starlineventures/chatgpt

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: microsoft/Phi-3.5-mini-instruct
+base_model: microsoft/phi-2
 library_name: peft
 license: mit
 tags:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
 
 ## Model description
 

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "Phi3ForCausalLM",
-    "parent_library": "transformers_modules.microsoft.Phi-3.5-mini-instruct.3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca.modeling_phi3"
+    "base_model_class": "PhiForCausalLM",
+    "parent_library": "transformers.models.phi.modeling_phi"
   },
-  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "base_model_name_or_path": "microsoft/phi-2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "o_proj",
-    "q_proj",
+    "up_proj",
     "v_proj",
     "k_proj",
     "gate_proj",
-    "up_proj"
+    "q_proj",
+    "down_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ecc4ebb035abab1d5b06ebbb895750d78a6b579cadc196c3312310b4fc1bb3
-size 35668592
+oid sha256:073c24e6f5e00a1b88481cdfd1ea77dcab74b65cafb5fd6a7c44eac81a3910d5
+size 94422368

added_tokens.json

@@ -1,13 +1,40 @@
 {
-  "<|assistant|>": 32001,
-  "<|endoftext|>": 32000,
-  "<|end|>": 32007,
-  "<|placeholder1|>": 32002,
-  "<|placeholder2|>": 32003,
-  "<|placeholder3|>": 32004,
-  "<|placeholder4|>": 32005,
-  "<|placeholder5|>": 32008,
-  "<|placeholder6|>": 32009,
-  "<|system|>": 32006,
-  "<|user|>": 32010
+  "\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
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.41664891704624774,
-    "train_runtime": 99.7082,
-    "train_samples_per_second": 6.108,
-    "train_steps_per_second": 2.046
+    "train_loss": 0.4677507205336702,
+    "train_runtime": 113.1172,
+    "train_samples_per_second": 5.384,
+    "train_steps_per_second": 1.803
 }

special_tokens_map.json

@@ -1,6 +1,6 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -15,7 +15,7 @@
   },
   "pad_token": "<|endoftext|>",
   "unk_token": {
-    "content": "<unk>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,132 +1,327 @@
 {
   "add_bos_token": false,
-  "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "50256": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "50257": {
+      "content": "                               ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "2": {
-      "content": "</s>",
+    "50258": {
+      "content": "                              ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
       "special": false
     },
-    "32000": {
-      "content": "<|endoftext|>",
+    "50259": {
+      "content": "                             ",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32001": {
-      "content": "<|assistant|>",
+    "50260": {
+      "content": "                            ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32002": {
-      "content": "<|placeholder1|>",
+    "50261": {
+      "content": "                           ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32003": {
-      "content": "<|placeholder2|>",
+    "50262": {
+      "content": "                          ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32004": {
-      "content": "<|placeholder3|>",
+    "50263": {
+      "content": "                         ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32005": {
-      "content": "<|placeholder4|>",
+    "50264": {
+      "content": "                        ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32006": {
-      "content": "<|system|>",
+    "50265": {
+      "content": "                       ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32007": {
-      "content": "<|end|>",
+    "50266": {
+      "content": "                      ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32008": {
-      "content": "<|placeholder5|>",
+    "50267": {
+      "content": "                     ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32009": {
-      "content": "<|placeholder6|>",
+    "50268": {
+      "content": "                    ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "32010": {
-      "content": "<|user|>",
+    "50269": {
+      "content": "                   ",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": true,
+      "normalized": true,
+      "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "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
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "legacy": false,
+  "errors": "replace",
   "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.41664891704624774,
-    "train_runtime": 99.7082,
-    "train_samples_per_second": 6.108,
-    "train_steps_per_second": 2.046
+    "train_loss": 0.4677507205336702,
+    "train_runtime": 113.1172,
+    "train_samples_per_second": 5.384,
+    "train_steps_per_second": 1.803
 }

