yaniseuranova
commited on
Commit
•
e55d77b
1
Parent(s):
c54cce5
Training in progress, step 60
Browse files- all_results.json +8 -8
- eval_results.json +4 -4
- model.safetensors +1 -1
- runs/Aug30_08-26-44_7e2de4304170/events.out.tfevents.1725006458.7e2de4304170 +3 -0
- runs/Aug30_08-27-51_7e2de4304170/events.out.tfevents.1725006472.7e2de4304170 +3 -0
- train_results.json +4 -4
- trainer_state.json +16 -16
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
"total_flos": 1.7978141590585344e+16,
|
9 |
-
"train_loss": 0.
|
10 |
-
"train_runtime": 22.
|
11 |
-
"train_samples_per_second": 10.
|
12 |
-
"train_steps_per_second": 2.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.02930055744946003,
|
5 |
+
"eval_runtime": 2.166,
|
6 |
+
"eval_samples_per_second": 26.777,
|
7 |
+
"eval_steps_per_second": 3.693,
|
8 |
"total_flos": 1.7978141590585344e+16,
|
9 |
+
"train_loss": 0.3378882090250651,
|
10 |
+
"train_runtime": 22.8868,
|
11 |
+
"train_samples_per_second": 10.137,
|
12 |
+
"train_steps_per_second": 2.622
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.02930055744946003,
|
5 |
+
"eval_runtime": 2.166,
|
6 |
+
"eval_samples_per_second": 26.777,
|
7 |
+
"eval_steps_per_second": 3.693
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343223968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:953fd1dc14bcfe4abbbc4074f5f494a5910fdeb3f3c545442210eccd9e7d17fe
|
3 |
size 343223968
|
runs/Aug30_08-26-44_7e2de4304170/events.out.tfevents.1725006458.7e2de4304170
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad9c4b85611803c1f263162539c266d4c8b44a573e66f834ea13f47c6679544b
|
3 |
+
size 357
|
runs/Aug30_08-27-51_7e2de4304170/events.out.tfevents.1725006472.7e2de4304170
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32f34170112b4fd8d7ec18ca3c8b3d117bdaf93031a56379a2b547dfd4820e12
|
3 |
+
size 6439
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 1.7978141590585344e+16,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime": 22.
|
6 |
-
"train_samples_per_second": 10.
|
7 |
-
"train_steps_per_second": 2.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 1.7978141590585344e+16,
|
4 |
+
"train_loss": 0.3378882090250651,
|
5 |
+
"train_runtime": 22.8868,
|
6 |
+
"train_samples_per_second": 10.137,
|
7 |
+
"train_steps_per_second": 2.622
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,54 +10,54 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6666666666666666,
|
13 |
-
"grad_norm": 1.
|
14 |
"learning_rate": 0.0001666666666666667,
|
15 |
-
"loss": 0.
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.3333333333333333,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 0.00013333333333333334,
|
22 |
-
"loss": 0.
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 2.0,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 0.0001,
|
29 |
-
"loss": 0.
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.6666666666666665,
|
34 |
-
"grad_norm": 0.
|
35 |
"learning_rate": 6.666666666666667e-05,
|
36 |
-
"loss": 0.
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 3.3333333333333335,
|
41 |
-
"grad_norm": 0.
|
42 |
"learning_rate": 3.3333333333333335e-05,
|
43 |
-
"loss": 0.
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 4.0,
|
48 |
-
"grad_norm": 0.
|
49 |
"learning_rate": 0.0,
|
50 |
-
"loss": 0.
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 4.0,
|
55 |
"step": 60,
|
56 |
"total_flos": 1.7978141590585344e+16,
|
57 |
-
"train_loss": 0.
|
58 |
-
"train_runtime": 22.
|
59 |
-
"train_samples_per_second": 10.
|
60 |
-
"train_steps_per_second": 2.
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 10,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.6666666666666666,
|
13 |
+
"grad_norm": 1.332340121269226,
|
14 |
"learning_rate": 0.0001666666666666667,
|
15 |
+
"loss": 0.6343,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 1.3333333333333333,
|
20 |
+
"grad_norm": 2.4813578128814697,
|
21 |
"learning_rate": 0.00013333333333333334,
|
22 |
+
"loss": 0.6705,
|
23 |
"step": 20
|
24 |
},
|
25 |
{
|
26 |
"epoch": 2.0,
|
27 |
+
"grad_norm": 12.414591789245605,
|
28 |
"learning_rate": 0.0001,
|
29 |
+
"loss": 0.4595,
|
30 |
"step": 30
|
31 |
},
|
32 |
{
|
33 |
"epoch": 2.6666666666666665,
|
34 |
+
"grad_norm": 0.5009147524833679,
|
35 |
"learning_rate": 6.666666666666667e-05,
|
36 |
+
"loss": 0.1393,
|
37 |
"step": 40
|
38 |
},
|
39 |
{
|
40 |
"epoch": 3.3333333333333335,
|
41 |
+
"grad_norm": 0.22140513360500336,
|
42 |
"learning_rate": 3.3333333333333335e-05,
|
43 |
+
"loss": 0.0828,
|
44 |
"step": 50
|
45 |
},
|
46 |
{
|
47 |
"epoch": 4.0,
|
48 |
+
"grad_norm": 0.21809758245944977,
|
49 |
"learning_rate": 0.0,
|
50 |
+
"loss": 0.0409,
|
51 |
"step": 60
|
52 |
},
|
53 |
{
|
54 |
"epoch": 4.0,
|
55 |
"step": 60,
|
56 |
"total_flos": 1.7978141590585344e+16,
|
57 |
+
"train_loss": 0.3378882090250651,
|
58 |
+
"train_runtime": 22.8868,
|
59 |
+
"train_samples_per_second": 10.137,
|
60 |
+
"train_steps_per_second": 2.622
|
61 |
}
|
62 |
],
|
63 |
"logging_steps": 10,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba7eb858551fcb097ddfd61ed2f90174151a8d0add0067132e152ce53542b915
|
3 |
size 5176
|