End of training

README.md

@@ -1,7 +1,7 @@
 ---
 base_model: microsoft/Phi-3.5-mini-instruct
 library_name: transformers
-model_name: results
+model_name: phi3_5_adapter_model
 tags:
 - generated_from_trainer
 - trl
@@ -9,7 +9,7 @@ tags:
 licence: license
 ---
 
-# Model Card for results
+# Model Card for phi3_5_adapter_model
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -20,7 +20,7 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="yongtaek/results", device="cuda")
+generator = pipeline("text-generation", model="yongtaek/phi3_5_adapter_model", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
@@ -35,7 +35,7 @@ This model was trained with SFT.
 
 - TRL: 0.12.0
 - Transformers: 4.46.2
-- Pytorch: 2.5.1
+- Pytorch: 2.3.0
 - Datasets: 3.1.0
 - Tokenizers: 0.20.3
 

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "qkv_proj",
     "gate_up_proj",
-    "down_proj",
-    "qkv_proj"
+    "o_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01940fef994adcd95c6c24772f60d02ca5342d2982f311dccbd56dc364928479
+oid sha256:eba77701cdb28054bc433bb41335e1fab52199a74c5d7191f1fb6e8442136aa0
 size 402688040

runs/Dec04_04-35-02_e18105abca6d/events.out.tfevents.1733286950.e18105abca6d.4461.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb19555011082d000c2db969e78b7f6ec1629969b8d15a73d21984323e580f2
+size 8307

runs/Dec04_04-36-45_e18105abca6d/events.out.tfevents.1733287015.e18105abca6d.4461.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91ab1b96f13cef1173ce2b11e08aad5ab78ee325034c12e7e08361f6bb77e48
+size 22567

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cb60d212bb9616a866a351092166fa935eee482d0789d7e47427eaba453b20
+oid sha256:ddb13b5198f684e5efc7d98ab507d093a8c7f10719b9fe12fcf27ffd7572b842
 size 5560