Training in progress, step 13, checkpoint
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 58562260
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c60ab1d42319bc487c4ace3721fe887ce575ebd071ea06ce7032d16cf05f2880
|
3 |
size 58562260
|
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:bd2d7770a458a27d27b46b504355e8a10cae64e62369261eb787f250e8e1f5d8
|
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 sha256:339b579a534790054eb28e51de35d1a47ad1a4526ec1be6232e5e2a340410148
|
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":
|
5 |
"eval_steps": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -75,12 +75,12 @@
|
|
75 |
"should_evaluate": false,
|
76 |
"should_log": false,
|
77 |
"should_save": true,
|
78 |
-
"should_training_stop":
|
79 |
},
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
-
"total_flos":
|
84 |
"train_batch_size": 2,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0392156862745099,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 13,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
75 |
"should_evaluate": false,
|
76 |
"should_log": false,
|
77 |
"should_save": true,
|
78 |
+
"should_training_stop": true
|
79 |
},
|
80 |
"attributes": {}
|
81 |
}
|
82 |
},
|
83 |
+
"total_flos": 3707722751016960.0,
|
84 |
"train_batch_size": 2,
|
85 |
"trial_name": null,
|
86 |
"trial_params": null
|