vanherzog/Mixtral_Alpace_v2_NIKI

README.md

@@ -19,8 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
 # Mixtral_Alpace_v2_NIKI
 
 This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3429
 
 ## Model description
 
@@ -40,20 +38,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2.5e-05
-- train_batch_size: 8
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 0.03
-- training_steps: 10
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.3678        | 0.0606 | 10   | 1.3429          |
-
+- training_steps: 300
 
 ### Framework versions
 

runs/May01_10-53-12_fa05a75abf57/events.out.tfevents.1714560800.fa05a75abf57.281.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4920b0e92a18a42994ae17487d2a061a44f98cda7c1e79528969a5b17f7afadc
+size 4184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0dbf698588b77ea006c912a98e500352d60aec2ee07d76b6cd15315f61aecb2
+oid sha256:dbe1f4e76d9f3e41b2c1dc12d129abb190c4437549bfb30b5e3b82304279edab
 size 5048