Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07d271253ad7eddb3db134bdc96bf72b6fb29b6eb89123849a14c7282a602b17
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0be3c6f687e594da8e7c05affb0a3216e74ada978a190ce6a966734a0423ef4
|
3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eeef5a5cd399c2cfa96c423b188489f80b820a820435147acbd8127820b7b621
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c5235b2e87f9d721a92e0318f55cf82a1eb4118f0ef4f59ca28e5b517cde92c
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -13,13 +13,19 @@
|
|
13 |
"learning_rate": 0.0009846531614487416,
|
14 |
"loss": 0.5762,
|
15 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
17 |
],
|
18 |
"logging_steps": 500,
|
19 |
"max_steps": 32580,
|
20 |
"num_train_epochs": 5,
|
21 |
"save_steps": 500,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1534683855125844,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
13 |
"learning_rate": 0.0009846531614487416,
|
14 |
"loss": 0.5762,
|
15 |
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.15,
|
19 |
+
"learning_rate": 0.0009693063228974831,
|
20 |
+
"loss": 0.6042,
|
21 |
+
"step": 1000
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
"max_steps": 32580,
|
26 |
"num_train_epochs": 5,
|
27 |
"save_steps": 500,
|
28 |
+
"total_flos": 529584010297344.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|