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: 1.6702
+- Loss: 1.5191
 
 ## Model description
 
@@ -39,7 +39,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2857        | 0.03  | 25   | 2.0678          |
-| 1.8703        | 0.05  | 50   | 1.8014          |
-| 1.7283        | 0.08  | 75   | 1.7335          |
-| 1.6706        | 0.11  | 100  | 1.7046          |
-| 1.7128        | 0.13  | 125  | 1.6872          |
-| 1.6585        | 0.16  | 150  | 1.6762          |
-| 1.72          | 0.19  | 175  | 1.6709          |
-| 1.622         | 0.22  | 200  | 1.6702          |
+| 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          |
 
 
 ### Framework versions

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "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:c92f85209000cb52e10bc2a300b89437dad3b66c55e910ee9cf9209d568c6e34
-size 27280152
+oid sha256:b9b8685f80dd1450b204fc2031b1e0b5ea56a7d35efbb3b31a478c8ecfdb1e36
+size 54543184

runs/Mar04_14-45-38_ed9712ffb2e1/events.out.tfevents.1709563538.ed9712ffb2e1.567.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d94f9e2bd25349cbc65ca7453da83c4a7316468c942c622bd935159622be01
+size 9072

runs/Mar04_14-53-42_ed9712ffb2e1/events.out.tfevents.1709564022.ed9712ffb2e1.567.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cb6442b2352ed30c6b13ba4bfb5779e38bb261d55946f838317c9a02af3f6a
+size 7293

runs/Mar04_14-59-30_ed9712ffb2e1/events.out.tfevents.1709564370.ed9712ffb2e1.567.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443f0834b7ac93b4c299eac3cf15cda84ee4a805de487442b68f882e711e9510
+size 11716

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:debbd06bc8d0da008d82e044da756b8583115cef0b42e4ea46718c71007d4251
+oid sha256:0d267d5071f5602d321678bb7a43a6bc9598b39554ffad3a2cb0e3d60eb65608
 size 4920