Training in progress, step 7, 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 150486964
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62c58066ebd736de7ffaeec97b826c389c9c1b460c83ab9df2b691f05c06561a
|
3 |
size 150486964
|
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 sha256:5472f98c2ad9bd4abfb8c409ce5738521e3910aae76db97f4e69ffc71a546bc5
|
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 sha256:5d44c0ecfb16f05885a8478afdaa40e988069bb6891bbc6c82185a9b1533b4c7
|
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": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -54,6 +54,29 @@
|
|
54 |
"eval_samples_per_second": 35.288,
|
55 |
"eval_steps_per_second": 5.881,
|
56 |
"step": 5
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 3,
|
@@ -73,7 +96,7 @@
|
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
-
"total_flos":
|
77 |
"train_batch_size": 8,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.1538461538461537,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 7,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
54 |
"eval_samples_per_second": 35.288,
|
55 |
"eval_steps_per_second": 5.881,
|
56 |
"step": 5
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.8461538461538463,
|
60 |
+
"grad_norm": NaN,
|
61 |
+
"learning_rate": 6e-05,
|
62 |
+
"loss": 0.0,
|
63 |
+
"step": 6
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 1.8461538461538463,
|
67 |
+
"eval_loss": NaN,
|
68 |
+
"eval_runtime": 0.1715,
|
69 |
+
"eval_samples_per_second": 34.989,
|
70 |
+
"eval_steps_per_second": 5.831,
|
71 |
+
"step": 6
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.1538461538461537,
|
75 |
+
"eval_loss": NaN,
|
76 |
+
"eval_runtime": 0.1688,
|
77 |
+
"eval_samples_per_second": 35.549,
|
78 |
+
"eval_steps_per_second": 5.925,
|
79 |
+
"step": 7
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 3,
|
|
|
96 |
"attributes": {}
|
97 |
}
|
98 |
},
|
99 |
+
"total_flos": 1819967886458880.0,
|
100 |
"train_batch_size": 8,
|
101 |
"trial_name": null,
|
102 |
"trial_params": null
|