End of training

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3537
+- Loss: 0.3536
 
 ## Model description
 
@@ -41,11 +41,9 @@ The following hyperparameters were used during training:
 - train_batch_size: 16
 - eval_batch_size: 64
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 250
+- training_steps: 12850
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -308,6 +306,7 @@ The following hyperparameters were used during training:
 | 0.3476        | 4.08  | 12700 | 0.3540          |
 | 0.3547        | 4.09  | 12750 | 0.3536          |
 | 0.3529        | 4.11  | 12800 | 0.3537          |
+| 0.3374        | 2.06  | 12850 | 0.3536          |
 
 
 ### Framework versions

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d4040ebbe971787fcd9a56c98db182dc69dfee6b72d61df454ddebedf3b2f5
+oid sha256:549515421a3e673de404ca707c050e805d91eca6172fc2362d9da44fd60cd815
 size 4664