Training in progress, step 500
Browse files- all_results.json +4 -4
- pytorch_model.bin +1 -1
- runs/Apr19_18-18-14_brutasse/1650392300.707668/events.out.tfevents.1650392300.brutasse.24843.1 +3 -0
- runs/Apr19_18-18-14_brutasse/events.out.tfevents.1650392300.brutasse.24843.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +5 -5
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime": 258.
|
5 |
-
"train_samples_per_second": 32.
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7826860427856446,
|
4 |
+
"train_runtime": 258.8973,
|
5 |
+
"train_samples_per_second": 32.832,
|
6 |
+
"train_steps_per_second": 2.086
|
7 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14963873
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0737bead5076597ff9b508116a9221b1669e8c8645dd5cbe37f4e4f04e533522
|
3 |
size 14963873
|
runs/Apr19_18-18-14_brutasse/1650392300.707668/events.out.tfevents.1650392300.brutasse.24843.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a88c87e272369a82e2fac75b6281bcd334da6e48735ae400c132f007e0082269
|
3 |
+
size 5023
|
runs/Apr19_18-18-14_brutasse/events.out.tfevents.1650392300.brutasse.24843.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edec9767fcf267268deb035ecdfc2dbc59ffc72293ed7a5dc7fa5212701c9a74
|
3 |
+
size 5938
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime": 258.
|
5 |
-
"train_samples_per_second": 32.
|
6 |
-
"train_steps_per_second": 2.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7826860427856446,
|
4 |
+
"train_runtime": 258.8973,
|
5 |
+
"train_samples_per_second": 32.832,
|
6 |
+
"train_steps_per_second": 2.086
|
7 |
}
|
trainer_state.json
CHANGED
@@ -10,17 +10,17 @@
|
|
10 |
{
|
11 |
"epoch": 9.26,
|
12 |
"learning_rate": 3.7037037037037037e-06,
|
13 |
-
"loss": 1.
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
"epoch": 10.0,
|
18 |
"step": 540,
|
19 |
"total_flos": 1.49327778152448e+17,
|
20 |
-
"train_loss": 1.
|
21 |
-
"train_runtime": 258.
|
22 |
-
"train_samples_per_second": 32.
|
23 |
-
"train_steps_per_second": 2.
|
24 |
}
|
25 |
],
|
26 |
"max_steps": 540,
|
|
|
10 |
{
|
11 |
"epoch": 9.26,
|
12 |
"learning_rate": 3.7037037037037037e-06,
|
13 |
+
"loss": 1.8126,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
"epoch": 10.0,
|
18 |
"step": 540,
|
19 |
"total_flos": 1.49327778152448e+17,
|
20 |
+
"train_loss": 1.7826860427856446,
|
21 |
+
"train_runtime": 258.8973,
|
22 |
+
"train_samples_per_second": 32.832,
|
23 |
+
"train_steps_per_second": 2.086
|
24 |
}
|
25 |
],
|
26 |
"max_steps": 540,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3183
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea876266c13e6ddfc3462bad57f207b6841e05eb1b5464b2880ee52a61af70a2
|
3 |
size 3183
|