End of training
Browse files- adapter_config.json +2 -2
- all_results.json +3 -3
- train_results.json +3 -3
- trainer_state.json +3 -3
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -20,8 +20,8 @@
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
|
|
|
| 20 |
"rank_pattern": {},
|
| 21 |
"revision": null,
|
| 22 |
"target_modules": [
|
| 23 |
+
"v_proj",
|
| 24 |
+
"q_proj"
|
| 25 |
],
|
| 26 |
"task_type": "CAUSAL_LM",
|
| 27 |
"use_dora": false,
|
all_results.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
"epoch": 40.0,
|
| 3 |
"total_flos": 4.167371548576973e+18,
|
| 4 |
"train_loss": 1.28,
|
| 5 |
-
"train_runtime": 813.
|
| 6 |
"train_samples": 2698,
|
| 7 |
-
"train_samples_per_second": 132.
|
| 8 |
-
"train_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 2 |
"epoch": 40.0,
|
| 3 |
"total_flos": 4.167371548576973e+18,
|
| 4 |
"train_loss": 1.28,
|
| 5 |
+
"train_runtime": 813.9929,
|
| 6 |
"train_samples": 2698,
|
| 7 |
+
"train_samples_per_second": 132.581,
|
| 8 |
+
"train_steps_per_second": 0.491
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -2,8 +2,8 @@
|
|
| 2 |
"epoch": 40.0,
|
| 3 |
"total_flos": 4.167371548576973e+18,
|
| 4 |
"train_loss": 1.28,
|
| 5 |
-
"train_runtime": 813.
|
| 6 |
"train_samples": 2698,
|
| 7 |
-
"train_samples_per_second": 132.
|
| 8 |
-
"train_steps_per_second": 0.
|
| 9 |
}
|
|
|
|
| 2 |
"epoch": 40.0,
|
| 3 |
"total_flos": 4.167371548576973e+18,
|
| 4 |
"train_loss": 1.28,
|
| 5 |
+
"train_runtime": 813.9929,
|
| 6 |
"train_samples": 2698,
|
| 7 |
+
"train_samples_per_second": 132.581,
|
| 8 |
+
"train_steps_per_second": 0.491
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -13,9 +13,9 @@
|
|
| 13 |
"step": 400,
|
| 14 |
"total_flos": 4.167371548576973e+18,
|
| 15 |
"train_loss": 1.28,
|
| 16 |
-
"train_runtime": 813.
|
| 17 |
-
"train_samples_per_second": 132.
|
| 18 |
-
"train_steps_per_second": 0.
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
|
|
|
| 13 |
"step": 400,
|
| 14 |
"total_flos": 4.167371548576973e+18,
|
| 15 |
"train_loss": 1.28,
|
| 16 |
+
"train_runtime": 813.9929,
|
| 17 |
+
"train_samples_per_second": 132.581,
|
| 18 |
+
"train_steps_per_second": 0.491
|
| 19 |
}
|
| 20 |
],
|
| 21 |
"logging_steps": 500,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa313f432fbfbf115d032750ed07765306411536623e97638819d769713dfcd3
|
| 3 |
size 8824
|