Training in progress, step 25

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "defog/sqlcoder-7b-2",
+  "base_model_name_or_path": "meta-llama/Llama-2-13b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,7 +9,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 64,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
     "k_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f567278abac0a182c45835aeeebcf74ff1ae9af34c0dbacb7ab3fe490aa5b1e
-size 536906096
+oid sha256:335ff3ab02635313a29bd60a29e36f5945243b709320d83cfa5ece896a4ce0b6
+size 838904832

special_tokens_map.json

@@ -1,14 +1,4 @@
 {
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>",
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer.json

@@ -34,42 +34,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32007,
-      "content": "▁<PRE>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32008,
-      "content": "▁<SUF>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32009,
-      "content": "▁<MID>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32010,
-      "content": "▁<EOT>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {
@@ -32175,23 +32139,7 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "给": 31999,
-      "▁<SU": 32000,
-      "▁<SUF": 32001,
-      "▁<PRE": 32002,
-      "▁<M": 32003,
-      "▁<MID": 32004,
-      "▁<E": 32005,
-      "▁<EOT": 32006,
-      "▁<PRE>": 32007,
-      "▁<SUF>": 32008,
-      "▁<MID>": 32009,
-      "▁<EOT>": 32010,
-      "▁<EOT><EOT>": 32011,
-      "▁<EOT><EOT><EOT>": 32012,
-      "▁<EOT><EOT><EOT><EOT>": 32013,
-      "▁<EOT><EOT><EOT><EOT><EOT>": 32014,
-      "▁<EOT><EOT><EOT><EOT><EOT><EOT>": 32015
+      "给": 31999
     },
     "merges": [
       "▁ t",
@@ -93442,18 +93390,7 @@
       "▁▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁▁▁▁▁ ▁▁▁▁",
-      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
-      "▁< SU",
-      "▁<SU F",
-      "▁< PRE",
-      "▁< M",
-      "▁<M ID",
-      "▁< E",
-      "▁<E OT",
-      "▁<PRE >",
-      "▁<SUF >",
-      "▁<MID >",
-      "▁<EOT >"
+      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
     ]
   }
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
-size 500058
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -25,63 +25,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32007": {
-      "content": "▁<PRE>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "▁<SUF>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "▁<MID>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "▁<EOT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>",
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
-  "prefix_token": "▁<PRE>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "CodeLlamaTokenizer",
+  "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 sha256:6bd37a7bed4b29db3131947c878454b234a832069e5051a4e513a682b0b6b1f6
+oid sha256:229196146870c6d4028c2c7478b67450b5d84079445d42ab8c78010679048a83
 size 4856