paul-stansifer/llama3-qwantz-gen

README.md

@@ -1,9 +1,9 @@
 ---
-license: llama2
+base_model: unsloth/llama-3-8b-bnb-4bit
 library_name: peft
+license: llama2
 tags:
 - generated_from_trainer
-base_model: unsloth/llama-3-8b-bnb-4bit
 model-index:
 - name: llama3-qwantz-gen
   results: []
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.4044
+- eval_loss: 1.4032
+- eval_runtime: 305.3925
+- eval_samples_per_second: 0.508
+- eval_steps_per_second: 0.128
+- epoch: 0.8052
+- step: 248
 
 ## Model description
 
@@ -41,22 +46,12 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
-
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.5072        | 0.2013 | 62   | 1.4683          |
-| 1.3859        | 0.4026 | 124  | 1.4277          |
-| 1.3615        | 0.6039 | 186  | 1.4143          |
-| 1.3761        | 0.8052 | 248  | 1.4044          |
-
+- num_epochs: 2
 
 ### Framework versions
 
 - PEFT 0.11.1
 - Transformers 4.41.2
 - Pytorch 2.3.0+cu121
-- Datasets 2.19.2
+- Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "k_proj",
     "v_proj",
-    "q_proj",
-    "k_proj"
+    "o_proj",
+    "q_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:ad12c76dc75d7b2e3a5456807749fedbeec9270bf4094dbc71f0fb0366f4933e
+oid sha256:bdc66dcd776a7511e925982f8d1b6c4d8b6fcc150e159f9ecf22563acf5eb373
 size 54560368

runs/Jul12_15-29-47_0aa09e1ec8f8/events.out.tfevents.1720798188.0aa09e1ec8f8.494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599e483f59fac80f13bf3bd48cf176c21b59d50e72ab7e5a26e154e9986cfe6d
+size 10125

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d438c6d93b28027ae191269cf45c7f34f382ff16511d0dabe1d72d255709698f
+oid sha256:44abc76211d6bcfcad6bdd9fdad8a28bfe03bf64381d4253c4f7cbcb551f6344
 size 5112