Training in progress, step 18000

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -24,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "k_proj",
+    "o_proj",
+    "gate_proj",
     "down_proj",
     "up_proj",
-    "o_proj",
     "q_proj",
-    "gate_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6df9a92c9f9a1695c272e73bbd9e2a550957c2df8194cc3d0ca01feda4230a
-size 872476576
+oid sha256:add9cf0d0586e0e704b741ea0b080528627b2185302a501b69a0771ae185b93f
+size 2436952864

special_tokens_map.json

@@ -1,20 +1,13 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|begin_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
+    "content": "<|end_of_text|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86980e0400d056507c97b2edd15b1fd5f943e4884c9309c4a4915e8670e22c6
+oid sha256:596a7706dd2dff7b0f3aa22a469f3e0a1bfcf925af802d8b3839a1d03f159bc5
 size 5048