Training in progress, step 100

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff8fed1ac295ad6612f1ec72a2e90a858ae01d71f92cdbbce3665b3208cd447
+oid sha256:2f252896c9613c0fedbd910733da9f9435ceb11d3655a3ccfd233d068e70c14c
 size 671150064

runs/Mar07_10-37-47_ale-dpo-1-0-0/events.out.tfevents.1709808377.ale-dpo-1-0-0.1134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c43dc8db670763e6e5285d6d8574e28db2da4ac2f45bd34fe8850b5170e7cd4
+size 13383

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b078c10e6845a22b03afa9a0da2c25ff9bc36784268193bcc785a0d69734dc
+oid sha256:c3cf8aa6be47845e82647cb3169580dedc51e6c45504409861b6a7ab89f8f094
 size 5048