mistralai/mistral-instruct-generation_tr

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [malhajar/Mistral-7B-Instruct-v0.2-turkish](https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1798
+- Loss: 0.0124
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.5135        | 0.0268 | 20   | 1.4756          |
-| 1.2468        | 0.0537 | 40   | 1.3090          |
-| 1.3422        | 0.0805 | 60   | 1.2245          |
-| 1.1841        | 0.1074 | 80   | 1.1970          |
-| 1.1622        | 0.1342 | 100  | 1.1798          |
+| 0.3331        | 0.1198 | 20   | 0.1119          |
+| 0.0341        | 0.2395 | 40   | 0.0257          |
+| 0.0207        | 0.3593 | 60   | 0.0180          |
+| 0.0192        | 0.4790 | 80   | 0.0137          |
+| 0.0139        | 0.5988 | 100  | 0.0124          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd4e35dbf36a1b2de637c6bbb85a6a7ce6a5a045ac519fabd8865f8ef615855
+oid sha256:762293ffaf42d2e105b18f3fd6623292ef2a525ccdea3d74ee22e20834b03c13
 size 27280152

runs/Jun05_06-33-33_8b03f221dc5a/events.out.tfevents.1717569232.8b03f221dc5a.839.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15208b8c3aa1a59c6e61baf4c795612b16bcad82828ea29ccf633945ec9aab33
+size 9105

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef6ec3e164939c4103884e565f8151b98dbd920a6edec40f94e68cc44838d44
+oid sha256:779abec1470741eb52211bd5de689a9dd197d8c37f6d5555c175213f9370c828
 size 5112