Training in progress, step 500

adapter_config.json

@@ -1,6 +1,9 @@
 {
   "alpha_pattern": {},
-  "auto_mapping": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama"
+  },
   "base_model_name_or_path": "sarvamai/sarvam-2b-v0.5",
   "bias": "none",
   "fan_in_fan_out": false,
@@ -10,21 +13,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "lm_head",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
     "k_proj",
     "v_proj",
-    "q_proj"
+    "o_proj"
   ],
-  "task_type": "CAUSAL_LM",
+  "task_type": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffb43b4eec709153e712e12cf4d492aa60c5d5f724e305101115f027a5aef32
-size 9197152
+oid sha256:4734f3193c0d3b64f207d921a6da2081e309c71ae6ce7ba67405bc5d17390ee5
+size 925856160

runs/Aug27_16-06-12_c4360c0a3a51/events.out.tfevents.1724774777.c4360c0a3a51.718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6871e6695b1be0c73adaef50770979bb1f227eb3b7313838ad4ad4326cd943
+size 6776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053cbd8ac888cf598c473c0ed514c19aed357ce8fec9afc0382812b44e909005
+oid sha256:0552b941a38395d71b9343e2f45f69b4dc1767fecd44ac9f391e3fffa3d71e69
 size 5240