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": 3.0,
|
3 |
"total_flos": 9.210874701004407e+18,
|
4 |
"train_loss": 2.3821448783248442,
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 150796,
|
7 |
-
"train_samples_per_second": 75.
|
8 |
-
"train_steps_per_second": 1.
|
9 |
}
|
|
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 9.210874701004407e+18,
|
4 |
"train_loss": 2.3821448783248442,
|
5 |
+
"train_runtime": 5996.2012,
|
6 |
"train_samples": 150796,
|
7 |
+
"train_samples_per_second": 75.446,
|
8 |
+
"train_steps_per_second": 1.179
|
9 |
}
|
train_results.json
CHANGED
@@ -2,8 +2,8 @@
|
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 9.210874701004407e+18,
|
4 |
"train_loss": 2.3821448783248442,
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 150796,
|
7 |
-
"train_samples_per_second": 75.
|
8 |
-
"train_steps_per_second": 1.
|
9 |
}
|
|
|
2 |
"epoch": 3.0,
|
3 |
"total_flos": 9.210874701004407e+18,
|
4 |
"train_loss": 2.3821448783248442,
|
5 |
+
"train_runtime": 5996.2012,
|
6 |
"train_samples": 150796,
|
7 |
+
"train_samples_per_second": 75.446,
|
8 |
+
"train_steps_per_second": 1.179
|
9 |
}
|
trainer_state.json
CHANGED
@@ -111,9 +111,9 @@
|
|
111 |
"step": 7068,
|
112 |
"total_flos": 9.210874701004407e+18,
|
113 |
"train_loss": 2.3821448783248442,
|
114 |
-
"train_runtime":
|
115 |
-
"train_samples_per_second": 75.
|
116 |
-
"train_steps_per_second": 1.
|
117 |
}
|
118 |
],
|
119 |
"logging_steps": 500,
|
|
|
111 |
"step": 7068,
|
112 |
"total_flos": 9.210874701004407e+18,
|
113 |
"train_loss": 2.3821448783248442,
|
114 |
+
"train_runtime": 5996.2012,
|
115 |
+
"train_samples_per_second": 75.446,
|
116 |
+
"train_steps_per_second": 1.179
|
117 |
}
|
118 |
],
|
119 |
"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 7224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa2ad8a78bb9caf7942c3b65abd9cdc9033851a854c32a3b2eb53cc639747551
|
3 |
size 7224
|