Commit
•
a2ef6f2
1
Parent(s):
d72709f
Training in progress, epoch 5, checkpoint
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/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +637 -3
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 272138666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c448104ce2d154398926b10f5da1a068cc005b858ff145e388bffd773d180f87
|
| 3 |
size 272138666
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 136067312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d522f48035551cde94f250a105d3f95296a4bbeab93d5b3d3564c104aecb6596
|
| 3 |
size 136067312
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d46f7c0ba4feb2125c13deda1ba0b721e0efe91bcba4140ca17136cad45c48a3
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85312c5143eb72e5e61ba4a319c997e347a39a399dd2227831e2d75a9642adec
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a8352611a4312779c3a8d7ccc5cd6742e36dab552d14e699adf613271f5c02
|
| 3 |
size 21687
|
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 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b37613fe778cfe2e6f052607845b13507fca8d228aab57a081250d0579c8f0c
|
| 3 |
size 21687
|
last-checkpoint/rng_state_4.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1719e13a0f31b2a8346b234c197bedeb66d5e3a9ca796b9296180e2a5acd65
|
| 3 |
size 21687
|
last-checkpoint/rng_state_5.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee6061d4eb9c4722da13bb14acdbd266fcc9780b11acf895ab0612c1b31f5a61
|
| 3 |
size 21687
|
last-checkpoint/rng_state_6.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f111ad4c6d15bd49b5db0a3a88b93cea27f4f9c389fa8e486ed9639c4a3d613c
|
| 3 |
size 21687
|
last-checkpoint/rng_state_7.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21687
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:111c33490270e9bb9e95ce9eed65ea10f26f937a0aec179323d14088fa7d6a98
|
| 3 |
size 21687
|
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:ed29c8a99623c2a97230e7e5a3a6a12bd70f67f1cb68462fbad60d321f9a3ce3
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -937,13 +937,647 @@
|
|
| 937 |
"learning_rate": 1.7493335291185675e-05,
|
| 938 |
"loss": 0.0324,
|
| 939 |
"step": 615
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 940 |
}
|
| 941 |
],
|
| 942 |
"logging_steps": 5,
|
| 943 |
"max_steps": 1030,
|
| 944 |
"num_train_epochs": 5,
|
| 945 |
"save_steps": 500,
|
| 946 |
-
"total_flos":
|
| 947 |
"trial_name": null,
|
| 948 |
"trial_params": null
|
| 949 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 1030,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 937 |
"learning_rate": 1.7493335291185675e-05,
|
| 938 |
"loss": 0.0324,
|
| 939 |
"step": 615
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 3.01,
|
| 943 |
+
"learning_rate": 1.7130543699071327e-05,
|
| 944 |
+
"loss": 0.0459,
|
| 945 |
+
"step": 620
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 3.03,
|
| 949 |
+
"learning_rate": 1.67695824264883e-05,
|
| 950 |
+
"loss": 0.0365,
|
| 951 |
+
"step": 625
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 3.03,
|
| 955 |
+
"eval_loss": 0.04022263363003731,
|
| 956 |
+
"eval_runtime": 0.1169,
|
| 957 |
+
"eval_samples_per_second": 3516.3,
|
| 958 |
+
"eval_steps_per_second": 111.221,
|
| 959 |
+
"step": 625
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 3.06,
|
| 963 |
+
"learning_rate": 1.6410535427707634e-05,
|
| 964 |
+
"loss": 0.0307,
|
| 965 |
+
"step": 630
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.08,
|
| 969 |
+
"learning_rate": 1.6053486211768503e-05,
