Training in progress, step 1500

adapter_config.json

@@ -22,13 +22,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "v_proj",
-    "up_proj",
-    "gate_proj",
     "down_proj",
-    "k_proj"
+    "k_proj",
+    "up_proj",
+    "lm_head",
+    "o_proj",
+    "q_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6245617412dc43ea81131dc52245aec1884d049b4667ab177a444c2ef317beee
-size 2460946960
+oid sha256:994b715e3e3aecec9695f60cbdd1ba7f6ba3abf0bede77add39d740f9991ed2c
+size 1444314856

special_tokens_map.json

@@ -1,19 +1,7 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "[SQL]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "[/SQL]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "[SQL]",
+    "[/SQL]"
   ],
   "bos_token": {
     "content": "<|endoftext|>",

tokenizer.json

@@ -499,7 +499,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
-    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

tokenizer_config.json

@@ -404,8 +404,12 @@
   "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 4096,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1247e38f19114d0f10ca81ca5420a0a5ac694e2b7fe90f563f640541064309a
-size 5112
+oid sha256:197267dd45789e99dbf88be971b2223190d42503cdd003a15db8e3f7996a29d5
+size 4984