Training in progress, step 4, 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 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e661a0d3726d1e40e33fb6c8305d1549867653aecb8b32f3e7643a23e386967
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5afc4b38a643969f108871550f71bcdd6cf6ab9e8f1098858106736ec367816f
|
3 |
size 328468404
|
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 sha256:45f1f318f9413aafe69a36595e5bb7bcdbdff88710bdb6c9f7ab2a70ccfa3731
|
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:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
|
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,
|
@@ -38,6 +38,14 @@
|
|
38 |
"eval_samples_per_second": 12.931,
|
39 |
"eval_steps_per_second": 4.31,
|
40 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"logging_steps": 3,
|
@@ -57,7 +65,7 @@
|
|
57 |
"attributes": {}
|
58 |
}
|
59 |
},
|
60 |
-
"total_flos":
|
61 |
"train_batch_size": 8,
|
62 |
"trial_name": null,
|
63 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.571428571428571,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
38 |
"eval_samples_per_second": 12.931,
|
39 |
"eval_steps_per_second": 4.31,
|
40 |
"step": 3
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 2.571428571428571,
|
44 |
+
"eval_loss": NaN,
|
45 |
+
"eval_runtime": 0.2227,
|
46 |
+
"eval_samples_per_second": 13.473,
|
47 |
+
"eval_steps_per_second": 4.491,
|
48 |
+
"step": 4
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 3,
|
|
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
+
"total_flos": 5687554741370880.0,
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|