End of training

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 nipsllm_3601.1733584591283538056.pt.trace.json filter=lfs diff=lfs merge=lfs -text
 nipsllm_13350.1733587985088903357.pt.trace.json filter=lfs diff=lfs merge=lfs -text
+nipsllm_19414.1733589361760356058.pt.trace.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2331
+- Loss: 1.2332
 
 ## Model description
 
@@ -45,7 +45,7 @@ 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: 0.02
-- num_epochs: 0.4
+- num_epochs: 0.43
 
 ### Training results
 
@@ -82,6 +82,8 @@ The following hyperparameters were used during training:
 | 1.2077        | 0.3757 | 58   | 1.2331          |
 | 1.1729        | 0.3887 | 60   | 1.2330          |
 | 1.2643        | 0.4016 | 62   | 1.2331          |
+| 1.3324        | 0.4146 | 64   | 1.2331          |
+| 1.2215        | 0.4275 | 66   | 1.2332          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "q_proj",
-    "k_proj",
     "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
     "o_proj",
-    "down_proj",
-    "gate_proj"
+    "k_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

nipsllm_19414.1733589361760356058.pt.trace.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6acafe330a93670cc865a03390645b33204ad7c9c6ec0dc71fbbbfa7d2983f4
+size 7108103518

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4acdf5d9d14749a7ba943f69011cd34aabbb367437fc76cd520d695b4617adad
+oid sha256:5218ddc8ec609e3a7f01b0f2768d9cff95c7d21a038f162095b01a7715f1ec82
 size 5304