Training in progress, step 594000
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
- pytorch_model.bin +1 -1
- runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0 +2 -2
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:fe0d9f56726daf6b16bb8d5d4f4ade97bb5cc7e60a7f11eb05a8e66f54c42e0f
|
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 sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
|
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 sha256:26c8c95b482dc20288935c89df5726ca51c516105c7e5f74e609c7af3177d0c8
|
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:e77e56a2ba56c21827ec91d155588126ec53ab90307574dd6bbda5b13092a2f8
|
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 sha256:64ce8d836ce27c39f0d4109ce68497decb68e999658c622e881394a4eb6c288a
|
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": 15.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -7098,11 +7098,47 @@
|
|
7098 |
"learning_rate": 6.024926992769612e-07,
|
7099 |
"loss": 1.0252,
|
7100 |
"step": 591000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7101 |
}
|
7102 |
],
|
7103 |
"max_steps": 762960,
|
7104 |
"num_train_epochs": 20,
|
7105 |
-
"total_flos": 7.
|
7106 |
"trial_name": null,
|
7107 |
"trial_params": null
|
7108 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 15.570917784232105,
|
5 |
+
"global_step": 594000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
7098 |
"learning_rate": 6.024926992769612e-07,
|
7099 |
"loss": 1.0252,
|
7100 |
"step": 591000
|
7101 |
+
},
|
7102 |
+
{
|
7103 |
+
"epoch": 15.51,
|
7104 |
+
"learning_rate": 5.991455467779178e-07,
|
7105 |
+
"loss": 1.0212,
|
7106 |
+
"step": 591500
|
7107 |
+
},
|
7108 |
+
{
|
7109 |
+
"epoch": 15.52,
|
7110 |
+
"learning_rate": 5.958064514933821e-07,
|
7111 |
+
"loss": 1.04,
|
7112 |
+
"step": 592000
|
7113 |
+
},
|
7114 |
+
{
|
7115 |
+
"epoch": 15.53,
|
7116 |
+
"learning_rate": 5.924754275768859e-07,
|
7117 |
+
"loss": 1.023,
|
7118 |
+
"step": 592500
|
7119 |
+
},
|
7120 |
+
{
|
7121 |
+
"epoch": 15.54,
|
7122 |
+
"learning_rate": 5.891591269459249e-07,
|
7123 |
+
"loss": 1.0252,
|
7124 |
+
"step": 593000
|
7125 |
+
},
|
7126 |
+
{
|
7127 |
+
"epoch": 15.56,
|
7128 |
+
"learning_rate": 5.85844271876021e-07,
|
7129 |
+
"loss": 1.0256,
|
7130 |
+
"step": 593500
|
7131 |
+
},
|
7132 |
+
{
|
7133 |
+
"epoch": 15.57,
|
7134 |
+
"learning_rate": 5.825375304011768e-07,
|
7135 |
+
"loss": 1.0333,
|
7136 |
+
"step": 594000
|
7137 |
}
|
7138 |
],
|
7139 |
"max_steps": 762960,
|
7140 |
"num_train_epochs": 20,
|
7141 |
+
"total_flos": 7.103152678841303e+17,
|
7142 |
"trial_name": null,
|
7143 |
"trial_params": null
|
7144 |
}
|
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 sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
|
3 |
size 1944201353
|
runs/Jun01_02-00-15_72d6bfb1a401/events.out.tfevents.1685586378.72d6bfb1a401.2268.0
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:fa6281f8fec358f3409920ee2385a0c2769b293403eb4304c3a5bc9ceb1b5b04
|
3 |
+
size 13101
|