Training in progress, epoch 0

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "gpt2",
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -14,7 +14,8 @@
   "r": 64,
   "revision": null,
   "target_modules": [
-    "c_attn"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9e4438bab6f631c6b37b13598144e78334f0646a382aef37bc083342601040
-size 9446006
+oid sha256:905f9bcc99c6c914a97007d7185aa46e51b6b913d6949c9a9ad57a402395ebaf
+size 109098378

added_tokens.json

@@ -1,3 +1,5 @@
 {
-  "<|endoftext|>": 50256
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
 }

special_tokens_map.json

@@ -1,6 +1,11 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.model

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

tokenizer_config.json

@@ -1,8 +1,23 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,11 +25,20 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13de623cfacfc064ec689d869cdbbfd81a59d20b7bc69949322906a809624d6e
+oid sha256:40b29c70b2fdffcd5dd5fcb5cca0f37c223fb17c87ef40c7e46f7a3eb09d0a4d
 size 4536