Training in progress, step 7, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 864368280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:879311a4aebc17b4fafcb549aa97630288d831fabf9f2b7c29c0be0e3f4d6cd9
|
3 |
size 864368280
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1729074742
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3307f49c2895af38b46962aea4ec72240ac1ecffff0a114178a9d05df44a3d28
|
3 |
size 1729074742
|
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 sha256:99b98c21a6c7c3c92fc68e617bba8fd566712396b2134a20b6aff6e47927480b
|
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": 2.
|
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,
|
@@ -69,6 +69,14 @@
|
|
69 |
"eval_samples_per_second": 7.766,
|
70 |
"eval_steps_per_second": 3.107,
|
71 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
}
|
73 |
],
|
74 |
"logging_steps": 3,
|
@@ -88,7 +96,7 @@
|
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
-
"total_flos": 1.
|
92 |
"train_batch_size": 4,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.6363636363636362,
|
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,
|
|
|
69 |
"eval_samples_per_second": 7.766,
|
70 |
"eval_steps_per_second": 3.107,
|
71 |
"step": 6
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 2.6363636363636362,
|
75 |
+
"eval_loss": 0.0004186338628642261,
|
76 |
+
"eval_runtime": 0.6418,
|
77 |
+
"eval_samples_per_second": 7.791,
|
78 |
+
"eval_steps_per_second": 3.116,
|
79 |
+
"step": 7
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 3,
|
|
|
96 |
"attributes": {}
|
97 |
}
|
98 |
},
|
99 |
+
"total_flos": 1.1753603576365056e+16,
|
100 |
"train_batch_size": 4,
|
101 |
"trial_name": null,
|
102 |
"trial_params": null
|