Training in progress, step 630000
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 +39 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun03_20-07-36_5814eb69ea9a/1685824428.675766/events.out.tfevents.1685824428.5814eb69ea9a.704.1 +3 -0
- runs/Jun03_20-07-36_5814eb69ea9a/events.out.tfevents.1685824428.5814eb69ea9a.704.0 +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 sha256:4e6d1b247617f454f8aba2d725b4b716e0e51b61999906e6bdb1b6bb40ec3856
|
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:f825359cc32e06cdd2a780f075f408d8b0f23a0b1be16adda6020c3fee000f02
|
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 sha256:15a1f862e56bea0c697db0f7c551b1c23f429cc092728541a372282c506543b9
|
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:e7470e23b2c705976001439269366835bc44d2ce969c2d60f638dc1ef7d70370
|
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 sha256:9dfdf862b25dade6b656c8ca945dace95c219bab8aa3565ea0e06857dfb4e22a
|
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": 16.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7530,11 +7530,47 @@
|
|
7530 |
"learning_rate": 3.8297124131692177e-07,
|
7531 |
"loss": 1.0129,
|
7532 |
"step": 627000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7533 |
}
|
7534 |
],
|
7535 |
"max_steps": 762960,
|
7536 |
"num_train_epochs": 20,
|
7537 |
-
"total_flos": 7.
|
7538 |
"trial_name": null,
|
7539 |
"trial_params": null
|
7540 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 16.514621845215004,
|
5 |
+
"global_step": 630000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7530 |
"learning_rate": 3.8297124131692177e-07,
|
7531 |
"loss": 1.0129,
|
7532 |
"step": 627000
|
7533 |
+
},
|
7534 |
+
{
|
7535 |
+
"epoch": 16.45,
|
7536 |
+
"learning_rate": 3.802380513016235e-07,
|
7537 |
+
"loss": 1.0221,
|
7538 |
+
"step": 627500
|
7539 |
+
},
|
7540 |
+
{
|
7541 |
+
"epoch": 16.46,
|
7542 |
+
"learning_rate": 3.775138463912581e-07,
|
7543 |
+
"loss": 1.0119,
|
7544 |
+
"step": 628000
|
7545 |
+
},
|
7546 |
+
{
|
7547 |
+
"epoch": 16.48,
|
7548 |
+
"learning_rate": 3.7479863813300294e-07,
|
7549 |
+
"loss": 1.0212,
|
7550 |
+
"step": 628500
|
7551 |
+
},
|
7552 |
+
{
|
7553 |
+
"epoch": 16.49,
|
7554 |
+
"learning_rate": 3.7209243803590006e-07,
|
7555 |
+
"loss": 1.0243,
|
7556 |
+
"step": 629000
|
7557 |
+
},
|
7558 |
+
{
|
7559 |
+
"epoch": 16.5,
|
7560 |
+
"learning_rate": 3.69395257570809e-07,
|
7561 |
+
"loss": 1.025,
|
7562 |
+
"step": 629500
|
7563 |
+
},
|
7564 |
+
{
|
7565 |
+
"epoch": 16.51,
|
7566 |
+
"learning_rate": 3.6671247544857765e-07,
|
7567 |
+
"loss": 1.0369,
|
7568 |
+
"step": 630000
|
7569 |
}
|
7570 |
],
|
7571 |
"max_steps": 762960,
|
7572 |
"num_train_epochs": 20,
|
7573 |
+
"total_flos": 7.499479244393595e+17,
|
7574 |
"trial_name": null,
|
7575 |
"trial_params": null
|
7576 |
}
|
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:a817e83c25ddaa8901cfc233f35e575b7ed2a8f04ee848f1df7a6ce2254ee042
|
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:f825359cc32e06cdd2a780f075f408d8b0f23a0b1be16adda6020c3fee000f02
|
3 |
size 1944201353
|
runs/Jun03_20-07-36_5814eb69ea9a/1685824428.675766/events.out.tfevents.1685824428.5814eb69ea9a.704.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a45957087d60ba82cebff2e1ba5034a47961917d8f0acd8b366e1c31721030cc
|
3 |
+
size 6184
|
runs/Jun03_20-07-36_5814eb69ea9a/events.out.tfevents.1685824428.5814eb69ea9a.704.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7fa3c5c4fd8134e8f1b69a09e298c911d8d89cd9a0733740e8195019ea66202
|
3 |
+
size 5421
|
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:a817e83c25ddaa8901cfc233f35e575b7ed2a8f04ee848f1df7a6ce2254ee042
|
3 |
size 3771
|