Training in progress, step 25

adapter_config.json

@@ -10,23 +10,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj",
-    "down_proj",
-    "up_proj",
-    "k_proj",
     "gate_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj",
+    "v_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:c1a1bb46ed9e48699a6dcd2975a1c10a73f7bf79caefd13c74e78d8de0f4f536
-size 1342239008
+oid sha256:b0cb6e61af3aa5f205aa32fcd554bffa194c030e10d5416a095db26d681cc42e
+size 369142184

runs/Jun12_09-34-03_ip-172-31-30-172.ec2.internal/events.out.tfevents.1718184844.ip-172-31-30-172.ec2.internal.22497.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b4bf627f542401e84a2530ea75feae7d1bbed373f171e29f36f7485350965f4
+size 5544

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 3072,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176cd0caac509f728b33ee995b5840921867029e00ef1afa50f1971190f97381
+oid sha256:442ee676c956fc65c04961ce59c62197bd0e9fd000789efd75bc9789e72e667a
 size 5112