Model save
Browse files- adapter_config.json +4 -4
- all_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"v_proj",
|
24 |
-
"
|
|
|
25 |
"k_proj",
|
|
|
26 |
"down_proj",
|
27 |
-
"up_proj"
|
28 |
-
"q_proj",
|
29 |
-
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"gate_proj",
|
26 |
"k_proj",
|
27 |
+
"o_proj",
|
28 |
"down_proj",
|
29 |
+
"up_proj"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
all_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.0,
|
5 |
-
"train_runtime": 0.
|
6 |
"train_samples": 20000,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.0105,
|
6 |
"train_samples": 20000,
|
7 |
+
"train_samples_per_second": 1898476.441,
|
8 |
+
"train_steps_per_second": 118654.778
|
9 |
}
|
train_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.0,
|
5 |
-
"train_runtime": 0.
|
6 |
"train_samples": 20000,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second":
|
9 |
}
|
|
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 0.0,
|
4 |
"train_loss": 0.0,
|
5 |
+
"train_runtime": 0.0105,
|
6 |
"train_samples": 20000,
|
7 |
+
"train_samples_per_second": 1898476.441,
|
8 |
+
"train_steps_per_second": 118654.778
|
9 |
}
|
trainer_state.json
CHANGED
@@ -3970,9 +3970,9 @@
|
|
3970 |
"step": 1250,
|
3971 |
"total_flos": 0.0,
|
3972 |
"train_loss": 0.0,
|
3973 |
-
"train_runtime": 0.
|
3974 |
-
"train_samples_per_second":
|
3975 |
-
"train_steps_per_second":
|
3976 |
}
|
3977 |
],
|
3978 |
"logging_steps": 5,
|
|
|
3970 |
"step": 1250,
|
3971 |
"total_flos": 0.0,
|
3972 |
"train_loss": 0.0,
|
3973 |
+
"train_runtime": 0.0105,
|
3974 |
+
"train_samples_per_second": 1898476.441,
|
3975 |
+
"train_steps_per_second": 118654.778
|
3976 |
}
|
3977 |
],
|
3978 |
"logging_steps": 5,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc5b53ff73df66c7260b82ecb294a63bdca90dc2d9429f032457138df19f2d95
|
3 |
size 6200
|