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: 1.4451
+- Loss: 1.4564
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 3
 - training_steps: 200
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5193        | 0.22  | 25   | 1.4962          |
-| 1.5949        | 0.43  | 50   | 1.4670          |
-| 1.5858        | 0.65  | 75   | 1.4560          |
-| 1.5601        | 0.86  | 100  | 1.4491          |
-| 1.5426        | 1.08  | 125  | 1.4476          |
-| 1.4427        | 1.29  | 150  | 1.4457          |
-| 1.428         | 1.51  | 175  | 1.4452          |
-| 1.4782        | 1.72  | 200  | 1.4451          |
+| 1.3933        | 0.22  | 25   | 1.4568          |
+| 1.5293        | 0.43  | 50   | 1.4532          |
+| 1.5359        | 0.65  | 75   | 1.4515          |
+| 1.5199        | 0.86  | 100  | 1.4474          |
+| 1.5109        | 1.08  | 125  | 1.4495          |
+| 1.4256        | 1.29  | 150  | 1.4505          |
+| 1.4093        | 1.51  | 175  | 1.4541          |
+| 1.4664        | 1.72  | 200  | 1.4564          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7787252584fdcbd4558848132e9fa7f0df33dee96f730756483a0e3ccec8d9ba
-size 27282328
+oid sha256:c248fa09951057d010bce1a628d169a97ae41d127401137420b4b8f3c6440ced
+size 13652784

runs/Mar04_13-17-39_f7ad4747e4a8/events.out.tfevents.1709558259.f7ad4747e4a8.1838.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d865ecf80a9b0fee6b2b24423f16df2851b8b88e236298f5cc05cc80cd937b84
+size 11718

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d72561a9c89dca0695ad579ded23197b110e44b22950e8e7ba24b0e6f88ee4
+oid sha256:cccd50edd35c927ff5b99cf051be9491434ac810e4029f9b2cf1afcc763dac54
 size 4920