adil0101/falcon_instruct_generation

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-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5623
+- Loss: 0.5379
 
 ## Model description
 
@@ -53,17 +53,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.6959        | 1.0   | 20   | 0.6080          |
-| 0.6022        | 2.0   | 40   | 0.5696          |
-| 0.5497        | 3.0   | 60   | 0.5566          |
-| 0.4953        | 4.0   | 80   | 0.5542          |
-| 0.4469        | 5.0   | 100  | 0.5623          |
+| 0.7039        | 1.0   | 20   | 0.5936          |
+| 0.5821        | 2.0   | 40   | 0.5534          |
+| 0.5477        | 3.0   | 60   | 0.5422          |
+| 0.4996        | 4.0   | 80   | 0.5402          |
+| 0.4485        | 5.0   | 100  | 0.5379          |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.3
+- Transformers 4.40.0
 - Pytorch 2.2.2+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35ea1f109783c5796c1cc37533ba82a7117d6ef640ae0b5602dc6f483e5fb7d
+oid sha256:cb4678f4cf156e9c32fe3e380e02e93105c10979d2231e8c98ceebe4524f28fd
 size 109069176

runs/Apr18_22-45-14_ebeca3ee6be0/events.out.tfevents.1713480316.ebeca3ee6be0.4873.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d774f279e09433848d4279f70887767bb03a73769e37788e986795cdf6f0e8
+size 8932

tokenizer.json

@@ -134,6 +134,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d371f1bf33f7d6dc02637fd323722f184e27363eef225770e2dfd2dc86fda916
-size 4920
+oid sha256:5a3857492eb571d37c27a3e8780ae5baa138d7434de7f221d135538764c2ce22
+size 5048