steffygreypaul/LoRA_finetuned

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-3B-Instruct
+base_model: meta-llama/Llama-3.2-1B-Instruct
 datasets:
 - generator
 library_name: peft
@@ -18,7 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-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 generator dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0057
 
 ## Model description
 
@@ -37,20 +39,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0005
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 1
-- mixed_precision_training: Native AMP
+- training_steps: 50
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.33          | 0.0277 | 10   | 1.2129          |
+| 1.1447        | 0.0553 | 20   | 1.0979          |
+| 1.0316        | 0.0830 | 30   | 1.0379          |
+| 0.9919        | 0.1107 | 40   | 1.0169          |
+| 0.9903        | 0.1383 | 50   | 1.0057          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -10,18 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 8,
   "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,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_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 sha256:0e5ceb216599113955fb046366e338dd7e36152aa88fd5b332d2e6b3c507beb0
-size 73415408
+oid sha256:b8693e82b93957aaaa01727bf1e8a4a70e603528c24af8fce031e9315c341bb5
+size 3416264

runs/Oct05_09-44-23_1c19e0adc58d/events.out.tfevents.1728121689.1c19e0adc58d.5547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eed07ba5a4cdf354356edc13b9023933ad75674683ce9b53713cff91c130cf7
+size 8229

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fcf876aad706f024be5e4df0f9caa8b0cc643c4c59d036ce47ee3e9dc7d781b
+oid sha256:2972ce8d54804c085c7836ca6776d68f400268c1085966dd58712d0ee5801aef
 size 5432