Training in progress, step 500

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
     "o_proj",
-    "k_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33628ad5ab4aca3422a8bfef5ef30036609afb86d9b06a2793b17b00cab7c4ea
+oid sha256:8bbe43b43cb25b41c99a9cb4acc499e7810b9945ef6c5c206aee3c44a6b6a770
 size 27297032

runs/Nov01_21-31-11_b5a514ce42ec/events.out.tfevents.1730496683.b5a514ce42ec.5894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2d7fd842f6741d861164f05ed384b6f282525a9bae8bf1ed63169e8c7d87db
+size 7164

special_tokens_map.json

@@ -1,24 +1,17 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|eot_id|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e0b12698f5018abdc09ffd6f3d6bd7656f7613be9a0736a917d195f5354db0
+oid sha256:be9f91140b4b9ef5bf3e4fcc94e5b88cd218290efd208f27b750451fae6b86da
 size 5624