Training in progress, step 4500, 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:bc34f72bc206211019f1ac87672fec4bb1800bccb02cfd70aa3445bbd42808ff
|
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:f4f3f80faecd06b5c81695f7bff406742fd1d556851645d7a4c28070542c5bb8
|
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 sha256:6d040460cc5ddb10d804623d80986dd017725da0bde74990a1956f8e83464c73
|
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 sha256:8b89c2970f0d9788e95ecb02fcb06c5a504b563e10dbc3d91e866b0c4214e319
|
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,
|
@@ -55,13 +55,19 @@
|
|
55 |
"learning_rate": 0.0008772252915899325,
|
56 |
"loss": 0.6104,
|
57 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
61 |
"max_steps": 32580,
|
62 |
"num_train_epochs": 5,
|
63 |
"save_steps": 500,
|
64 |
-
"total_flos":
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6906077348066298,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"learning_rate": 0.0008772252915899325,
|
56 |
"loss": 0.6104,
|
57 |
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.69,
|
61 |
+
"learning_rate": 0.0008619091467157766,
|
62 |
+
"loss": 0.6154,
|
63 |
+
"step": 4500
|
64 |
}
|
65 |
],
|
66 |
"logging_steps": 500,
|
67 |
"max_steps": 32580,
|
68 |
"num_train_epochs": 5,
|
69 |
"save_steps": 500,
|
70 |
+
"total_flos": 2383386041647104.0,
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|