Model save

README.md

@@ -39,8 +39,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5

adapter_config.json

@@ -9,23 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
-  "lora_dropout": 0.0,
+  "lora_alpha": 16,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
-    "gate_proj",
     "up_proj",
     "v_proj",
-    "k_proj",
     "q_proj",
-    "o_proj"
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155384370ab5b739f94702b2f2afc94091bdb01997072bd97626dfb68d0ebcec
-size 4538331488
+oid sha256:4b38c39e740e6bb45b51b4f6a49aca8ed62e9b515cd7e19ae8862e75b99945d9
+size 4370559328

runs/Jun05_12-21-38_2ede59de4e1e/events.out.tfevents.1717590100.2ede59de4e1e.6703.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4435b190cefd7ecb76f813c671b1ce9061ed643e986c7569de320286108de65a
+size 96397

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8146ff80314c2831c413b423394e6b63629924e0c9579df82c8443eb3f62ec39
+oid sha256:6411a7a11c7594f9eb3f38b56a7e3ace631749db3441eb8da44bcd8fd10ae80f
 size 5112