End of training

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: 0.03
-- training_steps: 10
+- training_steps: 100
 
 ### Training results
 

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
+    "k_proj",
     "v_proj",
     "gate_proj",
-    "k_proj",
-    "q_proj",
-    "o_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb795f9fe468854fb26f9b989ba4a71ec2a6899ccb9e53afaa2e16f74871d6ba
+oid sha256:53a6315aae6af16d8b33c622955e7f0e21938a3de2bb3e8565eb4809020faad1
 size 184592616

runs/May27_16-44-26_e7b77b27a26e/events.out.tfevents.1716828293.e7b77b27a26e.2463.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:389767f50f970e1471c707d11707f7698aaac80c26d9c59e9507fa52bd316fc5
+size 88

runs/May27_16-49-26_e7b77b27a26e/events.out.tfevents.1716828600.e7b77b27a26e.17940.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce93729abd04dfd022a14d0aa5fff330f1df17f904cb6b219864c80735b1f02
+size 7697

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d318d7dbd4d07582aa41b699e6107cca197296b7f959c374dd432c539e4d8055
+oid sha256:63ff68597d9d6fa8d953026d4731f771be1a70978e24b1d749402b285dc0bc35
 size 5112