gemma2B-It-Caption-Finetuned-2epochs

README.md

@@ -1,5 +1,5 @@
 ---
-license: other
+license: gemma
 library_name: peft
 tags:
 - trl
@@ -36,14 +36,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 1
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 16
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 140
+- training_steps: 251
 
 ### 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": "google/gemma-2b-it",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -15,17 +15,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "o_proj",
+    "k_proj",
     "up_proj",
     "down_proj",
-    "v_proj",
-    "k_proj",
     "gate_proj",
-    "o_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564baef948c1c3ec200d528fd06a5fcd757bff2b54a677d3190b1dae17846cb8
-size 78484352
+oid sha256:4cf3f4e277c396290f8d1f862d6929a3bc25a711f7460257dc7b8babe40e15e1
+size 156926880

runs/Apr09_14-13-41_3505830ebc84/events.out.tfevents.1712672026.3505830ebc84.1544.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fec2ef7b68f481800a25c3606100899009a47ecb3dc9acc51d822241d6404b66
+size 4996

runs/Apr09_14-26-08_3505830ebc84/events.out.tfevents.1712672772.3505830ebc84.1544.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e109a6a021249fab424698d1ec7d7d1e35172235a3f671a48aa29c7dc823fb
+size 4996

runs/Apr09_14-27-01_3505830ebc84/events.out.tfevents.1712672825.3505830ebc84.1544.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04546a595c2e710df914e4fdbdd10322a97cca4534893e88ec3e1699b004d3a4
+size 10577

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce19157ce6b457736a0015a2a4fb06c966c6ff252ec9d1950777eec6598abf6d
-size 17478028
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d762cae44da0ef032ea87b818369afc5bca58006ca7507457c9fb71cee95e261
+oid sha256:e72fce78122e6b846e71c891c51435d95d65ed578da157df66e24faa586095c9
 size 4920