End of training

README.md

@@ -35,12 +35,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 1
+- learning_rate: 5e-05
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 256,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c7da2aaa7395b9546939aba64c0f3c0fa8c526db71790465458a7f56d5cc02
-size 84972816
+oid sha256:cd04306d3fc4122de7a33d8c6d774d43473d80d1ee2e9514f619d55bccd231b5
+size 1358993696

runs/May12_16-56-55_d3d5113b4054/events.out.tfevents.1715533093.d3d5113b4054.3173.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52337c0db0a970425ca174f0386a486cc22a2e9f92bf0387cd099ccf2cec0f7d
+size 170522

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c75c59987b0229b9a7b60dfa28eb45c374234e885772a7098e050400bd303d0
+oid sha256:86146dee46cb197e09f8c736f9dd4112a1e96f57d53d0312e0e732c82d0fc162
 size 4728