rajtest/llama2_update_model_senti

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/llama-2-7b-bnb-4bit](https://huggingface.co/unsloth/llama-2-7b-bnb-4bit) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6415
+- Loss: 0.0000
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5898        | 0.9981 | 262  | 0.6107          |
-| 0.5152        | 2.0    | 525  | 0.6107          |
-| 0.3907        | 2.9943 | 786  | 0.6415          |
+| 0.0           | 0.9981 | 262  | 0.0000          |
+| 0.0           | 2.0    | 525  | 0.0000          |
+| 0.0           | 2.9943 | 786  | 0.0000          |
 
 
 ### Framework versions

adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "k_proj",
-    "gate_proj",
+    "v_proj",
     "q_proj",
+    "down_proj",
     "o_proj",
-    "v_proj",
-    "down_proj"
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59b30e8d76172471eaeb0ef0d9229110a340843d6e2242a968b90f32485f69c
+oid sha256:11d01e2d22c647175bf0c8c08f71b3c232ff0e45532078d31a557aa45af4bac1
 size 159967880

runs/Aug20_04-15-56_ef6e98509916/events.out.tfevents.1724127359.ef6e98509916.351.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e09566e6944842b84ec792416c742c5ee76387acbd25bbab97317f35d680fc6
+size 8047

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892a245f81bc957aafeeed5e1675b7e15b7170b6c9921e590058f76a36aa246c
+oid sha256:baa299a672a9e4b150423b76b38b8e6b1d6c1e5809dccd5b888f8573c46889cf
 size 5176