Model save

README.md

@@ -6,8 +6,6 @@ tags:
 - sft
 - generated_from_trainer
 base_model: Viet-Mistral/Vistral-7B-Chat
-datasets:
-- generator
 model-index:
 - name: vietnamese-news-summarization-vistral-7b
   results: []
@@ -18,9 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vietnamese-news-summarization-vistral-7b
 
-This model is a fine-tuned version of [Viet-Mistral/Vistral-7B-Chat](https://huggingface.co/Viet-Mistral/Vistral-7B-Chat) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.2539
+This model is a fine-tuned version of [Viet-Mistral/Vistral-7B-Chat](https://huggingface.co/Viet-Mistral/Vistral-7B-Chat) on an unknown dataset.
 
 ## Model description
 
@@ -48,17 +44,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 0.03
 - training_steps: 100
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.2306        | 0.0060 | 20   | 1.2918          |
-| 1.2802        | 0.0119 | 40   | 1.2651          |
-| 1.4084        | 0.0179 | 60   | 1.2528          |
-| 1.2944        | 0.0238 | 80   | 1.2497          |
-| 1.288         | 0.0298 | 100  | 1.2539          |
-
-
 ### Framework versions
 
 - PEFT 0.10.0

adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "lm_head",
     "v_proj",
-    "k_proj",
-    "up_proj",
+    "gate_proj",
     "o_proj",
     "q_proj",
-    "down_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee800e98cdedc1291dd6d3480cc3da5dc5a37a0bcebcbaa7e64eedecda81b66
+oid sha256:5c0a04c8e78c679d5d984a2fb1d55635400cbf91ff676da1c63d9e8f9ae6ec06
 size 1310658800

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fe97dd103430815b891f2662819b75a267bec5baf6a117674bad779c1c37829
+oid sha256:3abe19c5218c6edaa71d54dfb2b20648c33de801feaeb5c3d863a3898476c135
 size 5240