Training in progress, step 31

adapter_config.json

@@ -13,22 +13,19 @@
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": [
-    "embed_tokens",
-    "lm_head"
-  ],
+  "modules_to_save": null,
   "peft_type": "LORA",
   "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
+    "gate_proj",
     "q_proj",
+    "up_proj",
     "v_proj",
     "down_proj",
-    "up_proj",
-    "gate_proj"
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:316878b4a49d1c171a8d228fdc437744ff5d02b881a48e5415e1b417e2a18a30
-size 1656911144
+oid sha256:bd3686256b7ec74df9cbf5a30be3e57dc64e1fef33ce243a2557d8b1e7ccf766
+size 83946192

config.json

@@ -22,5 +22,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.0.dev0",
   "use_cache": false,
-  "vocab_size": 32002
+  "vocab_size": 32000
 }

tokenizer_config.json

@@ -25,22 +25,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "function_token",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "32001": {
-      "content": "conversation_token",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
     }
   },
   "additional_special_tokens": [],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11fb09b85b2473b9ae774df9cc92ebcb8492bf80c76098a21faa9419a7432a48
-size 5624
+oid sha256:d50f11a95e1eddb77c0fc35354918b475fd0da0af52232636216c228afc4352a
+size 5560