Johannes Garstenauer commited on
Commit ·
922285f
1
Parent(s): 28458b3
Training in progress, step 4104
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 532524613
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac5ed724c14630ace1af91e200e1f6e320fe2f053e5a1d14448e2fa238d4575
|
| 3 |
size 532524613
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 266267309
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:883552f6021d2b21df787f36ce686cc8228c1374be6224606bfbda1e345649ba
|
| 3 |
size 266267309
|
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 sha256:262ec0a781fe8693519172ed50fd203ae9aaa2efd827758129213caf1afbba51
|
| 3 |
size 14575
|
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:c922809123cf1ce663209ab85f7165d4bb2dc50c50432e65afade4b4028455c3
|
| 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": 1.
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -56,11 +56,17 @@
|
|
| 56 |
"learning_rate": 3.7662337662337666e-06,
|
| 57 |
"loss": 0.1427,
|
| 58 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"max_steps": 4312,
|
| 62 |
"num_train_epochs": 2,
|
| 63 |
-
"total_flos": 6.
|
| 64 |
"trial_name": null,
|
| 65 |
"trial_params": null
|
| 66 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9035250463821893,
|
| 5 |
+
"global_step": 4104,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 56 |
"learning_rate": 3.7662337662337666e-06,
|
| 57 |
"loss": 0.1427,
|
| 58 |
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.86,
|
| 62 |
+
"learning_rate": 1.4471243042671615e-06,
|
| 63 |
+
"loss": 0.1442,
|
| 64 |
+
"step": 4000
|
| 65 |
}
|
| 66 |
],
|
| 67 |
"max_steps": 4312,
|
| 68 |
"num_train_epochs": 2,
|
| 69 |
+
"total_flos": 6.957929594845594e+16,
|
| 70 |
"trial_name": null,
|
| 71 |
"trial_params": null
|
| 72 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 266267309
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:883552f6021d2b21df787f36ce686cc8228c1374be6224606bfbda1e345649ba
|
| 3 |
size 266267309
|