trainer_state.json

@@ -10,152 +10,152 @@
   "log_history": [
     {
       "epoch": 0.14705882352941177,
-      "grad_norm": 1.1769816875457764,
+      "grad_norm": 6.151556968688965,
       "learning_rate": 9.509803921568627e-05,
-      "loss": 3.0083,
+      "loss": 0.8078,
       "step": 10
     },
     {
       "epoch": 0.29411764705882354,
-      "grad_norm": 0.9931313395500183,
+      "grad_norm": 5.537124156951904,
       "learning_rate": 9.019607843137255e-05,
-      "loss": 0.3765,
+      "loss": 0.5717,
       "step": 20
     },
     {
       "epoch": 0.4411764705882353,
-      "grad_norm": 1.2492034435272217,
+      "grad_norm": 4.549717426300049,
       "learning_rate": 8.529411764705883e-05,
-      "loss": 0.45,
+      "loss": 0.6521,
       "step": 30
     },
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 0.9271335005760193,
+      "grad_norm": 2.5774660110473633,
       "learning_rate": 8.039215686274511e-05,
-      "loss": 0.354,
+      "loss": 0.4809,
       "step": 40
     },
     {
       "epoch": 0.7352941176470589,
-      "grad_norm": 0.9514768719673157,
+      "grad_norm": 2.7017040252685547,
       "learning_rate": 7.549019607843137e-05,
-      "loss": 0.3358,
+      "loss": 0.4491,
       "step": 50
     },
     {
       "epoch": 0.8823529411764706,
-      "grad_norm": 0.6885753870010376,
+      "grad_norm": 1.613568902015686,
       "learning_rate": 7.058823529411765e-05,
-      "loss": 0.403,
+      "loss": 0.5115,
       "step": 60
     },
     {
       "epoch": 1.0294117647058822,
-      "grad_norm": 0.7592061161994934,
+      "grad_norm": 2.709432601928711,
       "learning_rate": 6.568627450980392e-05,
-      "loss": 0.431,
+      "loss": 0.55,
       "step": 70
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 0.9498554468154907,
+      "grad_norm": 3.952850818634033,
       "learning_rate": 6.078431372549019e-05,
-      "loss": 0.2607,
+      "loss": 0.4256,
       "step": 80
     },
     {
       "epoch": 1.3235294117647058,
-      "grad_norm": 0.8069510459899902,
+      "grad_norm": 2.875826358795166,
       "learning_rate": 5.588235294117647e-05,
-      "loss": 0.2868,
+      "loss": 0.4734,
       "step": 90
     },
     {
       "epoch": 1.4705882352941178,
-      "grad_norm": 0.7954164147377014,
+      "grad_norm": 2.6799256801605225,
       "learning_rate": 5.0980392156862745e-05,
-      "loss": 0.2608,
+      "loss": 0.4256,
       "step": 100
     },
     {
       "epoch": 1.6176470588235294,
-      "grad_norm": 0.6208708882331848,
+      "grad_norm": 1.358408808708191,
       "learning_rate": 4.607843137254902e-05,
-      "loss": 0.2575,
+      "loss": 0.4089,
       "step": 110
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 0.5807853937149048,
+      "grad_norm": 1.366873025894165,
       "learning_rate": 4.11764705882353e-05,
-      "loss": 0.3115,
+      "loss": 0.4921,
       "step": 120
     },
     {
       "epoch": 1.9117647058823528,
-      "grad_norm": 0.9814097881317139,
+      "grad_norm": 3.361318588256836,
       "learning_rate": 3.627450980392157e-05,
-      "loss": 0.2838,
+      "loss": 0.4334,
       "step": 130
     },
     {
       "epoch": 2.0588235294117645,
-      "grad_norm": 0.7195965051651001,
+      "grad_norm": 1.263223648071289,
       "learning_rate": 3.137254901960784e-05,
-      "loss": 0.2277,
+      "loss": 0.3971,
       "step": 140
     },
     {
       "epoch": 2.2058823529411766,
-      "grad_norm": 0.7863514423370361,
+      "grad_norm": 1.3559168577194214,
       "learning_rate": 2.647058823529412e-05,
-      "loss": 0.1986,
+      "loss": 0.3945,
       "step": 150
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 0.6758102178573608,
+      "grad_norm": 1.3529400825500488,
       "learning_rate": 2.1568627450980395e-05,
-      "loss": 0.2185,
+      "loss": 0.4233,
       "step": 160
     },
     {
       "epoch": 2.5,
-      "grad_norm": 1.3710891008377075,
+      "grad_norm": 1.8559266328811646,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.1649,
+      "loss": 0.3216,
       "step": 170
     },
     {
       "epoch": 2.6470588235294117,
-      "grad_norm": 0.8887768387794495,
+      "grad_norm": 1.4294967651367188,
       "learning_rate": 1.1764705882352942e-05,
-      "loss": 0.1913,
+      "loss": 0.4001,
       "step": 180
     },
     {
       "epoch": 2.7941176470588234,
-      "grad_norm": 1.0456489324569702,
+      "grad_norm": 1.6639864444732666,
       "learning_rate": 6.862745098039216e-06,
-      "loss": 0.2106,
+      "loss": 0.3968,
       "step": 190
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.153358817100525,
+      "grad_norm": 1.9823282957077026,
       "learning_rate": 1.96078431372549e-06,
-      "loss": 0.188,
+      "loss": 0.3785,
       "step": 200
     },
     {
       "epoch": 3.0,
       "step": 204,
       "total_flos": 0.0,
-      "train_loss": 0.41664891704624774,
-      "train_runtime": 99.7082,
-      "train_samples_per_second": 6.108,
-      "train_steps_per_second": 2.046
+      "train_loss": 0.4677507205336702,
+      "train_runtime": 113.1172,
+      "train_samples_per_second": 5.384,
+      "train_steps_per_second": 1.803
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1daa919d0ce200e377fefdad454b4385952ae4a5fdfc46d20940a70fdf517c8b
+oid sha256:4f3ded48d9febf2f6f7ca41ec8be465c369d7768ebc7cf6b7b294f7132b117a7
 size 5432