checkpoint-1700-v4
Browse files- README.md +1 -1
- adapter_config.json +7 -6
- adapter_model.safetensors +2 -2
- optimizer.pt +2 -2
- scheduler.pt +1 -1
- trainer_state.json +0 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
base_model: unsloth/qwen2.5-0.5b
|
3 |
library_name: peft
|
4 |
---
|
5 |
|
|
|
1 |
---
|
2 |
+
base_model: unsloth/qwen2.5-0.5b
|
3 |
library_name: peft
|
4 |
---
|
5 |
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "unsloth/qwen2.5-0.5b
|
5 |
"bias": "none",
|
6 |
"eva_config": null,
|
7 |
"exclude_modules": null,
|
@@ -18,20 +18,21 @@
|
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": [
|
|
|
21 |
"lm_head"
|
22 |
],
|
23 |
"peft_type": "LORA",
|
24 |
-
"r":
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
|
|
|
|
|
|
28 |
"k_proj",
|
29 |
"q_proj",
|
30 |
-
"up_proj",
|
31 |
-
"v_proj",
|
32 |
"down_proj",
|
33 |
-
"
|
34 |
-
"o_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
37 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/qwen2.5-0.5b",
|
5 |
"bias": "none",
|
6 |
"eva_config": null,
|
7 |
"exclude_modules": null,
|
|
|
18 |
"megatron_config": null,
|
19 |
"megatron_core": "megatron.core",
|
20 |
"modules_to_save": [
|
21 |
+
"embed_tokens",
|
22 |
"lm_head"
|
23 |
],
|
24 |
"peft_type": "LORA",
|
25 |
+
"r": 16,
|
26 |
"rank_pattern": {},
|
27 |
"revision": null,
|
28 |
"target_modules": [
|
29 |
+
"gate_proj",
|
30 |
+
"o_proj",
|
31 |
+
"v_proj",
|
32 |
"k_proj",
|
33 |
"q_proj",
|
|
|
|
|
34 |
"down_proj",
|
35 |
+
"up_proj"
|
|
|
36 |
],
|
37 |
"task_type": "CAUSAL_LM",
|
38 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd24e24b9e9ac2e9e94046fcc12a9c0cc35ac57c6e4598b67a0f1e7b8675ee47
|
3 |
+
size 579775952
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae86a8dddfcb85f17a42d51600cfcc7ffeecedd17a7a5f8d4c81d55f3a2844d0
|
3 |
+
size 571859772
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10a5dab67af519845eac645ac4a741e3907ce89b888a8546509b408fce597029
|
3 |
size 1064
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1271f1f54ea6aa2d1713daf7042fbb8490c4ea7300fcbfb84f807306c7a7e967
|
3 |
size 5624
|