Training in progress, step 10

README.md

@@ -8,18 +8,18 @@ tags:
 - unsloth
 - generated_from_trainer
 model-index:
-- name: SFT-unsloth-mrd3-Llama-3-8B-Instruct
+- name: SFT-unsloth-garrethlee-MAWPS-Llama-3-8B-Instruct
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# SFT-unsloth-mrd3-Llama-3-8B-Instruct
+# SFT-unsloth-garrethlee-MAWPS-Llama-3-8B-Instruct
 
 This model is a fine-tuned version of [unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7508
+- Loss: 1.0258
 
 ## Model description
 
@@ -47,15 +47,14 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5
-- num_epochs: 1
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.0478        | 0.4278 | 20   | 0.8067          |
-| 0.7757        | 0.8556 | 40   | 0.7508          |
+| 1.5657        | 1.3793 | 10   | 1.0258          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "q_proj",
+    "o_proj",
     "up_proj",
     "v_proj",
-    "o_proj",
+    "down_proj",
+    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba3361ed25d33a37ab6610e84a7e3186f52f33c743fc1b41b7d53e7f1668fd90
+oid sha256:3a381e6920b24fee09d876f75b184d04a2a934ab4db172f4c5173f4ae1cc8ae8
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3528b746e93bcd05c84b9849adf79f2f1aa477c2f9483245ccd644918866f6bd
+oid sha256:bea3ac2aa2a8676b425d5c49a681275c4e5c88294de4c5c4554442fb1f2bf165
 size 5432