Training in progress, step 88000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +2 -2
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/May15_17-32-55_19599b9fb4f0/1684173637.585357/events.out.tfevents.1684173637.19599b9fb4f0.1168.1 +3 -0
- runs/May15_17-32-55_19599b9fb4f0/events.out.tfevents.1684173637.19599b9fb4f0.1168.0 +3 -0
- training_args.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 3871544599
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f65a1b1ad6a6d4c3f194fd2e2b41e87bf16b995f3dc81e93effc58bcd903702f
|
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 sha256:0c363c59d410214e2182b4cda43d4ced15855f6fe36954144299b10e0fdfa267
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fdafee001ede888cf0ab17d583f9351eb1d79851d397a6b6fb7f91d1321842a
|
3 |
+
size 14639
|
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:c72263ff174d5b97c40d547565fd4c89ebb79dc2842ecce4206713535ba1aa8d
|
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 sha256:3ad5b341eddecd904c370cdae0d92e1d886e83f8397a6082751b4788787ac6cd
|
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,
|
@@ -1014,11 +1014,59 @@
|
|
1014 |
"learning_rate": 4.956691589818862e-06,
|
1015 |
"loss": 1.5717,
|
1016 |
"step": 84000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1017 |
}
|
1018 |
],
|
1019 |
"max_steps": 1415120,
|
1020 |
"num_train_epochs": 10,
|
1021 |
-
"total_flos": 4.
|
1022 |
"trial_name": null,
|
1023 |
"trial_params": null
|
1024 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6218553903555882,
|
5 |
+
"global_step": 88000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1014 |
"learning_rate": 4.956691589818862e-06,
|
1015 |
"loss": 1.5717,
|
1016 |
"step": 84000
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 0.6,
|
1020 |
+
"learning_rate": 4.956175785746677e-06,
|
1021 |
+
"loss": 1.5993,
|
1022 |
+
"step": 84500
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.6,
|
1026 |
+
"learning_rate": 4.955657996050618e-06,
|
1027 |
+
"loss": 1.5842,
|
1028 |
+
"step": 85000
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 0.6,
|
1032 |
+
"learning_rate": 4.955136146059475e-06,
|
1033 |
+
"loss": 1.5906,
|
1034 |
+
"step": 85500
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.61,
|
1038 |
+
"learning_rate": 4.954611271044838e-06,
|
1039 |
+
"loss": 1.5686,
|
1040 |
+
"step": 86000
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.61,
|
1044 |
+
"learning_rate": 4.954083371653418e-06,
|
1045 |
+
"loss": 1.59,
|
1046 |
+
"step": 86500
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.61,
|
1050 |
+
"learning_rate": 4.9535535133991276e-06,
|
1051 |
+
"loss": 1.5915,
|
1052 |
+
"step": 87000
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.62,
|
1056 |
+
"learning_rate": 4.953019573254659e-06,
|
1057 |
+
"loss": 1.5991,
|
1058 |
+
"step": 87500
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.62,
|
1062 |
+
"learning_rate": 4.95248261069457e-06,
|
1063 |
+
"loss": 1.6045,
|
1064 |
+
"step": 88000
|
1065 |
}
|
1066 |
],
|
1067 |
"max_steps": 1415120,
|
1068 |
"num_train_epochs": 10,
|
1069 |
+
"total_flos": 4.435188659955302e+16,
|
1070 |
"trial_name": null,
|
1071 |
"trial_params": null
|
1072 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9ac0fcb13e241dd0ffcaa12aae4b2a732edb5f8bfbd7375a7791f0928aa525b
|
3 |
size 3771
|
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 sha256:0c363c59d410214e2182b4cda43d4ced15855f6fe36954144299b10e0fdfa267
|
3 |
size 1944201353
|
runs/May15_17-32-55_19599b9fb4f0/1684173637.585357/events.out.tfevents.1684173637.19599b9fb4f0.1168.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab32ebf82868bc27c1dbd2f98016e77aa15c2132d287eab0a56ae286ae6d0d39
|
3 |
+
size 6187
|
runs/May15_17-32-55_19599b9fb4f0/events.out.tfevents.1684173637.19599b9fb4f0.1168.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5285ea7dfcb205a7d35aa1645cace0ce90fbe39f1f4a59a059a1a50fa65dbbc2
|
3 |
+
size 5743
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9ac0fcb13e241dd0ffcaa12aae4b2a732edb5f8bfbd7375a7791f0928aa525b
|
3 |
size 3771
|