End of training

README.md

@@ -114,7 +114,7 @@ xformers_attention: null
 
 This model is a fine-tuned version of [unsloth/tinyllama-chat](https://huggingface.co/unsloth/tinyllama-chat) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0756
+- Loss: 1.0771
 
 ## Model description
 
@@ -153,10 +153,10 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
 | 1.6449        | 0.0036 | 1    | 1.3712          |
-| 1.2327        | 0.0179 | 5    | 1.3046          |
-| 1.1865        | 0.0358 | 10   | 1.1667          |
-| 0.9997        | 0.0538 | 15   | 1.1061          |
-| 1.077         | 0.0717 | 20   | 1.0756          |
+| 1.2343        | 0.0179 | 5    | 1.3073          |
+| 1.1898        | 0.0358 | 10   | 1.1699          |
+| 1.0003        | 0.0538 | 15   | 1.1078          |
+| 1.0803        | 0.0717 | 20   | 1.0771          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,10 +22,10 @@
   "target_modules": [
     "o_proj",
     "v_proj",
-    "k_proj",
     "down_proj",
-    "up_proj",
     "gate_proj",
+    "up_proj",
+    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9afa57aae6fb41d6c2cf3480aa4262a359b673c50de036302f1098b63e322abf
+oid sha256:28cec1dcdd37b7266bccead698416b2ffe7928af705d7e4872664772fa66bca9
 size 101036698

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d021bed2dd2ea6cbc23c3a8b867bffdd55f4c368e04d09f17f3b51d4d108b02
+oid sha256:cb6e295ad631ead3de5960e8ca95d746da3534bf237f79aa05f672c56c4a8753
 size 100966336

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e50aba904d39c5864e0f36c27d2c58f2cca1afdba552845d8b36d9735033ed
+oid sha256:8ad82ad32525e933af8b9fc0db6dec8e95c1d489a1adc2b0fa6be91ccfcf9268
 size 6712