Training in progress, step 10
Browse files
README.md
CHANGED
@@ -4,8 +4,8 @@ library_name: transformers
|
|
4 |
model_name: Qwen2-0.5B-GRPO-test
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
-
- trl
|
8 |
- grpo
|
|
|
9 |
licence: license
|
10 |
---
|
11 |
|
|
|
4 |
model_name: Qwen2-0.5B-GRPO-test
|
5 |
tags:
|
6 |
- generated_from_trainer
|
|
|
7 |
- grpo
|
8 |
+
- trl
|
9 |
licence: license
|
10 |
---
|
11 |
|
adapter_config.json
CHANGED
@@ -25,8 +25,8 @@
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"target_parameters": null,
|
32 |
"task_type": "CAUSAL_LM",
|
|
|
25 |
"rank_pattern": {},
|
26 |
"revision": null,
|
27 |
"target_modules": [
|
28 |
+
"v_proj",
|
29 |
+
"q_proj"
|
30 |
],
|
31 |
"target_parameters": null,
|
32 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2175168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f844e09404ae3b99bca6c032d09eb1240b95a69bc844b584b30e91af919f8854
|
3 |
size 2175168
|
runs/Sep04_17-16-45_r4inst/events.out.tfevents.1756999023.r4inst
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9423
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a150f6bad9cf49a13e8042cb81c04d3b18bd19e6cae11313b007e25077cba02e
|
3 |
size 9423
|
runs/Sep04_17-24-42_r4inst/events.out.tfevents.1756999491.r4inst
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5b769ebf93e90c44d2066b3167c0128fa2d839b60cfdc51303d6a739a2a4eda
|
3 |
+
size 7897
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6993
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef376834623865a8ff10720fb41512c12edfd4847327e9fa5374858d6d354c15
|
3 |
size 6993
|