🍻 cheers
Browse files- all_results.json +8 -8
- eval_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +7 -7
all_results.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 6.
|
6 |
-
"eval_samples_per_second": 5.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"train_loss": 0.
|
9 |
-
"train_runtime":
|
10 |
-
"train_samples_per_second": 4.
|
11 |
-
"train_steps_per_second": 0.
|
12 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.005373110994696617,
|
5 |
+
"eval_runtime": 6.0446,
|
6 |
+
"eval_samples_per_second": 5.956,
|
7 |
+
"eval_steps_per_second": 0.827,
|
8 |
+
"train_loss": 0.05584914175172647,
|
9 |
+
"train_runtime": 136.48,
|
10 |
+
"train_samples_per_second": 4.22,
|
11 |
+
"train_steps_per_second": 0.264
|
12 |
}
|
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.
|
6 |
-
"eval_samples_per_second": 5.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"eval_accuracy": 1.0,
|
4 |
+
"eval_loss": 0.005373110994696617,
|
5 |
+
"eval_runtime": 6.0446,
|
6 |
+
"eval_samples_per_second": 5.956,
|
7 |
+
"eval_steps_per_second": 0.827
|
8 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples_per_second": 4.
|
6 |
-
"train_steps_per_second": 0.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
+
"train_loss": 0.05584914175172647,
|
4 |
+
"train_runtime": 136.48,
|
5 |
+
"train_samples_per_second": 4.22,
|
6 |
+
"train_steps_per_second": 0.264
|
7 |
}
|
trainer_state.json
CHANGED
@@ -10,29 +10,29 @@
|
|
10 |
{
|
11 |
"epoch": 1.11,
|
12 |
"learning_rate": 0.00014444444444444444,
|
13 |
-
"loss": 0.
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 2.22,
|
18 |
"learning_rate": 8.888888888888889e-05,
|
19 |
-
"loss": 0.
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 3.33,
|
24 |
"learning_rate": 3.3333333333333335e-05,
|
25 |
-
"loss": 0.
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 4.0,
|
30 |
"step": 36,
|
31 |
"total_flos": 4.463538601800499e+16,
|
32 |
-
"train_loss": 0.
|
33 |
-
"train_runtime":
|
34 |
-
"train_samples_per_second": 4.
|
35 |
-
"train_steps_per_second": 0.
|
36 |
}
|
37 |
],
|
38 |
"max_steps": 36,
|
|
|
10 |
{
|
11 |
"epoch": 1.11,
|
12 |
"learning_rate": 0.00014444444444444444,
|
13 |
+
"loss": 0.182,
|
14 |
"step": 10
|
15 |
},
|
16 |
{
|
17 |
"epoch": 2.22,
|
18 |
"learning_rate": 8.888888888888889e-05,
|
19 |
+
"loss": 0.0101,
|
20 |
"step": 20
|
21 |
},
|
22 |
{
|
23 |
"epoch": 3.33,
|
24 |
"learning_rate": 3.3333333333333335e-05,
|
25 |
+
"loss": 0.0058,
|
26 |
"step": 30
|
27 |
},
|
28 |
{
|
29 |
"epoch": 4.0,
|
30 |
"step": 36,
|
31 |
"total_flos": 4.463538601800499e+16,
|
32 |
+
"train_loss": 0.05584914175172647,
|
33 |
+
"train_runtime": 136.48,
|
34 |
+
"train_samples_per_second": 4.22,
|
35 |
+
"train_steps_per_second": 0.264
|
36 |
}
|
37 |
],
|
38 |
"max_steps": 36,
|