Model save
Browse files- all_results.json +17 -17
- eval_results.json +8 -8
- runs/Dec31_23-40-45_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735688523.hn-fornix-testing-gpu-platform-2.1028595.1 +3 -0
- runs/Dec31_23-47-53_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735688888.hn-fornix-testing-gpu-platform-2.1030578.0 +3 -0
- test_results.json +7 -7
- train_results.json +3 -3
- trainer_state.json +9 -9
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,21 +1,21 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"eval_f1": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_precision": 0.
|
6 |
-
"eval_recall": 0.
|
7 |
-
"eval_runtime": 0.
|
8 |
-
"eval_samples_per_second":
|
9 |
-
"eval_steps_per_second": 4.
|
10 |
-
"test_f1": 0.
|
11 |
-
"test_loss":
|
12 |
-
"test_precision": 0.
|
13 |
-
"test_recall": 0.
|
14 |
-
"test_runtime": 0.
|
15 |
-
"test_samples_per_second":
|
16 |
-
"test_steps_per_second": 3.
|
17 |
"train_loss": 1.836273193359375,
|
18 |
-
"train_runtime": 55.
|
19 |
-
"train_samples_per_second":
|
20 |
-
"train_steps_per_second": 0.
|
21 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"eval_f1": 0.12910686958067819,
|
4 |
+
"eval_loss": 1.8330078125,
|
5 |
+
"eval_precision": 0.16504066117321736,
|
6 |
+
"eval_recall": 0.1890018282051825,
|
7 |
+
"eval_runtime": 0.2281,
|
8 |
+
"eval_samples_per_second": 8767.11,
|
9 |
+
"eval_steps_per_second": 4.384,
|
10 |
+
"test_f1": 0.12457335796698589,
|
11 |
+
"test_loss": 1.833984375,
|
12 |
+
"test_precision": 0.16755594823291797,
|
13 |
+
"test_recall": 0.1749254997504109,
|
14 |
+
"test_runtime": 0.3141,
|
15 |
+
"test_samples_per_second": 6366.553,
|
16 |
+
"test_steps_per_second": 3.183,
|
17 |
"train_loss": 1.836273193359375,
|
18 |
+
"train_runtime": 55.3814,
|
19 |
+
"train_samples_per_second": 577.811,
|
20 |
+
"train_steps_per_second": 0.289
|
21 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_f1": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_precision": 0.
|
6 |
-
"eval_recall": 0.
|
7 |
-
"eval_runtime": 0.
|
8 |
-
"eval_samples_per_second":
|
9 |
-
"eval_steps_per_second": 4.
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_f1": 0.12910686958067819,
|
4 |
+
"eval_loss": 1.8330078125,
|
5 |
+
"eval_precision": 0.16504066117321736,
|
6 |
+
"eval_recall": 0.1890018282051825,
|
7 |
+
"eval_runtime": 0.2281,
|
8 |
+
"eval_samples_per_second": 8767.11,
|
9 |
+
"eval_steps_per_second": 4.384
|
10 |
}
|
runs/Dec31_23-40-45_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735688523.hn-fornix-testing-gpu-platform-2.1028595.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82f51daf4ecc2397b6b606e478b1fd1796bad352a2636ce7fda6a54ee2b8b2ab
|
3 |
+
size 500
|
runs/Dec31_23-47-53_hn-fornix-testing-gpu-platform-2/events.out.tfevents.1735688888.hn-fornix-testing-gpu-platform-2.1030578.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fad170bb4e5fc427e08dba614e7eb018daf49b93053ec3cf3f8b2b5128e745fc
|
3 |
+
size 7818
|
test_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"test_f1": 0.
|
3 |
-
"test_loss":
|
4 |
-
"test_precision": 0.
|
5 |
-
"test_recall": 0.
|
6 |
-
"test_runtime": 0.
|
7 |
-
"test_samples_per_second":
|
8 |
-
"test_steps_per_second": 3.
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"test_f1": 0.12457335796698589,
|
3 |
+
"test_loss": 1.833984375,
|
4 |
+
"test_precision": 0.16755594823291797,
|
5 |
+
"test_recall": 0.1749254997504109,
|
6 |
+
"test_runtime": 0.3141,
|
7 |
+
"test_samples_per_second": 6366.553,
|
8 |
+
"test_steps_per_second": 3.183
|
9 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"train_loss": 1.836273193359375,
|
4 |
-
"train_runtime": 55.
|
5 |
-
"train_samples_per_second":
|
6 |
-
"train_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"train_loss": 1.836273193359375,
|
4 |
+
"train_runtime": 55.3814,
|
5 |
+
"train_samples_per_second": 577.811,
|
6 |
+
"train_steps_per_second": 0.289
|
7 |
}
|
trainer_state.json
CHANGED
@@ -21,9 +21,9 @@
|
|
21 |
"eval_loss": 1.8330078125,
|
22 |
"eval_precision": 0.16504066117321736,
|
23 |
"eval_recall": 0.1890018282051825,
|
24 |
-
"eval_runtime": 8.
|
25 |
-
"eval_samples_per_second":
|
26 |
-
"eval_steps_per_second": 0.
|
27 |
"step": 8
|
28 |
},
|
29 |
{
|
@@ -46,9 +46,9 @@
|
|
46 |
"eval_loss": 1.8330078125,
|
47 |
"eval_precision": 0.16504066117321736,
|
48 |
"eval_recall": 0.1890018282051825,
|
49 |
-
"eval_runtime": 0.
|
50 |
-
"eval_samples_per_second":
|
51 |
-
"eval_steps_per_second": 3.
|
52 |
"step": 16
|
53 |
},
|
54 |
{
|
@@ -56,9 +56,9 @@
|
|
56 |
"step": 16,
|
57 |
"total_flos": 1489153141243904.0,
|
58 |
"train_loss": 1.836273193359375,
|
59 |
-
"train_runtime": 55.
|
60 |
-
"train_samples_per_second":
|
61 |
-
"train_steps_per_second": 0.
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 5,
|
|
|
21 |
"eval_loss": 1.8330078125,
|
22 |
"eval_precision": 0.16504066117321736,
|
23 |
"eval_recall": 0.1890018282051825,
|
24 |
+
"eval_runtime": 8.5241,
|
25 |
+
"eval_samples_per_second": 234.629,
|
26 |
+
"eval_steps_per_second": 0.117,
|
27 |
"step": 8
|
28 |
},
|
29 |
{
|
|
|
46 |
"eval_loss": 1.8330078125,
|
47 |
"eval_precision": 0.16504066117321736,
|
48 |
"eval_recall": 0.1890018282051825,
|
49 |
+
"eval_runtime": 0.2771,
|
50 |
+
"eval_samples_per_second": 7218.143,
|
51 |
+
"eval_steps_per_second": 3.609,
|
52 |
"step": 16
|
53 |
},
|
54 |
{
|
|
|
56 |
"step": 16,
|
57 |
"total_flos": 1489153141243904.0,
|
58 |
"train_loss": 1.836273193359375,
|
59 |
+
"train_runtime": 55.3814,
|
60 |
+
"train_samples_per_second": 577.811,
|
61 |
+
"train_steps_per_second": 0.289
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 5,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3eca857a5e7424f30d3c72eb902866ef8a6aa76cff072375554179622676a32
|
3 |
size 6840
|