": 102500
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 0.73,
|
1242 |
+
"learning_rate": 4.934980528951094e-06,
|
1243 |
+
"loss": 1.7087,
|
1244 |
+
"step": 103000
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 0.73,
|
1248 |
+
"learning_rate": 4.9343502600952685e-06,
|
1249 |
+
"loss": 1.6645,
|
1250 |
+
"step": 103500
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.73,
|
1254 |
+
"learning_rate": 4.9337169918266646e-06,
|
1255 |
+
"loss": 1.6942,
|
1256 |
+
"step": 104000
|
1257 |
}
|
1258 |
],
|
1259 |
"max_steps": 1415120,
|
1260 |
"num_train_epochs": 10,
|
1261 |
+
"total_flos": 4.963728541905715e+16,
|
1262 |
"trial_name": null,
|
1263 |
"trial_params": null
|
1264 |
}
|
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 sha256:06e0f8fd34ad9689e90c51a6ce416bb3efe00164a6779e3a86f8096cf6b0c3e6
|
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 sha256:3f04fd7a7e58b8b6bf9158b672f823af500a6cb60bdddafb0354038ce68a02da
|
3 |
+
size 10863
|