Training in progress, step 955

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "base_model_name_or_path": "HuggingFaceH4/mistral-7b-sft-beta",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj",
     "k_proj",
-    "down_proj"
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30a7a4badef97c6dfcd8926c13ead9c59cb66a2a3eeb2b655d70e26c1cef415
+oid sha256:b8536ff19ec7018ef89bae2852ce52776f2d31cb826c9d48e0fcaad4cbff9d03
 size 335605144

special_tokens_map.json

@@ -1,4 +1,9 @@
 {
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -27,7 +28,11 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
   "bos_token": "<s>",
   "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
@@ -38,6 +43,7 @@
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe19b748ca3fddccc7ee76272be28fd47fa1e74bf00b4cac21fa1ecd0626e9d
-size 6200
+oid sha256:b01eda64c995920d56d88bf2c19f7d830a6527691e7cba97d27965809403bf20
+size 6648