Training in progress, step 300

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/llama-2-7b",
+  "base_model_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "up_proj",
+    "o_proj",
     "k_proj",
+    "up_proj",
+    "gate_proj",
     "v_proj",
-    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:955f08f4035429adbfaf4f7b9f231d7ee9dadc72be9b5e4082d5544a7d584667
-size 159967880
+oid sha256:a5d51a97009f47cfe68e6bd0b61fbc5f9825a04f4f6f66a3968cc410b788916e
+size 167832240

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -25,14 +27,16 @@
       "special": true
     }
   },
+  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 4096,
+  "legacy": true,
+  "model_max_length": 32768,
   "pad_token": "<unk>",
   "padding_side": "right",
   "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef851fa80f86633184d3b999b4d4b5d6e87522407e1c87ebca99f72dc4681ff3
-size 4536
+oid sha256:103e2fd40afe139f7b824b072c3cdeec30ae99b239db3007e3a20abcf10473a8
+size 4664