Training in progress, epoch 5

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-7b",
+  "base_model_name_or_path": "google/gemma-2b",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,24 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 258,
+  "r": 124,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "k_proj",
     "down_proj",
+    "gate_proj",
+    "up_proj",
     "o_proj",
-    "v_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj"
+    "v_proj"
   ],
-  "task_type": "CAUSAL_LM",
-  "use_rslora": false
+  "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a04b801c9056eee20f7cb0e05018563b9081794027eff49e0a7029fa4a697e
-size 3225309928
+oid sha256:eb8990858b196378834fae0d7392a92e740f5f313a2c24806329b873631c8b1f
+size 607995296

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:062df80807378bb0dd848ebad11036a147ca00e5a9bbc4c8778dfb94826a443e
+oid sha256:fc81d166050007d4ccaad804f8e03cf2abbe18f176d117a1cf180542bb0e800b
 size 4920