Training in progress, step 95000
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 sha256:9383d4666eeeafc05e937e02f292247bb6ed63c694ad2e844acb2473908c89e6
|
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:b4a2faea047cb9b2b0cf113eecb945f723361f63a827436ce80ec70c60bea870
|
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 sha256:7efa5cd772ce4ea497b2566a23af159eef5aa21434cb9759b60999a948ec2815
|
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 sha256:651c7e07f7962b9d797a42f3b4c51dec78ffb402b9848fa9f5be146e560eb46a
|
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:f1c87d301112719d00df543775e8c189216d1253ac68a2478841b87b7e4ce29a
|
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 sha256:4130fc24a029257f4fa579f17c078f97fdb453d661ae6ffc0c5e1f7239bf5fe9
|
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 sha256:262727666821e8fc41a0d4ecd6658b6c25f75f8b011184bdd8b59ffeedf4e1b6
|
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 sha256:0c40f39f5b58ba1097e410d23f90905de95dbcf8124e6137d7837a066b34d657
|
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,
|
@@ -1086,6 +1086,66 @@
|
|
1086 |
"learning_rate": 0.0001391107305894032,
|
1087 |
"loss": 0.352,
|
1088 |
"step": 90000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1089 |
}
|
1090 |
],
|
1091 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6170212765957448,
|
5 |
+
"global_step": 95000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1086 |
"learning_rate": 0.0001391107305894032,
|
1087 |
"loss": 0.352,
|
1088 |
"step": 90000
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.54,
|
1092 |
+
"learning_rate": 0.0001389926431188934,
|
1093 |
+
"loss": 0.352,
|
1094 |
+
"step": 90500
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.55,
|
1098 |
+
"learning_rate": 0.00013887421133451205,
|
1099 |
+
"loss": 0.3515,
|
1100 |
+
"step": 91000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 1.56,
|
1104 |
+
"learning_rate": 0.00013875496172903372,
|
1105 |
+
"loss": 0.3516,
|
1106 |
+
"step": 91500
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 1.57,
|
1110 |
+
"learning_rate": 0.0001386351322358035,
|
1111 |
+
"loss": 0.3516,
|
1112 |
+
"step": 92000
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.57,
|
1116 |
+
"learning_rate": 0.00013851472403749002,
|
1117 |
+
"loss": 0.3514,
|
1118 |
+
"step": 92500
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 1.58,
|
1122 |
+
"learning_rate": 0.00013839398086947267,
|
1123 |
+
"loss": 0.3512,
|
1124 |
+
"step": 93000
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 1.59,
|
1128 |
+
"learning_rate": 0.00013827241998328336,
|
1129 |
+
"loss": 0.3509,
|
1130 |
+
"step": 93500
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.6,
|
1134 |
+
"learning_rate": 0.00013815028397183435,
|
1135 |
+
"loss": 0.3515,
|
1136 |
+
"step": 94000
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.61,
|
1140 |
+
"learning_rate": 0.00013802757404055875,
|
1141 |
+
"loss": 0.3509,
|
1142 |
+
"step": 94500
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 1.62,
|
1146 |
+
"learning_rate": 0.00013790453853658956,
|
1147 |
+
"loss": 0.3509,
|
1148 |
+
"step": 95000
|
1149 |
}
|
1150 |
],
|
1151 |
"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:b4a2faea047cb9b2b0cf113eecb945f723361f63a827436ce80ec70c60bea870
|
3 |
size 201355195
|