Training in progress, step 180

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "gate_proj",
     "o_proj",
-    "v_proj",
+    "down_proj",
     "q_proj",
-    "k_proj",
     "up_proj",
-    "down_proj",
-    "gate_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16665e931595c3b18e924e20ea00483aa35da292edfbd6b808f0a8c0c70f9654
+oid sha256:0193720627ba187d157f36f3418274618e30626d95bfe5d04776c369ac193274
 size 807445312

config.json

@@ -33,7 +33,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.37.0",
   "use_cache": false,
   "vocab_size": 32000

runs/Jan28_11-08-18_70d5883869d0/events.out.tfevents.1706440165.70d5883869d0.11342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f6dcda63f9eaa3a0fa89f36c6308da2a879ea8acf9d243df555e33f4f3b04f
+size 117642

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481d4c1bee3ea66c70787c290d78b65b2f851bd0f1b1edba3e8f0aa62c79424e
+oid sha256:b5cc2f5dd7838c602c9ca4f054ad3552c9e00913bc17471311ecf66160a4a418
 size 4792