End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bn22/Mistral-7B-Instruct-v0.1-sharded](https://huggingface.co/bn22/Mistral-7B-Instruct-v0.1-sharded) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4588
+- Loss: 1.1925
 
 ## Model description
 
@@ -43,15 +43,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- num_epochs: 20
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6538        | 5.71  | 10   | 1.6288          |
-| 1.3789        | 11.43 | 20   | 1.4588          |
+| 1.1387        | 5.71  | 10   | 1.2070          |
+| 0.9337        | 11.43 | 20   | 1.1634          |
+| 0.8676        | 17.14 | 30   | 1.1697          |
+| 0.8065        | 22.86 | 40   | 1.1868          |
+| 0.7759        | 28.57 | 50   | 1.1925          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f15bf7120b945ec3bf8f42bed6fdd0b9b1c4453a065f684a37828e4e0e0977f1
+oid sha256:bb0fe292c94a53468d9c80a1641777d6ce16ef84ac2a21298655b72903e791a7
 size 27280152

runs/Dec01_06-58-43_6d678263285c/events.out.tfevents.1701413923.6d678263285c.161.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ffb6b510c85e095359dea7353520ba32f90af3f65d14e8f82170f681391011
+size 14065

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e162daaf1b9179a328ad43c02b813a355f004d94ec98116b251f4290edc6bc4e
+oid sha256:c8a429ca743faab48d1964a0552fe699384d058521171e6eba96eab4d727ad28
 size 4664