Model save
Browse files
README.md
CHANGED
@@ -42,8 +42,10 @@ The following hyperparameters were used during training:
|
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 4
|
44 |
- distributed_type: multi-GPU
|
|
|
45 |
- gradient_accumulation_steps: 4
|
46 |
-
- total_train_batch_size:
|
|
|
47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
- lr_scheduler_type: cosine
|
49 |
- num_epochs: 1
|
|
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 4
|
44 |
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 2
|
46 |
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 32
|
48 |
+
- total_eval_batch_size: 16
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
51 |
- num_epochs: 1
|
adapter_config.json
CHANGED
@@ -19,12 +19,12 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"q_proj",
|
24 |
-
"up_proj",
|
25 |
"o_proj",
|
|
|
|
|
26 |
"down_proj",
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
"down_proj",
|
27 |
+
"up_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_rslora": false
|
runs/May16_15-44-36_c842148f8542/events.out.tfevents.1715874324.c842148f8542.21570.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f88c67cfb4b6c56c505d7e4f4820e2b0c7029d990cc8f229adb5503ee0433ac
|
3 |
+
size 4477
|
step_0/adapter_config.json
CHANGED
@@ -19,12 +19,12 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"q_proj",
|
24 |
-
"up_proj",
|
25 |
"o_proj",
|
|
|
|
|
26 |
"down_proj",
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"v_proj",
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"q_proj",
|
25 |
+
"k_proj",
|
26 |
"down_proj",
|
27 |
+
"up_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_rslora": false
|
step_0/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037cb93649ce2c00bfe42f23882c655e67e006c8997cb25bf1e587e809060da7
|
3 |
size 5688
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:037cb93649ce2c00bfe42f23882c655e67e006c8997cb25bf1e587e809060da7
|
3 |
size 5688
|