Training in progress, step 9500

adapter_config.json

@@ -22,13 +22,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
+    "q_proj",
     "o_proj",
-    "v_proj",
-    "k_proj",
     "gate_proj",
-    "q_proj"
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "up_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:de6d2e9efbcba2d0070d50a726b5421c74f777257623b333867185d54de251a6
+oid sha256:b2fd4f2ca2d228c9aa0287573cdb4c0b4cac6aa158f3379c9bdabe47bd2360de
 size 2460946960

special_tokens_map.json

@@ -1,8 +1,4 @@
 {
-  "additional_special_tokens": [
-    "[SQL]",
-    "[/SQL]"
-  ],
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -437,8 +437,8 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     },
     {
       "id": 50300,
@@ -446,8 +446,8 @@
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
-      "normalized": false,
-      "special": true
+      "normalized": true,
+      "special": false
     }
   ],
   "normalizer": {
@@ -460,30 +460,10 @@
     "use_regex": true
   },
   "post_processor": {
-    "type": "TemplateProcessing",
-    "single": [
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      }
-    ],
-    "pair": [
-      {
-        "Sequence": {
-          "id": "A",
-          "type_id": 0
-        }
-      },
-      {
-        "Sequence": {
-          "id": "B",
-          "type_id": 1
-        }
-      }
-    ],
-    "special_tokens": {}
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
   },
   "decoder": {
     "type": "ByteLevel",

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
@@ -382,34 +380,26 @@
     "50299": {
       "content": "[SQL]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
     "50300": {
       "content": "[/SQL]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     }
   },
-  "additional_special_tokens": [
-    "[SQL]",
-    "[/SQL]"
-  ],
   "bos_token": "<|endoftext|>",
   "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 sha256:90541c3584b21931f20b7d44745efd12253bc6c59be244f5e3a02e61ee3dd381
+oid sha256:8415041ca672e470b777a760ebcf14fbca29ab93475dc4bd62233bcbf2ca1246
 size 4984