|
| 970 |
+
"loss": 0.0316,
|
| 971 |
+
"step": 635
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.11,
|
| 975 |
+
"learning_rate": 1.5698517823055242e-05,
|
| 976 |
+
"loss": 0.0236,
|
| 977 |
+
"step": 640
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.13,
|
| 981 |
+
"learning_rate": 1.5345712821982443e-05,
|
| 982 |
+
"loss": 0.0187,
|
| 983 |
+
"step": 645
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.16,
|
| 987 |
+
"learning_rate": 1.4995153265792642e-05,
|
| 988 |
+
"loss": 0.0282,
|
| 989 |
+
"step": 650
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.16,
|
| 993 |
+
"eval_loss": 0.04607125371694565,
|
| 994 |
+
"eval_runtime": 0.1202,
|
| 995 |
+
"eval_samples_per_second": 3419.582,
|
| 996 |
+
"eval_steps_per_second": 108.162,
|
| 997 |
+
"step": 650
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 3.18,
|
| 1001 |
+
"learning_rate": 1.4646920689470967e-05,
|
| 1002 |
+
"loss": 0.013,
|
| 1003 |
+
"step": 655
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 3.2,
|
| 1007 |
+
"learning_rate": 1.4301096086781363e-05,
|
| 1008 |
+
"loss": 0.0035,
|
| 1009 |
+
"step": 660
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 3.23,
|
| 1013 |
+
"learning_rate": 1.3957759891428568e-05,
|
| 1014 |
+
"loss": 0.0043,
|
| 1015 |
+
"step": 665
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 3.25,
|
| 1019 |
+
"learning_rate": 1.3616991958350494e-05,
|
| 1020 |
+
"loss": 0.0072,
|
| 1021 |
+
"step": 670
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.28,
|
| 1025 |
+
"learning_rate": 1.3278871545145084e-05,
|
| 1026 |
+
"loss": 0.0391,
|
| 1027 |
+
"step": 675
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 3.28,
|
| 1031 |
+
"eval_loss": 0.04361347481608391,
|
| 1032 |
+
"eval_runtime": 0.1163,
|
| 1033 |
+
"eval_samples_per_second": 3535.033,
|
| 1034 |
+
"eval_steps_per_second": 111.814,
|
| 1035 |
+
"step": 675
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.3,
|
| 1039 |
+
"learning_rate": 1.294347729363618e-05,
|
| 1040 |
+
"loss": 0.0266,
|
| 1041 |
+
"step": 680
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.33,
|
| 1045 |
+
"learning_rate": 1.2610887211582612e-05,
|
| 1046 |
+
"loss": 0.0256,
|
| 1047 |
+
"step": 685
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 3.35,
|
| 1051 |
+
"learning_rate": 1.2281178654534734e-05,
|
| 1052 |
+
"loss": 0.0311,
|
| 1053 |
+
"step": 690
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 3.37,
|
| 1057 |
+
"learning_rate": 1.1954428307842646e-05,
|
| 1058 |
+
"loss": 0.0054,
|
| 1059 |
+
"step": 695
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 3.4,
|
| 1063 |
+
"learning_rate": 1.1630712168820351e-05,
|
| 1064 |
+
"loss": 0.0282,
|
| 1065 |
+
"step": 700
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 3.4,
|
| 1069 |
+
"eval_loss": 0.04334261640906334,
|
| 1070 |
+
"eval_runtime": 0.1164,
|
| 1071 |
+
"eval_samples_per_second": 3530.458,
|
| 1072 |
+
"eval_steps_per_second": 111.669,
|
| 1073 |
+
"step": 700
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 3.42,
|
| 1077 |
+
"learning_rate": 1.1310105529069844e-05,
|
| 1078 |
+
"loss": 0.0409,
|
| 1079 |
+
"step": 705
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 3.45,
|
| 1083 |
+
"learning_rate": 1.0992682956969458e-05,
|
| 1084 |
+
"loss": 0.0331,
|
| 1085 |
+
"step": 710
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 3.47,
|
| 1089 |
+
"learning_rate": 1.0678518280330296e-05,
|
| 1090 |
+
"loss": 0.0116,
|
| 1091 |
+
"step": 715
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 3.5,
