Model save
Browse files
all_results.json
CHANGED
@@ -6,8 +6,8 @@
|
|
6 |
"eval_samples_per_second": 13.325,
|
7 |
"eval_steps_per_second": 1.777,
|
8 |
"total_flos": 9299872197181440.0,
|
9 |
-
"train_loss": 2.
|
10 |
-
"train_runtime": 8.
|
11 |
-
"train_samples_per_second": 13.
|
12 |
-
"train_steps_per_second": 1.
|
13 |
}
|
|
|
6 |
"eval_samples_per_second": 13.325,
|
7 |
"eval_steps_per_second": 1.777,
|
8 |
"total_flos": 9299872197181440.0,
|
9 |
+
"train_loss": 2.0122132897377014,
|
10 |
+
"train_runtime": 8.9154,
|
11 |
+
"train_samples_per_second": 13.46,
|
12 |
+
"train_steps_per_second": 1.795
|
13 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 343254736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29e9ae72ffd7850be2a3b0dc5e74cce7d8e8fec4f531471a799d02a828b580ca
|
3 |
size 343254736
|
runs/Mar22_10-48-55_X5C922065N/events.out.tfevents.1711100937.X5C922065N.52576.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9965efa251dc18aab5e56bc52fd656a67f314c22657383795610bda4f69be548
|
3 |
+
size 6113
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 9299872197181440.0,
|
4 |
-
"train_loss": 2.
|
5 |
-
"train_runtime": 8.
|
6 |
-
"train_samples_per_second": 13.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 4.0,
|
3 |
"total_flos": 9299872197181440.0,
|
4 |
+
"train_loss": 2.0122132897377014,
|
5 |
+
"train_runtime": 8.9154,
|
6 |
+
"train_samples_per_second": 13.46,
|
7 |
+
"train_steps_per_second": 1.795
|
8 |
}
|
trainer_state.json
CHANGED
@@ -10,19 +10,19 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 2.5,
|
13 |
-
"grad_norm": 2.
|
14 |
"learning_rate": 7.500000000000001e-05,
|
15 |
-
"loss": 2.
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 4.0,
|
20 |
"step": 16,
|
21 |
"total_flos": 9299872197181440.0,
|
22 |
-
"train_loss": 2.
|
23 |
-
"train_runtime": 8.
|
24 |
-
"train_samples_per_second": 13.
|
25 |
-
"train_steps_per_second": 1.
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 10,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 2.5,
|
13 |
+
"grad_norm": 2.5313448905944824,
|
14 |
"learning_rate": 7.500000000000001e-05,
|
15 |
+
"loss": 2.2157,
|
16 |
"step": 10
|
17 |
},
|
18 |
{
|
19 |
"epoch": 4.0,
|
20 |
"step": 16,
|
21 |
"total_flos": 9299872197181440.0,
|
22 |
+
"train_loss": 2.0122132897377014,
|
23 |
+
"train_runtime": 8.9154,
|
24 |
+
"train_samples_per_second": 13.46,
|
25 |
+
"train_steps_per_second": 1.795
|
26 |
}
|
27 |
],
|
28 |
"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 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5986e60995f0b4a642b5145e8844c9037ab084eecbe52c98b6672614af74fed9
|
3 |
size 4920
|