Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: meta-llama/Llama-3.2-3B-Instruct
+base_model: meta-llama/Llama-3.2-1B-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-3.2-3B-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-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -42,11 +42,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 4
+- num_epochs: 2
+
+### Training results
+
+
 
 ### Framework versions
 
 - PEFT 0.13.0
-- Transformers 4.43.4
+- Transformers 4.45.2
 - Pytorch 2.4.0
-- Tokenizers 0.19.1
+- Datasets 2.21.0
+- 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-3.2-3B-Instruct",
+  "base_model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
+    "v_proj",
     "o_proj",
-    "down_proj",
-    "up_proj",
     "gate_proj",
-    "v_proj",
-    "q_proj"
+    "down_proj",
+    "up_proj"
   ],
   "task_type": null,
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f60d803e465c15a3b1329a1a39c05400aaf1f0b148f411bc29d7b9ad1b2794cc
-size 1639093264
+oid sha256:87c6245eb4daaee1c4c5b51cba6948ff67053ebab3759dc1a01a4ca4fc4dc776
+size 1082290000

trainer_state.json

@@ -1,17 +1,55 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": null,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 0,
+  "global_step": 1030,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [],
-  "logging_steps": 500,
-  "max_steps": 0,
+  "log_history": [
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 1.80476975440979,
+      "learning_rate": 7.587548638132295e-05,
+      "loss": 0.6951,
+      "step": 250
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 1.3268828392028809,
+      "learning_rate": 5.155642023346303e-05,
+      "loss": 0.3819,
+      "step": 500
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 1.490614414215088,
+      "learning_rate": 2.7237354085603113e-05,
+      "loss": 0.3553,
+      "step": 750
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 1.4715696573257446,
+      "learning_rate": 2.9182879377431908e-06,
+      "loss": 0.3348,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "step": 1030,
+      "total_flos": 2.5008097487007744e+17,
+      "train_loss": 0.43835841891835037,
+      "train_runtime": 12656.9656,
+      "train_samples_per_second": 20.832,
+      "train_steps_per_second": 0.081
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 1030,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 0,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -25,8 +63,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 0,
-  "train_batch_size": null,
+  "total_flos": 2.5008097487007744e+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 sha256:433a5ba8b7a30a164725af7d6b34b7b3888f93ad48028cccf8be71dc4fe79bbf
+oid sha256:b8e0dae5103974b746d2fdd4495fd0e5453b289bdb72e5f359295701cf7eb031
 size 5176