kyryl-opens-ml
commited on
Commit
•
02703cb
1
Parent(s):
53aab42
End of training
Browse files- adapter_config.json +2 -2
- all_results.json +6 -6
- eval_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "SEQ_2_SEQ_LM"
|
26 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v",
|
23 |
+
"q"
|
24 |
],
|
25 |
"task_type": "SEQ_2_SEQ_LM"
|
26 |
}
|
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"eval_loss": 2.021235942840576,
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second":
|
7 |
"train_loss": 2.7679789066314697,
|
8 |
-
"train_runtime": 0.
|
9 |
-
"train_samples_per_second": 0.
|
10 |
-
"train_steps_per_second": 1.
|
11 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"eval_loss": 2.021235942840576,
|
4 |
+
"eval_runtime": 13.6322,
|
5 |
+
"eval_samples_per_second": 576.357,
|
6 |
+
"eval_steps_per_second": 36.091,
|
7 |
"train_loss": 2.7679789066314697,
|
8 |
+
"train_runtime": 0.7741,
|
9 |
+
"train_samples_per_second": 0.129,
|
10 |
+
"train_steps_per_second": 1.292
|
11 |
}
|
eval_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"eval_loss": 2.021235942840576,
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second":
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"eval_loss": 2.021235942840576,
|
4 |
+
"eval_runtime": 13.6322,
|
5 |
+
"eval_samples_per_second": 576.357,
|
6 |
+
"eval_steps_per_second": 36.091
|
7 |
}
|
train_results.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"train_loss": 2.7679789066314697,
|
4 |
-
"train_runtime": 0.
|
5 |
-
"train_samples_per_second": 0.
|
6 |
-
"train_steps_per_second": 1.
|
7 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.02,
|
3 |
"train_loss": 2.7679789066314697,
|
4 |
+
"train_runtime": 0.7741,
|
5 |
+
"train_samples_per_second": 0.129,
|
6 |
+
"train_steps_per_second": 1.292
|
7 |
}
|
trainer_state.json
CHANGED
@@ -13,9 +13,9 @@
|
|
13 |
"step": 1,
|
14 |
"total_flos": 517012193280.0,
|
15 |
"train_loss": 2.7679789066314697,
|
16 |
-
"train_runtime": 0.
|
17 |
-
"train_samples_per_second": 0.
|
18 |
-
"train_steps_per_second": 1.
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
|
|
13 |
"step": 1,
|
14 |
"total_flos": 517012193280.0,
|
15 |
"train_loss": 2.7679789066314697,
|
16 |
+
"train_runtime": 0.7741,
|
17 |
+
"train_samples_per_second": 0.129,
|
18 |
+
"train_steps_per_second": 1.292
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|