vuongnhathien
commited on
Commit
•
a9dbef9
1
Parent(s):
4a87f46
Training in progress, epoch 1
Browse files
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.4897708531712e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime": 81.
|
6 |
-
"train_samples_per_second": 7.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.4897708531712e+17,
|
4 |
+
"train_loss": 0.9100998878479004,
|
5 |
+
"train_runtime": 81.5049,
|
6 |
+
"train_samples_per_second": 7.852,
|
7 |
+
"train_steps_per_second": 0.491
|
8 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 350850048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a41fc9bbacdabc6af040a9154031959e80834cf136b9dec137e0dbd1315a4c8
|
3 |
size 350850048
|
runs/Jun02_08-43-54_ed60960060fb/events.out.tfevents.1717318005.ed60960060fb.34.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a1a6b28b3f31f80ab92b34c99c56e36fa7b7e6562513a668e541009e72f35e1
|
3 |
+
size 405
|
runs/Jun02_08-43-54_ed60960060fb/events.out.tfevents.1717319406.ed60960060fb.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:993069f5577853128fb5e34aae6d3e3725f6d37c0d794f3cc198bdc6648efe92
|
3 |
+
size 5829
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.4897708531712e+17,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime": 81.
|
6 |
-
"train_samples_per_second": 7.
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.4897708531712e+17,
|
4 |
+
"train_loss": 0.9100998878479004,
|
5 |
+
"train_runtime": 81.5049,
|
6 |
+
"train_samples_per_second": 7.852,
|
7 |
+
"train_steps_per_second": 0.491
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./test-top-5-acc/checkpoint-40",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,21 +10,21 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_accuracy": 0.
|
14 |
-
"eval_loss": 0.
|
15 |
-
"eval_runtime":
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_steps_per_second": 2.
|
18 |
"step": 40
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.0,
|
22 |
"step": 40,
|
23 |
"total_flos": 1.4897708531712e+17,
|
24 |
-
"train_loss": 0.
|
25 |
-
"train_runtime": 81.
|
26 |
-
"train_samples_per_second": 7.
|
27 |
-
"train_steps_per_second": 0.
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 100,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.46936607360839844,
|
3 |
"best_model_checkpoint": "./test-top-5-acc/checkpoint-40",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.8472222222222222,
|
14 |
+
"eval_loss": 0.46936607360839844,
|
15 |
+
"eval_runtime": 4.3862,
|
16 |
+
"eval_samples_per_second": 32.83,
|
17 |
+
"eval_steps_per_second": 2.052,
|
18 |
"step": 40
|
19 |
},
|
20 |
{
|
21 |
"epoch": 1.0,
|
22 |
"step": 40,
|
23 |
"total_flos": 1.4897708531712e+17,
|
24 |
+
"train_loss": 0.9100998878479004,
|
25 |
+
"train_runtime": 81.5049,
|
26 |
+
"train_samples_per_second": 7.852,
|
27 |
+
"train_steps_per_second": 0.491
|
28 |
}
|
29 |
],
|
30 |
"logging_steps": 100,
|