re-trained topic classifier with new labels and prefix
Browse files- all_results.json +4 -4
- train_results.json +4 -4
- trainer_state.json +6 -6
- training_args.bin +0 -0
all_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 3512395654225920.0,
|
4 |
-
"train_loss": 4.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 10842,
|
7 |
-
"train_samples_per_second": 23.
|
8 |
-
"train_steps_per_second": 2.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 3512395654225920.0,
|
4 |
+
"train_loss": 4.205222250789316,
|
5 |
+
"train_runtime": 910.1038,
|
6 |
"train_samples": 10842,
|
7 |
+
"train_samples_per_second": 23.826,
|
8 |
+
"train_steps_per_second": 2.98
|
9 |
}
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 3512395654225920.0,
|
4 |
-
"train_loss": 4.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 10842,
|
7 |
-
"train_samples_per_second": 23.
|
8 |
-
"train_steps_per_second": 2.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 3512395654225920.0,
|
4 |
+
"train_loss": 4.205222250789316,
|
5 |
+
"train_runtime": 910.1038,
|
6 |
"train_samples": 10842,
|
7 |
+
"train_samples_per_second": 23.826,
|
8 |
+
"train_steps_per_second": 2.98
|
9 |
}
|
trainer_state.json
CHANGED
@@ -10,23 +10,23 @@
|
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
"learning_rate": 5e-06,
|
13 |
-
"loss": 6.
|
14 |
"step": 1356
|
15 |
},
|
16 |
{
|
17 |
"epoch": 2.0,
|
18 |
"learning_rate": 0.0,
|
19 |
-
"loss":
|
20 |
"step": 2712
|
21 |
},
|
22 |
{
|
23 |
"epoch": 2.0,
|
24 |
"step": 2712,
|
25 |
"total_flos": 3512395654225920.0,
|
26 |
-
"train_loss": 4.
|
27 |
-
"train_runtime":
|
28 |
-
"train_samples_per_second": 23.
|
29 |
-
"train_steps_per_second": 2.
|
30 |
}
|
31 |
],
|
32 |
"max_steps": 2712,
|
|
|
10 |
{
|
11 |
"epoch": 1.0,
|
12 |
"learning_rate": 5e-06,
|
13 |
+
"loss": 6.2154,
|
14 |
"step": 1356
|
15 |
},
|
16 |
{
|
17 |
"epoch": 2.0,
|
18 |
"learning_rate": 0.0,
|
19 |
+
"loss": 2.1951,
|
20 |
"step": 2712
|
21 |
},
|
22 |
{
|
23 |
"epoch": 2.0,
|
24 |
"step": 2712,
|
25 |
"total_flos": 3512395654225920.0,
|
26 |
+
"train_loss": 4.205222250789316,
|
27 |
+
"train_runtime": 910.1038,
|
28 |
+
"train_samples_per_second": 23.826,
|
29 |
+
"train_steps_per_second": 2.98
|
30 |
}
|
31 |
],
|
32 |
"max_steps": 2712,
|
training_args.bin
CHANGED
Binary files a/training_args.bin and b/training_args.bin differ
|
|