Training in progress, epoch 0

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
     "o_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a126b3dff573bc42c185fdc14d10f4007712a89a09afdec39645fda79b8dac
+oid sha256:ffc51da30d7ee80dcd5c370b0c5edffe4e852ffa5c4f39653383a6e6859844fa
 size 109086416

config.json

@@ -17,7 +17,7 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "num_local_experts": 8,
-  "output_router_logits": true,
+  "output_router_logits": false,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",

runs/Feb29_20-51-41_azure-jap/events.out.tfevents.1709239903.azure-jap.6633.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b603ea22b78be3982ed28d43c9b08c46b0a20d9f0dcfedb6e0a0a8fab683f3c
+size 15241

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f4e75195439e3cdd0b24ae52a89f22f6c2bf1aae525a1b48ac39d438d6902c
+oid sha256:0a876d3ad1a3da34bc655ebf92da2818115160b7167df404045d8b809728134d
 size 4859