Model save

README.md

@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 0.0001
+- num_epochs: 0.001
 
 ### Training results
 

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "k_proj",
+    "up_proj",
     "q_proj",
+    "gate_proj",
     "o_proj",
-    "up_proj",
-    "k_proj",
-    "v_proj",
-    "down_proj"
+    "down_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d895935c1e1d8f12fefcd1d610474ba982c26505088a4b0e47648c07feea196
+oid sha256:08c779faaa234dbbafeff29bdb376c83f9a6bc1447175a45fefa70063b5f9cf5
 size 1342239008

all_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.0,
     "train_loss": 0.6931471824645996,
-    "train_runtime": 22.7564,
-    "train_samples_per_second": 0.04,
-    "train_steps_per_second": 0.044
+    "train_runtime": 56.9215,
+    "train_samples_per_second": 0.158,
+    "train_steps_per_second": 0.035
 }

runs/Jun10_01-23-48_ip-172-31-4-18/events.out.tfevents.1717982674.ip-172-31-4-18.3691.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b49debb792440c288cb33381a56059da6d222c21caf5575eeadd17349714e483
+size 5097

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.0,
     "train_loss": 0.6931471824645996,
-    "train_runtime": 22.7564,
-    "train_samples_per_second": 0.04,
-    "train_steps_per_second": 0.044
+    "train_runtime": 56.9215,
+    "train_samples_per_second": 0.158,
+    "train_steps_per_second": 0.035
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc85119d32ecf4f56e19f8b3bd35e80173ca9a792cd584d0d6d5711a53eba9de
+oid sha256:28bfb9a5bbdffcd64328629d7bbfbceb92c2aff89d5f6a691365e856daa9f5fd
 size 4664