Training in progress, epoch 1

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-2-70b-chat-hf",
+  "base_model_name_or_path": "codellama/CodeLlama-7b-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,14 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "gate_proj",
-    "k_proj",
-    "down_proj",
     "q_proj",
+    "gate_proj",
+    "up_proj",
     "v_proj",
-    "o_proj"
+    "o_proj",
+    "down_proj",
+    "k_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 sha256:7792242ad6910a3fe13188098a0853647a383d646ab538d1f420b57220b8a144
-size 7675798384
+oid sha256:07a893ac183c68eb13b07e8b5ae88538e555554e96b59a93c4da8575b7bc4f77
+size 1803907984

runs/Sep16_04-58-39_8PYKQ04/events.out.tfevents.1726462726.8PYKQ04.4374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa52afdab18e66d68cf899a46938dd5a0d6ba41c774dc63c1a42be276594098
+size 9214

special_tokens_map.json

@@ -1,14 +1,14 @@
 {
   "additional_special_tokens": [
     {
-      "content": "<|im_end|>",
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false
     },
     {
-      "content": "<|im_start|>",
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

tokenizer.json

@@ -31,8 +31,26 @@
       "special": true
     },
     {
-      "id": 32000,
-      "content": "<|im_end|>",
+      "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,
@@ -40,13 +58,31 @@
       "special": true
     },
     {
-      "id": 32001,
+      "id": 32010,
+      "content": "▁<EOT>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 32016,
       "content": "<|im_start|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 32017,
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {
@@ -152,6 +188,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,
@@ -32152,7 +32189,23 @@
       "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 +93456,18 @@
       "▁▁▁▁▁▁▁▁▁ ▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁ ▁▁▁▁▁▁▁▁",
       "▁▁▁▁▁▁▁▁▁▁▁ ▁▁▁▁",
-      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁"
+      "▁ ▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "▁< SU",
+      "▁<SU F",
+      "▁< PRE",
+      "▁< M",
+      "▁<M ID",
+      "▁< E",
+      "▁<E OT",
+      "▁<PRE >",
+      "▁<SUF >",
+      "▁<MID >",
+      "▁<EOT >"
     ]
   }
 }

tokenizer_config.json

@@ -26,37 +26,73 @@
       "single_word": false,
       "special": true
     },
-    "32000": {
-      "content": "<|im_end|>",
+    "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
     },
-    "32001": {
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32017": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
-    "<|im_end|>",
-    "<|im_start|>"
+    "<|im_start|>",
+    "<|im_end|>"
   ],
   "bos_token": "<|im_start|>",
   "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:fc46b03d6ce07cc11851cace10a01050c91e0e15a9614e93960b87d32a361063
-size 4728
+oid sha256:0b28848c5969bf7d9f57b05e7b1ca571441f8d8d211f3ed305ccb3d8e71a791a
+size 5048