Training in progress, step 15, 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 325339796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:242e6b48563091af59d44cb94bdc8612a85936595e389dc9ffde811ee4c7805f
|
3 |
size 325339796
|
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 sha256:1536a74ca4489eb937b3ad7adca5c2d6216c23d952ac8ac1fa64693db343f00d
|
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:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,28 @@
|
|
52 |
"eval_samples_per_second": 13.374,
|
53 |
"eval_steps_per_second": 1.674,
|
54 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 3,
|
@@ -71,7 +93,7 @@
|
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos":
|
75 |
"train_batch_size": 8,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0044526901669758815,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 13.374,
|
53 |
"eval_steps_per_second": 1.674,
|
54 |
"step": 10
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.003562152133580705,
|
58 |
+
"grad_norm": NaN,
|
59 |
+
"learning_rate": 9.938441702975689e-05,
|
60 |
+
"loss": 0.0,
|
61 |
+
"step": 12
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.0044526901669758815,
|
65 |
+
"grad_norm": NaN,
|
66 |
+
"learning_rate": 9.619397662556435e-05,
|
67 |
+
"loss": 0.0,
|
68 |
+
"step": 15
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.0044526901669758815,
|
72 |
+
"eval_loss": NaN,
|
73 |
+
"eval_runtime": 424.023,
|
74 |
+
"eval_samples_per_second": 13.381,
|
75 |
+
"eval_steps_per_second": 1.674,
|
76 |
+
"step": 15
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 3,
|
|
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 2.1288138546610176e+16,
|
97 |
"train_batch_size": 8,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|