acrobatlm/mistral-7binstruct-summary-100s

README.md

@@ -5,9 +5,9 @@ tags:
 - trl
 - sft
 - generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
 - generator
-base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: mistral7binstruct_summarize
   results: []
@@ -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: 1.5011
+- Loss: 1.4968
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.7176        | 0.2212 | 25   | 1.5722          |
-| 1.6267        | 0.4425 | 50   | 1.5011          |
+| 1.7593        | 0.2193 | 25   | 1.5667          |
+| 1.5715        | 0.4386 | 50   | 1.4968          |
 
 
 ### Framework versions
@@ -61,5 +61,5 @@ The following hyperparameters were used during training:
 - PEFT 0.10.0
 - Transformers 4.40.0
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
+- Datasets 2.19.0
 - Tokenizers 0.19.1

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f57bef3246c59c405878b3b707cfc3831e31b553c1484785fd7e68070267572
+oid sha256:752ce582fd5e35becab02cbdbd1e459697b61807dd0febd49c048cc3e90818a1
 size 27280152

runs/Apr20_16-14-09_7f340966f3ab/events.out.tfevents.1713629661.7f340966f3ab.2765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa07aa199f7c0c85cbb078fd326e00941415b130d43726f2b9c64c71593e4ff0
+size 7112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8efaceddd2df97653d20329fcbef2324da8fcd9963392ed719431681c04db7f
+oid sha256:f64f69fc3ae333590dec5b32cc5ae184420b47514ed6ad25b76e50833b38b671
 size 4984