|
| 1095 |
+
"learning_rate": 1.0367684569225028e-05,
|
| 1096 |
+
"loss": 0.0037,
|
| 1097 |
+
"step": 720
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.52,
|
| 1101 |
+
"learning_rate": 1.0060254118992837e-05,
|
| 1102 |
+
"loss": 0.0465,
|
| 1103 |
+
"step": 725
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 3.52,
|
| 1107 |
+
"eval_loss": 0.048130132257938385,
|
| 1108 |
+
"eval_runtime": 0.1194,
|
| 1109 |
+
"eval_samples_per_second": 3441.283,
|
| 1110 |
+
"eval_steps_per_second": 108.848,
|
| 1111 |
+
"step": 725
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.54,
|
| 1115 |
+
"learning_rate": 9.756298433424587e-06,
|
| 1116 |
+
"loss": 0.1006,
|
| 1117 |
+
"step": 730
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 3.57,
|
| 1121 |
+
"learning_rate": 9.455888208132102e-06,
|
| 1122 |
+
"loss": 0.0071,
|
| 1123 |
+
"step": 735
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 3.59,
|
| 1127 |
+
"learning_rate": 9.159093314105405e-06,
|
| 1128 |
+
"loss": 0.0139,
|
| 1129 |
+
"step": 740
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 3.62,
|
| 1133 |
+
"learning_rate": 8.865982781461791e-06,
|
| 1134 |
+
"loss": 0.004,
|
| 1135 |
+
"step": 745
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 3.64,
|
| 1139 |
+
"learning_rate": 8.576624783390367e-06,
|
| 1140 |
+
"loss": 0.0557,
|
| 1141 |
+
"step": 750
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 3.64,
|
| 1145 |
+
"eval_loss": 0.04551706090569496,
|
| 1146 |
+
"eval_runtime": 0.1186,
|
| 1147 |
+
"eval_samples_per_second": 3464.82,
|
| 1148 |
+
"eval_steps_per_second": 109.593,
|
| 1149 |
+
"step": 750
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.67,
|
| 1153 |
+
"learning_rate": 8.291086620296052e-06,
|
| 1154 |
+
"loss": 0.0347,
|
| 1155 |
+
"step": 755
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.69,
|
| 1159 |
+
"learning_rate": 8.009434704146424e-06,
|
| 1160 |
+
"loss": 0.0413,
|
| 1161 |
+
"step": 760
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.71,
|
| 1165 |
+
"learning_rate": 7.731734543025345e-06,
|
| 1166 |
+
"loss": 0.0147,
|
| 1167 |
+
"step": 765
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.74,
|
| 1171 |
+
"learning_rate": 7.458050725896673e-06,
|
| 1172 |
+
"loss": 0.0502,
|
| 1173 |
+
"step": 770
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.76,
|
| 1177 |
+
"learning_rate": 7.188446907581894e-06,
|
| 1178 |
+
"loss": 0.058,
|
| 1179 |
+
"step": 775
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 3.76,
|
| 1183 |
+
"eval_loss": 0.04955735430121422,
|
| 1184 |
+
"eval_runtime": 0.1466,
|
| 1185 |
+
"eval_samples_per_second": 2802.9,
|
| 1186 |
+
"eval_steps_per_second": 88.656,
|
| 1187 |
+
"step": 775
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 3.79,
|
| 1191 |
+
"learning_rate": 6.922985793954881e-06,
|
| 1192 |
+
"loss": 0.0127,
|
| 1193 |
+
"step": 780
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 3.81,
|
| 1197 |
+
"learning_rate": 6.661729127357494e-06,
|
| 1198 |
+
"loss": 0.0335,
|
| 1199 |
+
"step": 785
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 3.83,
|
| 1203 |
+
"learning_rate": 6.404737672239173e-06,
|
| 1204 |
+
"loss": 0.0271,
|
| 1205 |
+
"step": 790
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 3.86,
|
| 1209 |
+
"learning_rate": 6.1520712010240455e-06,
|
| 1210 |
+
"loss": 0.0512,
|
| 1211 |
+
"step": 795
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 3.88,
|
| 1215 |
+
"learning_rate": 5.9037884802087325e-06,
|
| 1216 |
+
