sampangtf/law-nlp

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # law-nlp
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the None dataset.
 
 ## Model description
 
@@ -33,16 +33,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 5e-05
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
-- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- training_steps: 10
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "bias": "none",
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -17,17 +17,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 4,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
     "up_proj",
+    "v_proj",
     "q_proj",
     "o_proj",
-    "k_proj",
-    "v_proj"
+    "down_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:c184aeab4771f11aaa4617f92d78eddee35eef1ee64e2fca6bec505a2bf630f6
-size 24378648
+oid sha256:91ee21799eb515b87715145619beb950b11ca1db15625c805664a251d18d76b8
+size 48679352

runs/Oct06_18-45-39_a08af0033c7c/events.out.tfevents.1728240340.a08af0033c7c.218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3065ea58d127c3f9b5f8f5d41b69f6ef2c88c10d83debeffdaf8a7187678758
+size 6536

runs/Oct06_19-00-11_a08af0033c7c/events.out.tfevents.1728241211.a08af0033c7c.218.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85207e5358cf24d5e3c1a9b593d0a71e2711396a1b8343779afdfebccc8bae58
+size 22823

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4490b5e0c61ca5b905b86405f90804f53a24f21b3b044e843cb04a8f4d6b45a1
+oid sha256:81a2fdca9537711a6f57d53e2a2c44da5f22eb98c357353ee8db0e499c64ff80
 size 5240