Training in progress, step 500

adapter_config.json

@@ -10,17 +10,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "v_proj",
+    "k_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993bccaeae86515dfe8850337ccedd4972ba04695250a9397dbe017be1baab27
-size 9457520
+oid sha256:cca8fe96ed909e05df20ca6f961f0dd1de1d686ad665965e48a5e9937c05c913
+size 7108136

runs/Sep05_19-54-05_632e9ea172c1/events.out.tfevents.1725566047.632e9ea172c1.587254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d0dc91405054cc832cb3bba5540b6ec67c325f1208230a343b83fc08b3c770
+size 4184

runs/Sep05_19-57-51_632e9ea172c1/events.out.tfevents.1725566273.632e9ea172c1.589776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adef28ca17761498df804a013c124acdb627931ce7c4f40030c61d20a1afc83a
+size 4184

runs/Sep05_20-05-17_632e9ea172c1/events.out.tfevents.1725566719.632e9ea172c1.590900.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b33570ea785e8ac12c2f1d05dae11308e432427ee0af3e8cdc23aed580729b
+size 4184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b25f2878401c234c9383813c9a0aae1f4b93a35eb3da32b2a9bdf17fb62b895
+oid sha256:f1ce35009f186db29559ca704e389cacd95dcb79fde29440a0b027134128d37b
 size 5304