Kartheekb7/peft_llava_llama_2

README.md

@@ -1,5 +1,5 @@
 ---
-library_name: transformers
+library_name: peft
 license: llama3.2
 base_model: meta-llama/Llama-3.2-1B-Instruct
 tags:
@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 4
-- eval_batch_size: 8
+- learning_rate: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 5
+- training_steps: 10000
 
 ### Training results
 
@@ -47,7 +47,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
+- PEFT 0.13.2
 - Transformers 4.45.1
-- Pytorch 2.4.0+cpu
+- Pytorch 2.4.0
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17860c0cf5f03ab720fe637f05b45e712181b2c2af3a4773b2755899a819ad94
+size 6833928

runs/Oct29_17-41-50_4be4fe3b6de8/events.out.tfevents.1730223711.4be4fe3b6de8.115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34deba61516e7f38c72a01ee5ec596fd098d69cb4054c2a82d24d261d35e2fd6
+size 27141

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e42dec63cc3c3adacca7fe0920c03f791419ad1dd0cc28a538866ffd176ba7
+oid sha256:4acc6fa46b6208a4d69e9e7ae1a49babfeabd2c3e3d34bc4992689b017eb3a40
 size 5176