Training in progress, step 20

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "k_proj",
     "o_proj",
-    "up_proj",
-    "v_proj",
+    "down_proj",
     "gate_proj",
-    "q_proj"
+    "up_proj",
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71163ddfa02d1262f9dc5559e9efcd1a196a8b6582a782c9da9a2afb3d05154
+oid sha256:458e37d6e9b11b021a63c83c973242f925c0b88008207af0d2d228d8f977c5c9
 size 11301520

metrics.json

@@ -1 +1 @@
-{"run_name": "./custom_deepspeed", "train_runtime": 264.4556, "train_samples_per_second": 12.1, "train_steps_per_second": 0.076, "total_flos": 3.848728354383462e+16, "train_loss": 1.6189483642578124, "epoch": 0.0365296803652968}
+{"run_name": "./custom_deepspeed", "train_runtime": 264.5412, "train_samples_per_second": 12.096, "train_steps_per_second": 0.076, "total_flos": 3.848728354383462e+16, "train_loss": 1.6230262756347655, "epoch": 0.0365296803652968}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b4ef0ada0bb7702fd24371930da3d2298189a4d27c86b3c9aac6c85f106d575
-size 6289
+oid sha256:415e6d75d57b9d5459258bbd164747ad0006c273748d93a679d31fa50ce702be
+size 7633