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 sha256:49d2f9fd02baa9e0c22f5c82248312a95a270b3a028effebe32e1392f0c37fc2
|
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 sha256:5ac5235992e9611032e2c41f60afcde835225966992d0ea5cfd4d0eda9cba8a0
|
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:c9fe8c1f3fa28b12c9d2a65af760b0b35f65714034bb64c832234a8f24b344c8
|
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:a8ec81724571758b6d4301f68ec67b23dd77b1dc5a0ab1a193ecd39032e5dfcc
|
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 sha256:2c4a0b2174a92c44f50fd38251e945dda3c30ecce8231dab22a5b071d4e60c46
|
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 sha256:861db5ae944afe794057fd5610f75a42f98fa68025a2916d28fc7185e4e6d801
|
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 sha256:2a0f946614c19c2972db15bb634815fba8ed2e0baad2e81053291315bbb52cc8
|
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 sha256:103fe1f064bd97ae5baa548336c4edee90a9847277e285efd11ebc1b1de7fd09
|
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": 0.00013911237967573605,
|
1087 |
"loss": 0.3541,
|
1088 |
"step": 90000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1089 |
}
|
1090 |
],
|
1091 |
"max_steps": 500000,
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6170160253955286,
|
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": 0.00013911237967573605,
|
1087 |
"loss": 0.3541,
|
1088 |
"step": 90000
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 1.54,
|
1092 |
+
"learning_rate": 0.0001389943003647822,
|
1093 |
+
"loss": 0.3539,
|
1094 |
+
"step": 90500
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.55,
|
1098 |
+
"learning_rate": 0.00013887563880390073,
|
1099 |
+
"loss": 0.3536,
|
1100 |
+
"step": 91000
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 1.56,
|
1104 |
+
"learning_rate": 0.0001387563961642333,
|
1105 |
+
"loss": 0.3537,
|
1106 |
+
"step": 91500
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 1.57,
|
1110 |
+
"learning_rate": 0.00013863657362265668,
|
1111 |
+
"loss": 0.3549,
|
1112 |
+
"step": 92000
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 1.57,
|
1116 |
+
"learning_rate": 0.0001385161723617709,
|
1117 |
+
"loss": 0.3539,
|
1118 |
+
"step": 92500
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 1.58,
|
1122 |
+
"learning_rate": 0.00013839519356988788,
|
1123 |
+
"loss": 0.3535,
|
1124 |
+
"step": 93000
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 1.59,
|
1128 |
+
"learning_rate": 0.0001382736384410194,
|
1129 |
+
"loss": 0.3537,
|
1130 |
+
"step": 93500
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 1.6,
|
1134 |
+
"learning_rate": 0.00013815150817486554,
|
1135 |
+
"loss": 0.3527,
|
1136 |
+
"step": 94000
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.61,
|
1140 |
+
"learning_rate": 0.0001380288039768027,
|
1141 |
+
"loss": 0.3529,
|
1142 |
+
"step": 94500
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 1.62,
|
1146 |
+
"learning_rate": 0.00013790552705787178,
|
1147 |
+
"loss": 0.353,
|
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 sha256:5ac5235992e9611032e2c41f60afcde835225966992d0ea5cfd4d0eda9cba8a0
|
3 |
size 201355195
|