End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the OpenAssistant/oasst_top1_2023-08-25 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9883
+- Loss: 2.1361
 
 ## Model description
 
@@ -50,9 +50,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.4057        | 1.0   | 56   | 1.5748          |
-| 0.924         | 1.99  | 112  | 1.7516          |
-| 0.6519        | 2.99  | 168  | 1.9883          |
+| 1.8994        | 1.0   | 56   | 1.7425          |
+| 0.8603        | 1.99  | 112  | 1.9602          |
+| 0.5465        | 2.99  | 168  | 2.1361          |
 
 
 ### Framework versions

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "o_proj",
-    "down_proj",
+    "v_proj",
     "q_proj",
+    "gate_proj",
     "up_proj",
-    "k_proj",
-    "v_proj"
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca28466ddc70fde4aaff2e648e9219a65249474dc6635e8f7aa08a847dd7aabc
+oid sha256:a1024314204b45adf00b740187771a2497b34a8408bb4e3ebf72bbca2ec7e5b6
 size 1719791960

runs/Mar04_23-10-59_e67be63dcafc/events.out.tfevents.1709593861.e67be63dcafc.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0970c2605df87cd85685579aa624c23fbb61f1d5a902625e22b656a819a73a97
+size 31910

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f2cac4fd2f80424b260249424878d6b79ec306232cc1158e822e887e8f5f08
+oid sha256:59c77171bacb3634b6bdf042704eb85ba7f19b505a5946fc0961b399778dbe18
 size 4728