Training in progress, step 1900

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "up_proj",
-    "q_proj",
     "gate_proj",
     "down_proj",
-    "o_proj",
-    "k_proj"
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f28ad317e1d23fc764f93d152aa0417c6143646cb0e2f0f8e122ea0d9b6d88b9
+oid sha256:cac8df109dc1a48947927bccb834ffcbeb1556abaef98a836e41c2a9703e5c97
 size 671150064

runs/Apr05_19-58-41_allennlp-cirrascale-50.reviz.ai2.in/events.out.tfevents.1712372721.allennlp-cirrascale-50.reviz.ai2.in.49327.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec58a9f511bf997774492c14497b1fd6c4523e03078dbc4e969759e2216e41c2
-size 142934
+oid sha256:3c0a52645a90eaff093f102696d932312230be5386d4ca42cb92314b7f9d8c4b
+size 150554

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aed5e0579321afe046a90c0cc3a32c7d4cff2e81f00dc7223fdf2c95545813e
-size 5048
+oid sha256:947d927e61668b966ebb030da458e99bc33c421e45b93f656e038a0689c6f570
+size 5112