Training in progress, epoch 0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,14 +19,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "k_proj",
-    "o_proj",
     "v_proj",
+    "up_proj",
     "gate_proj",
+    "o_proj",
+    "k_proj",
     "down_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",
+  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2fa7a1d1a9c2bc8d01475780e0d63dbb0a6300943e302f8ea730aea9798b51
-size 1803645840
+oid sha256:082197c836547caaee7f8b0acd23b88aac55c953c58d2f8446293f5626b2fd1a
+size 1803907984

runs/Mar01_22-45-59_00282ec317e5/events.out.tfevents.1709333168.00282ec317e5.1271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40fa310692b62f039dcab425d6646a61c62f9a9de906f3543cac8067a4ad03db
+size 5688

tokenizer.json

@@ -31,7 +31,43 @@
       "special": true
     },
     {
-      "id": 32000,
+      "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
+    },
+    {
+      "id": 32016,
       "content": "<|im_end|>",
       "single_word": false,
       "lstrip": false,
@@ -40,7 +76,7 @@
       "special": true
     },
     {
-      "id": 32001,
+      "id": 32017,
       "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
@@ -32152,7 +32188,23 @@
       "왕": 31996,
       "收": 31997,
       "弘": 31998,
-      "给": 31999
+      "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
     },
     "merges": [
       "▁ t",
@@ -93403,7 +93455,18 @@
       "▁▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁▁▁▁▁ ▁▁▁▁",
-      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "▁< SU",
+      "▁<SU F",
+      "▁< PRE",
+      "▁< M",
+      "▁<M ID",
+      "▁< E",
+      "▁<E OT",
+      "▁<PRE >",
+      "▁<SUF >",
+      "▁<MID >",
+      "▁<EOT >"
     ]
   }
 }

tokenizer_config.json

@@ -26,7 +26,39 @@
       "single_word": false,
       "special": true
     },
-    "32000": {
+    "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
+    },
+    "32016": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -34,7 +66,7 @@
       "single_word": false,
       "special": true
     },
-    "32001": {
+    "32017": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -51,12 +83,16 @@
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
-  "legacy": false,
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|im_end|>",
-  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fa1ba59014e4e8e028b8a46ef609bc1bb6f80342b5f1442a0c383b971d6b067
+oid sha256:5b97ba3e0eb8fec02715c13b56f6c885a80d87983ccfc753e0bd8535de2c9c12
 size 4728