ai-maker-space/mistral-7binstruct-summary-100s

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: 1.5191
+- Loss: 1.4442
 
 ## Model description
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6262        | 0.03  | 25   | 1.6082          |
-| 1.5864        | 0.05  | 50   | 1.5514          |
-| 1.5134        | 0.08  | 75   | 1.5421          |
-| 1.4968        | 0.11  | 100  | 1.5329          |
-| 1.5627        | 0.13  | 125  | 1.5259          |
-| 1.5015        | 0.16  | 150  | 1.5221          |
-| 1.5712        | 0.19  | 175  | 1.5195          |
-| 1.4796        | 0.22  | 200  | 1.5191          |
+| 1.7037        | 0.22  | 25   | 1.5738          |
+| 1.5952        | 0.43  | 50   | 1.4712          |
+| 1.5767        | 0.65  | 75   | 1.4572          |
+| 1.5413        | 0.86  | 100  | 1.4535          |
+| 1.5256        | 1.08  | 125  | 1.4473          |
+| 1.4647        | 1.29  | 150  | 1.4462          |
+| 1.5195        | 1.51  | 175  | 1.4444          |
+| 1.464         | 1.72  | 200  | 1.4442          |
 
 
 ### Framework versions

adapter_config.json

@@ -9,18 +9,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:747dc31a276108f926759d4b7df3f83059f147bffe14c5e2a1cb97214e5ab02f
+size 27280152

runs/Mar04_16-30-13_acaf5e89fb3f/events.out.tfevents.1709569815.acaf5e89fb3f.2701.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b48555f6aaab49fafff779da3d6af3e04d4e609ec55235ef5ee4ff46f603d55
+size 11716

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d267d5071f5602d321678bb7a43a6bc9598b39554ffad3a2cb0e3d60eb65608
+oid sha256:48aa11c2f77e971eaef61863583c088a558ab7455f0f07001507bdadef4cbb3e
 size 4920