Training in progress, step 150

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-2-7b-chat-bnb-4bit",
+  "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
     "up_proj",
     "k_proj",
     "q_proj",
-    "gate_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b97d1c23158519bf1ae810d3922a872561ba30e8beb2584aa04baec5c2e7a7
-size 5117112704
+oid sha256:0ae0e474d7c7e036aafe1155d020869d830a252e5bd2405aeede6467ee276fcd
+size 5368770952

runs/Oct31_12-11-48_85d6f7dc0655/events.out.tfevents.1730376726.85d6f7dc0655.1452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575f62add635f219e8217698faec60861f839aef1c4bd12cbb8dbafdd35a7c04
+size 11463

special_tokens_map.json

@@ -14,7 +14,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<unk>",
+    "content": "[control_768]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c60f9cfc7e9c83a0c06145e2a7609cca95ba652065569a1cee831cd648f1fcd3
-size 5496
+oid sha256:2b04abb745b6d04e2292cd261b5802104a0414b325423d6187272f1223c3d1e8
+size 5432