"loss": 0.0057,
|
| 1217 |
+
"step": 800
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 3.88,
|
| 1221 |
+
"eval_loss": 0.051423329859972,
|
| 1222 |
+
"eval_runtime": 0.1163,
|
| 1223 |
+
"eval_samples_per_second": 3533.425,
|
| 1224 |
+
"eval_steps_per_second": 111.763,
|
| 1225 |
+
"step": 800
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 3.91,
|
| 1229 |
+
"learning_rate": 5.659947256694156e-06,
|
| 1230 |
+
"loss": 0.0029,
|
| 1231 |
+
"step": 805
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 3.93,
|
| 1235 |
+
"learning_rate": 5.420604244354408e-06,
|
| 1236 |
+
"loss": 0.0095,
|
| 1237 |
+
"step": 810
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.96,
|
| 1241 |
+
"learning_rate": 5.185815110845996e-06,
|
| 1242 |
+
"loss": 0.0491,
|
| 1243 |
+
"step": 815
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 3.98,
|
| 1247 |
+
"learning_rate": 4.9556344646603165e-06,
|
| 1248 |
+
"loss": 0.0251,
|
| 1249 |
+
"step": 820
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 4.0,
|
| 1253 |
+
"learning_rate": 4.73011584242257e-06,
|
| 1254 |
+
"loss": 0.032,
|
| 1255 |
+
"step": 825
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 4.0,
|
| 1259 |
+
"eval_loss": 0.05062270909547806,
|
| 1260 |
+
"eval_runtime": 0.1194,
|
| 1261 |
+
"eval_samples_per_second": 3442.19,
|
| 1262 |
+
"eval_steps_per_second": 108.877,
|
| 1263 |
+
"step": 825
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 4.03,
|
| 1267 |
+
"learning_rate": 4.509311696439903e-06,
|
| 1268 |
+
"loss": 0.0354,
|
| 1269 |
+
"step": 830
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 4.05,
|
| 1273 |
+
"learning_rate": 4.293273382501775e-06,
|
| 1274 |
+
"loss": 0.0737,
|
| 1275 |
+
"step": 835
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 4.08,
|
| 1279 |
+
"learning_rate": 4.082051147935373e-06,
|
| 1280 |
+
"loss": 0.0198,
|
| 1281 |
+
"step": 840
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.1,
|
| 1285 |
+
"learning_rate": 3.875694119918805e-06,
|
| 1286 |
+
"loss": 0.0266,
|
| 1287 |
+
"step": 845
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 4.13,
|
| 1291 |
+
"learning_rate": 3.6742502940548734e-06,
|
| 1292 |
+
"loss": 0.0056,
|
| 1293 |
+
"step": 850
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 4.13,
|
| 1297 |
+
"eval_loss": 0.048265255987644196,
|
| 1298 |
+
"eval_runtime": 0.1135,
|
| 1299 |
+
"eval_samples_per_second": 3619.583,
|
| 1300 |
+
"eval_steps_per_second": 114.488,
|
| 1301 |
+
"step": 850
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 4.15,
|
| 1305 |
+
"learning_rate": 3.477766523207965e-06,
|
| 1306 |
+
"loss": 0.0017,
|
| 1307 |
+
"step": 855
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 4.17,
|
| 1311 |
+
"learning_rate": 3.286288506606805e-06,
|
| 1312 |
+
"loss": 0.0009,
|
| 1313 |
+
"step": 860
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 4.2,
|
| 1317 |
+
"learning_rate": 3.0998607792154495e-06,
|
| 1318 |
+
"loss": 0.0153,
|
| 1319 |
+
"step": 865
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 4.22,
|
| 1323 |
+
"learning_rate": 2.91852670137516e-06,
|
| 1324 |
+
"loss": 0.0232,
|
| 1325 |
+
"step": 870
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 4.25,
|
| 1329 |
+
"learning_rate": 2.7423284487193697e-06,
|
| 1330 |
+
"loss": 0.0104,
|
| 1331 |
+
"step": 875
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 4.25,
|
| 1335 |
+
"eval_loss": 0.048452552407979965,
|
| 1336 |
+
"eval_runtime": 0.1158,
|
| 1337 |
+
"eval_samples_per_second": 3550.622,
|
| 1338 |
+
