End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-orchamath-lora
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
 
 ## Model description
 
@@ -33,10 +33,10 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0001
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 0
+- seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - num_epochs: 1
@@ -47,8 +47,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.39.3
-- Pytorch 2.2.2
+- PEFT 0.10.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
 - Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_config.json

@@ -6,27 +6,28 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "spectral_bottom": false,
   "spectral_top": false,
   "target_modules": [
-    "v_proj",
-    "up_proj",
     "down_proj",
+    "up_proj",
     "k_proj",
-    "gate_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd3843c76462e08f5bddcf5d18944c89311905fc56835e0a19e8da0643e546b
-size 302041912
+oid sha256:fb7626b696273f67961180cfbef24e1cce6771be90e8042fe12a84e07f6d10bf
+size 37799672

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f600243213199b42cdde022d8f24d67cb44b4eadf462c5e270160d256ff575
+oid sha256:274f719e7b1e68343980c1ee3245161bddb6bd6d0fb800240c2adeaa900af876
 size 4920