Training in progress, step 5, 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:e4c1ddeee7fb8fcd043f8a112334a14d99fbe6739194dbc28ed9868c6721dca9
|
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 sha256:103a96ef37cb357fa5c1052bbbc4b2a7dd59f64e361fb5446389e16a531c1ecf
|
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:f963f3b18e1ce5bf60b7659ac5cb6aaa997b0bf1c1c52830e575d74128f1f231
|
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 sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
|
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,
|
@@ -46,6 +46,14 @@
|
|
46 |
"eval_samples_per_second": 13.473,
|
47 |
"eval_steps_per_second": 4.491,
|
48 |
"step": 4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 3,
|
@@ -65,7 +73,7 @@
|
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
-
"total_flos":
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.2857142857142856,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 5,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
46 |
"eval_samples_per_second": 13.473,
|
47 |
"eval_steps_per_second": 4.491,
|
48 |
"step": 4
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.2857142857142856,
|
52 |
+
"eval_loss": NaN,
|
53 |
+
"eval_runtime": 0.2232,
|
54 |
+
"eval_samples_per_second": 13.442,
|
55 |
+
"eval_steps_per_second": 4.481,
|
56 |
+
"step": 5
|
57 |
}
|
58 |
],
|
59 |
"logging_steps": 3,
|
|
|
73 |
"attributes": {}
|
74 |
}
|
75 |
},
|
76 |
+
"total_flos": 7109443426713600.0,
|
77 |
"train_batch_size": 8,
|
78 |
"trial_name": null,
|
79 |
"trial_params": null
|