Training in progress, step 100

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "CodeGPTPlus/deepseek-coder-1.3b-typescript",
+  "base_model_name_or_path": "microsoft/phi-2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -24,7 +24,9 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "v_proj"
+    "v_proj",
+    "fc2",
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49326e9a42a2a7c08949b2569b1ad91735ffb4b3d543830abdb3547d7b3a89d2
-size 6304096
+oid sha256:63e3ae28670ba0d5849b06ee0792ec99fbe555e40736f67e07cd29ab660256e5
+size 36733184

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

runs/Feb19_20-51-04_nitro/events.out.tfevents.1740016266.nitro.3887.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da139c1a988fc4b5135b4fe3fa0f59302b687529581636772cc24823e6f235d2
+size 5912

runs/Feb19_21-06-19_nitro/events.out.tfevents.1740017185.nitro.5788.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fa1baace39814f27c5690348deb3cb14e98e01b30eb73b6c807a3e13241781
+size 5905

runs/Feb19_21-06-19_nitro/events.out.tfevents.1740017244.nitro.5788.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5459dc54950178a2754ae6ddf9942c68db166a2d41b76ba79c705ba0dd3d9b
+size 5905

runs/Feb19_21-13-25_nitro/events.out.tfevents.1740017607.nitro.6874.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:361acf9fdc5e0367ce644f2993b3dc5dacc8ce67110c0763894f170fe4417df3
+size 6733

special_tokens_map.json

@@ -1,20 +1,21 @@
 {
   "bos_token": {
-    "content": "<｜begin▁of▁sentence｜>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<｜end▁of▁sentence｜>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<｜end▁of▁sentence｜>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,178 +1,312 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "32000": {
-      "content": "õ",
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32001": {
-      "content": "÷",
+    "50258": {
+      "content": "                              ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32002": {
-      "content": "Á",
+    "50259": {
+      "content": "                             ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32003": {
-      "content": "ý",
+    "50260": {
+      "content": "                            ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32004": {
-      "content": "À",
+    "50261": {
+      "content": "                           ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32005": {
-      "content": "ÿ",
+    "50262": {
+      "content": "                          ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32006": {
-      "content": "ø",
+    "50263": {
+      "content": "                         ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32007": {
-      "content": "ú",
+    "50264": {
+      "content": "                        ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32008": {
-      "content": "þ",
+    "50265": {
+      "content": "                       ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32009": {
-      "content": "ü",
+    "50266": {
+      "content": "                      ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32010": {
-      "content": "ù",
+    "50267": {
+      "content": "                     ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32011": {
-      "content": "ö",
+    "50268": {
+      "content": "                    ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32012": {
-      "content": "û",
+    "50269": {
+      "content": "                   ",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32013": {
-      "content": "<｜begin▁of▁sentence｜>",
+    "50270": {
+      "content": "                  ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32014": {
-      "content": "<｜end▁of▁sentence｜>",
+    "50271": {
+      "content": "                 ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     },
-    "32015": {
-      "content": "<｜fim▁hole｜>",
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32016": {
-      "content": "<｜fim▁begin｜>",
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32017": {
-      "content": "<｜fim▁end｜>",
+    "50290": {
+      "content": "\t\t\t\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32018": {
-      "content": "<pad>",
+    "50291": {
+      "content": "\t\t\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32019": {
-      "content": "<|User|>",
+    "50292": {
+      "content": "\t\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32020": {
-      "content": "<|Assistant|>",
+    "50293": {
+      "content": "\t\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32021": {
-      "content": "<|EOT|>",
+    "50294": {
+      "content": "\t\t",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
@@ -180,15 +314,13 @@
       "special": false
     }
   },
-  "bos_token": "<｜begin▁of▁sentence｜>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<｜end▁of▁sentence｜>",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
-  "legacy": true,
-  "model_max_length": 16384,
-  "pad_token": "<｜end▁of▁sentence｜>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": null,
-  "use_default_system_prompt": false
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4050ad25eb9af7002dbdb07b020204b2560c1ef6e5c703c89cf6a6873ea954
+oid sha256:650d09b915dda5ba3db641c52a12ce5be71d826688ccb7a9a667d9d827d2dea0
 size 5560