Training in progress, epoch 1

adapter_config.json

@@ -9,23 +9,25 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "lm_head"
+  ],
   "peft_type": "LORA",
-  "r": 256,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
     "q_proj",
+    "up_proj",
     "o_proj",
     "v_proj",
-    "k_proj",
-    "up_proj"
+    "gate_proj",
+    "down_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 sha256:56b8dae5f9a1f47ebf1fe490086e72129224a6e3ce641dd5ed96ca9c554de1ac
-size 1866560416
+oid sha256:7fe9cee350da10c52853b6c6903c4d606830b57cc7a9c90250b4abf8d0a5e4ec
+size 1132590104

runs/Apr02_11-28-13_603006b3e205/events.out.tfevents.1712057301.603006b3e205.133.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ac7a0d2563c3799baa2ffcb25e708f4cc1e25ad5ed8df8d574c6892c2ef931
+size 4936

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8556e0645a9c47c752075e6802d7c32526f2643a5bbbb920822aa32260a3d285
+oid sha256:90e74608e5255888539e443ced632965dfc0cb94071c79d97fcbc8e8d95f1446
 size 4728