"eval_steps_per_second": 112.307,
|
| 1339 |
+
"step": 875
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 4.27,
|
| 1343 |
+
"learning_rate": 2.571307002364301e-06,
|
| 1344 |
+
"loss": 0.0146,
|
| 1345 |
+
"step": 880
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 4.3,
|
| 1349 |
+
"learning_rate": 2.4055021393773277e-06,
|
| 1350 |
+
"loss": 0.062,
|
| 1351 |
+
"step": 885
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 4.32,
|
| 1355 |
+
"learning_rate": 2.2449524235254484e-06,
|
| 1356 |
+
"loss": 0.0415,
|
| 1357 |
+
"step": 890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 4.34,
|
| 1361 |
+
"learning_rate": 2.089695196305888e-06,
|
| 1362 |
+
"loss": 0.0037,
|
| 1363 |
+
"step": 895
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 4.37,
|
| 1367 |
+
"learning_rate": 1.939766568261037e-06,
|
| 1368 |
+
"loss": 0.0353,
|
| 1369 |
+
"step": 900
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 4.37,
|
| 1373 |
+
"eval_loss": 0.04834846034646034,
|
| 1374 |
+
"eval_runtime": 0.1173,
|
| 1375 |
+
"eval_samples_per_second": 3503.757,
|
| 1376 |
+
"eval_steps_per_second": 110.824,
|
| 1377 |
+
"step": 900
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 4.39,
|
| 1381 |
+
"learning_rate": 1.7952014105796666e-06,
|
| 1382 |
+
"loss": 0.0316,
|
| 1383 |
+
"step": 905
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 4.42,
|
| 1387 |
+
"learning_rate": 1.656033346986416e-06,
|
| 1388 |
+
"loss": 0.0238,
|
| 1389 |
+
"step": 910
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 4.44,
|
| 1393 |
+
"learning_rate": 1.5222947459213793e-06,
|
| 1394 |
+
"loss": 0.025,
|
| 1395 |
+
"step": 915
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 4.47,
|
| 1399 |
+
"learning_rate": 1.3940167130117226e-06,
|
| 1400 |
+
"loss": 0.0076,
|
| 1401 |
+
"step": 920
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 4.49,
|
| 1405 |
+
"learning_rate": 1.2712290838369363e-06,
|
| 1406 |
+
"loss": 0.0044,
|
| 1407 |
+
"step": 925
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 4.49,
|
| 1411 |
+
"eval_loss": 0.0482080839574337,
|
| 1412 |
+
"eval_runtime": 0.1126,
|
| 1413 |
+
"eval_samples_per_second": 3651.3,
|
| 1414 |
+
"eval_steps_per_second": 115.491,
|
| 1415 |
+
"step": 925
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 4.51,
|
| 1419 |
+
"learning_rate": 1.1539604169895497e-06,
|
| 1420 |
+
"loss": 0.0038,
|
| 1421 |
+
"step": 930
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 4.54,
|
| 1425 |
+
"learning_rate": 1.0422379874328008e-06,
|
| 1426 |
+
"loss": 0.0038,
|
| 1427 |
+
"step": 935
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 4.56,
|
| 1431 |
+
"learning_rate": 9.360877801568968e-07,
|
| 1432 |
+
"loss": 0.0463,
|
| 1433 |
+
"step": 940
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 4.59,
|
| 1437 |
+
"learning_rate": 8.355344841352836e-07,
|
| 1438 |
+
"loss": 0.001,
|
| 1439 |
+
"step": 945
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 4.61,
|
| 1443 |
+
"learning_rate": 7.406014865823513e-07,
|
| 1444 |
+
"loss": 0.0449,
|
| 1445 |
+
"step": 950
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 4.61,
|
| 1449 |
+
"eval_loss": 0.04827665537595749,
|
| 1450 |
+
"eval_runtime": 0.1168,
|
| 1451 |
+
"eval_samples_per_second": 3519.71,
|
| 1452 |
+
"eval_steps_per_second": 111.329,
|
| 1453 |
+
"step": 950
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 4.64,
|
| 1457 |
+
"learning_rate": 6.513108675139101e-07,
|
| 1458 |
+
"loss": 0.0138,
|
| 1459 |
+
"step": 955
