End of training
Browse files
README.md
CHANGED
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 5
|
48 |
-
-
|
49 |
|
50 |
### Training results
|
51 |
|
|
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 5
|
48 |
+
- num_epochs: 5
|
49 |
|
50 |
### Training results
|
51 |
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": "unsloth",
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
"k_proj",
|
25 |
"gate_proj",
|
26 |
-
"up_proj",
|
27 |
"q_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": "unsloth",
|
22 |
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
+
"v_proj",
|
25 |
"k_proj",
|
26 |
"gate_proj",
|
|
|
27 |
"q_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2814847896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958238713a24f392de5c2923d158603fdb92f47d29daeddd00d97523cb06ec02
|
3 |
size 2814847896
|
runs/Jun19_14-41-21_f7783aeec42f/events.out.tfevents.1718808085.f7783aeec42f.257.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f1903fccc85b8d5579b5293506499c7752333c3ddcd0bebcbc0ef37d0ebd5c7
|
3 |
+
size 158372
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:664cd273722a1ceb84cfe9c0d04c8ef6fd3b7707b97ae195a034ee55330fb013
|
3 |
size 5368
|