EdBerg/Baha_1A_cupper_in_gold

README.md

@@ -27,14 +27,14 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jrtabletsms/huggingface/runs/cunjvc0i)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/harpermia882/huggingface/runs/yyxdqfqf)
 
 This model was trained with SFT.
 
 ### Framework versions
 
 - TRL: 0.12.0
-- Transformers: 4.49.0
+- Transformers: 4.48.3
 - Pytorch: 2.5.1+cu124
 - Datasets: 3.3.2
 - Tokenizers: 0.21.0

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj",
     "down_proj",
+    "gate_proj",
+    "q_proj",
+    "o_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b10a6566782afbd6728c6fb88be3fe801f60c042b64c7608ae4b8d58d08d4cd7
+oid sha256:143355e2d637602f6780bd386f3ba0b53283ec5768961bd172b38a9c0ed24cc2
 size 335604696

runs/Mar11_15-24-19_c93113ea815d/events.out.tfevents.1741706660.c93113ea815d.366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2a49f8c80d185cd62246ea577b7dd860c9b4dc429dff13c59411d665ac5087
+size 111512

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13574c77ca1d572525cfa7caac46cee99309100524dad568a7ef85ae383df39f
-size 17210018
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2060,5 +2060,5 @@
   ],
   "model_max_length": 131072,
   "pad_token": "<|eot_id|>",
-  "tokenizer_class": "PreTrainedTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f36bbd9d89e59542b8445818b109ae3b1304a0f3a976dc3a973f048f4af72c44
+oid sha256:1123a6cbbe374404a8c2cd451f808da466e1f022d6c117bb63740a9d4c694124
 size 5624