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 4.66,
|
| 1463 |
+
"learning_rate": 5.676833946117205e-07,
|
| 1464 |
+
"loss": 0.0407,
|
| 1465 |
+
"step": 960
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 4.68,
|
| 1469 |
+
"learning_rate": 4.897385183932179e-07,
|
| 1470 |
+
"loss": 0.0392,
|
| 1471 |
+
"step": 965
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 4.71,
|
| 1475 |
+
"learning_rate": 4.1749436768762084e-07,
|
| 1476 |
+
"loss": 0.0358,
|
| 1477 |
+
"step": 970
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 4.73,
|
| 1481 |
+
"learning_rate": 3.509677454194282e-07,
|
| 1482 |
+
"loss": 0.0626,
|
| 1483 |
+
"step": 975
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.73,
|
| 1487 |
+
"eval_loss": 0.04846416041254997,
|
| 1488 |
+
"eval_runtime": 0.116,
|
| 1489 |
+
"eval_samples_per_second": 3543.615,
|
| 1490 |
+
"eval_steps_per_second": 112.085,
|
| 1491 |
+
"step": 975
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 4.76,
|
| 1495 |
+
"learning_rate": 2.901741247002987e-07,
|
| 1496 |
+
"loss": 0.0069,
|
| 1497 |
+
"step": 980
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.78,
|
| 1501 |
+
"learning_rate": 2.3512764523025698e-07,
|
| 1502 |
+
"loss": 0.0697,
|
| 1503 |
+
"step": 985
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 4.81,
|
| 1507 |
+
"learning_rate": 1.8584111000897464e-07,
|
| 1508 |
+
"loss": 0.03,
|
| 1509 |
+
"step": 990
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 4.83,
|
| 1513 |
+
"learning_rate": 1.423259823580131e-07,
|
| 1514 |
+
"loss": 0.0007,
|
| 1515 |
+
"step": 995
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 4.85,
|
| 1519 |
+
"learning_rate": 1.0459238325460363e-07,
|
| 1520 |
+
"loss": 0.0631,
|
| 1521 |
+
"step": 1000
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 4.85,
|
| 1525 |
+
"eval_loss": 0.0483647957444191,
|
| 1526 |
+
"eval_runtime": 0.146,
|
| 1527 |
+
"eval_samples_per_second": 2815.962,
|
| 1528 |
+
"eval_steps_per_second": 89.069,
|
| 1529 |
+
"step": 1000
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 4.88,
|
| 1533 |
+
"learning_rate": 7.264908897766098e-08,
|
| 1534 |
+
"loss": 0.0569,
|
| 1535 |
+
"step": 1005
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 4.9,
|
| 1539 |
+
"learning_rate": 4.650352906655775e-08,
|
| 1540 |
+
"loss": 0.0304,
|
| 1541 |
+
"step": 1010
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 4.93,
|
| 1545 |
+
"learning_rate": 2.616178459311225e-08,
|
| 1546 |
+
"loss": 0.0101,
|
| 1547 |
+
"step": 1015
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 4.95,
|
| 1551 |
+
"learning_rate": 1.1628586747233772e-08,
|
| 1552 |
+
"loss": 0.0035,
|
| 1553 |
+
"step": 1020
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 4.98,
|
| 1557 |
+
"learning_rate": 2.9073157365056002e-09,
|
| 1558 |
+
"loss": 0.0054,
|
| 1559 |
+
"step": 1025
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 4.98,
|
| 1563 |
+
"eval_loss": 0.04826511815190315,
|
| 1564 |
+
"eval_runtime": 0.1121,
|
| 1565 |
+
"eval_samples_per_second": 3664.947,
|
| 1566 |
+
"eval_steps_per_second": 115.923,
|
| 1567 |
+
"step": 1025
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 5.0,
|
| 1571 |
+
"learning_rate": 0.0,
|
| 1572 |
+
"loss": 0.003,
|
| 1573 |
+
"step": 1030
|
| 1574 |
}
|
| 1575 |
],
|
| 1576 |
"logging_steps": 5,
|
| 1577 |
"max_steps": 1030,
|
| 1578 |
"num_train_epochs": 5,
|
| 1579 |
"save_steps": 500,
|
| 1580 |
+
"total_flos": 459260224208896.0,
|
| 1581 |
"trial_name": null,
|
| 1582 |
"trial_params": null
|
| 1583 |
}
|