Model save

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-1B-Instruct
+base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 license: llama3.2
 tags:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lora
 
-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 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 an unknown dataset.
 
 ## Model description
 
@@ -50,8 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.0
+- PEFT 0.13.1
 - Transformers 4.45.2
-- Pytorch 2.4.0
-- Datasets 2.21.0
+- Pytorch 2.4.1
 - Tokenizers 0.20.0

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "LlamaForCausalLM",
     "parent_library": "transformers.models.llama.modeling_llama"
   },
-  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "down_proj",
+    "o_proj",
     "k_proj",
+    "down_proj",
     "q_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "gate_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a303a92702749a443b42817db261f2fdc09af92f3ad54a21280d556fae23b56
-size 1082290000
+oid sha256:edc35461591e376a149bc97ee20d05ba3e08b63b4d1f0a96c620390206290710
+size 1639093264

trainer_state.json

@@ -10,40 +10,40 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 2.1019041538238525,
+      "grad_norm": 2.154229164123535,
       "learning_rate": 7.587548638132295e-05,
-      "loss": 0.6409,
+      "loss": 0.6104,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 1.5811957120895386,
+      "grad_norm": 1.9545427560806274,
       "learning_rate": 5.155642023346303e-05,
-      "loss": 0.3822,
+      "loss": 0.3677,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 1.7442209720611572,
+      "grad_norm": 2.771542549133301,
       "learning_rate": 2.7237354085603113e-05,
-      "loss": 0.3562,
+      "loss": 0.3307,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 1.6806491613388062,
+      "grad_norm": 2.780686140060425,
       "learning_rate": 2.9182879377431908e-06,
-      "loss": 0.3371,
+      "loss": 0.2978,
       "step": 1000
     },
     {
       "epoch": 2.0,
       "step": 1030,
-      "total_flos": 2.5008097487007744e+17,
-      "train_loss": 0.42616625943230196,
-      "train_runtime": 12653.0234,
-      "train_samples_per_second": 20.839,
-      "train_steps_per_second": 0.081
+      "total_flos": 7.232215420241879e+17,
+      "train_loss": 0.39821495037634397,
+      "train_runtime": 29524.5328,
+      "train_samples_per_second": 8.931,
+      "train_steps_per_second": 0.035
     }
   ],
   "logging_steps": 250,
@@ -63,7 +63,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5008097487007744e+17,
+  "total_flos": 7.232215420241879e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0677869408295d702cf38fcd8dfcebdedaa43f304e1e6cdee198846531fc6a5c
+oid sha256:04956adb5217175aaa36e11b2da87eace1a9f30a2a1627cc233a8fb4044febf4
 size 5176