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: 1.4551
+- Loss: 1.4866
 
 ## Model description
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3263        | 0.22  | 25   | 1.4551          |
-| 1.4328        | 0.43  | 50   | 1.4551          |
-| 1.4559        | 0.65  | 75   | 1.4551          |
-| 1.4446        | 0.86  | 100  | 1.4551          |
-| 1.4565        | 1.08  | 125  | 1.4551          |
-| 1.3922        | 1.29  | 150  | 1.4551          |
-| 1.3697        | 1.51  | 175  | 1.4551          |
-| 1.4504        | 1.72  | 200  | 1.4551          |
+| 1.3299        | 0.22  | 25   | 1.4606          |
+| 1.4385        | 0.43  | 50   | 1.4657          |
+| 1.4628        | 0.65  | 75   | 1.4560          |
+| 1.4457        | 0.86  | 100  | 1.4538          |
+| 1.4249        | 1.08  | 125  | 1.4624          |
+| 1.2826        | 1.29  | 150  | 1.4834          |
+| 1.264         | 1.51  | 175  | 1.4860          |
+| 1.3431        | 1.72  | 200  | 1.4866          |
 
 
 ### Framework versions

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:1d4aa27b3696e05f1cd612b74e2ca087497f0a8fd4837b42f2ed27cb0ffbb917
+size 54549712

runs/Mar04_13-34-29_f7ad4747e4a8/events.out.tfevents.1709559269.f7ad4747e4a8.1838.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe0d813db65c8fb322778466fac3e1795c6fa626405e2fe39202ead055d2a45
+size 11716

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d34dcd61de275b075414ab76f9e08f65d632ad46566f29d790e5d2391daac8
+oid sha256:41fbfff89d59b82561e7a45340838521acd56f185733ed361ecc7b073de3f28b
 size 4920