Training in progress, step 380
Browse files- README.md +2 -2
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,9 +4,9 @@ library_name: transformers
|
|
| 4 |
model_name: CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.3
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- unsloth
|
| 8 |
-
- trl
|
| 9 |
- grpo
|
|
|
|
|
|
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
|
|
|
| 4 |
model_name: CQoT_SFT_merged_16bit_lora-Llama-3.2-3B-Instruct-v.DR-GRPO_7.3
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
|
|
|
| 7 |
- grpo
|
| 8 |
+
- trl
|
| 9 |
+
- unsloth
|
| 10 |
licence: license
|
| 11 |
---
|
| 12 |
|
adapter_config.json
CHANGED
|
@@ -29,13 +29,13 @@
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
|
|
|
| 32 |
"down_proj",
|
| 33 |
-
"
|
|
|
|
| 34 |
"k_proj",
|
| 35 |
"up_proj",
|
| 36 |
-
"
|
| 37 |
-
"o_proj",
|
| 38 |
-
"q_proj"
|
| 39 |
],
|
| 40 |
"task_type": "CAUSAL_LM",
|
| 41 |
"trainable_token_indices": null,
|
|
|
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
"down_proj",
|
| 34 |
+
"q_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
"k_proj",
|
| 37 |
"up_proj",
|
| 38 |
+
"gate_proj"
|
|
|
|
|
|
|
| 39 |
],
|
| 40 |
"task_type": "CAUSAL_LM",
|
| 41 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 194563400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:666eb92c22aa1c00c715f2d637594bf432ce2069dd9bb7899512f880a79d72b1
|
| 3 |
size 194563400
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7121
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86e1a9a6fce1c0c4701a11718e283ef4150e034147fcb3faf84a82f000984b8b
|
| 3 |
size 7121
|