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

README.md

@@ -19,6 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 # mistral7binstruct_summarize
 
 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: 1.4609
 
 ## Model description
 
@@ -44,10 +46,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 0.03
-- training_steps: 10
+- training_steps: 100
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7171        | 0.22  | 25   | 1.5650          |
+| 1.5024        | 0.43  | 50   | 1.4814          |
+| 1.5448        | 0.65  | 75   | 1.4679          |
+| 1.5608        | 0.87  | 100  | 1.4609          |
 
 
 ### Framework versions
@@ -55,5 +63,5 @@ The following hyperparameters were used during training:
 - PEFT 0.9.0
 - Transformers 4.38.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.1
+- Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ab5ba497b1c90003830572904b5d524d6daaeca559b0b47f9dada63737ec7a
+oid sha256:338c6161d978a2adeedb83729204d0d71920cafa6559d2791308175a9510ecc6
 size 27280152

runs/Mar04_01-11-18_66c059ea6931/events.out.tfevents.1709514735.66c059ea6931.560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c3fbd7c94574fb84e5b5d8ddbf94881896cd94c31841e3b6dff76ca820794c
+size 8534

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e3bb4b63831ebf98226e5f0be5567d754e0af49ff18f67f5693af9c6174feea
+oid sha256:de6dba9b27166c339216480508a00f2b8a44115eb085b2132122a2f9e793b446
 size 4920