mitultiwari/mistral-7b-instruct-summarization-sft

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4693
+- Loss: 1.4712
 
 ## Model description
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7043        | 0.22  | 25   | 1.5441          |
-| 1.5081        | 0.43  | 50   | 1.4693          |
+| 1.7461        | 0.22  | 25   | 1.5484          |
+| 1.5634        | 0.43  | 50   | 1.4712          |
 
 
 ### Framework versions
 
-- PEFT 0.8.2
-- Transformers 4.38.1
+- PEFT 0.9.0
+- Transformers 4.38.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.1
+- Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,9 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81680d7ae504ba370edac0176ec088ac7be3055494a7e975e0f0afea86f4be7
+oid sha256:231466cdc2b072fc42f52110cca8d5556b64ff7081cf86b445c809132aca0efc
 size 27280152

runs/Mar04_00-26-57_8982399105cf/events.out.tfevents.1709512019.8982399105cf.6924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3806a58616eee1fb235d2cd5bbbbb973a5f8cca16f0810c726a77d537f3a2f9e
+size 6966

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63314d514154cba7a6193dc69b9b2ae9ec47ee83bd4abc24668d387e5b69ea2b
+oid sha256:effda184743792267f6dc17f3bf630c7b79cf770218aadd674de247113a2c0cb
 size 4920