starlineventures/chatgpt

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: microsoft/phi-2
+base_model: microsoft/Phi-3.5-mini-instruct
 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-2](https://huggingface.co/microsoft/phi-2) on an unknown dataset.
+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.
 
 ## Model description
 

adapter_config.json

@@ -1,10 +1,10 @@
 {
   "alpha_pattern": {},
   "auto_mapping": {
-    "base_model_class": "PhiForCausalLM",
-    "parent_library": "transformers.models.phi.modeling_phi"
+    "base_model_class": "Phi3ForCausalLM",
+    "parent_library": "transformers_modules.microsoft.Phi-3.5-mini-instruct.3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca.modeling_phi3"
   },
-  "base_model_name_or_path": "microsoft/phi-2",
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
     "k_proj",
-    "down_proj",
     "up_proj",
+    "q_proj",
     "o_proj",
-    "v_proj"
+    "v_proj",
+    "gate_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 sha256:537817d8a957663d34acfd9678d3fcdb85a1092df7428631b9b5efebce235b80
-size 94422368
+oid sha256:fff7b051d12ef77bb0c869afde32d845678781cf3b5494203b66572011f998b2
+size 35668592

added_tokens.json

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

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.4417308241713281,
-    "train_runtime": 112.6516,
-    "train_samples_per_second": 5.406,
-    "train_steps_per_second": 1.811
+    "train_loss": 0.4158199636959562,
+    "train_runtime": 99.4711,
+    "train_samples_per_second": 6.122,
+    "train_steps_per_second": 2.051
 }

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,327 +1,132 @@
 {
   "add_bos_token": false,
-  "add_prefix_space": false,
+  "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
-    "50256": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50257": {
-      "content": "                               ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50258": {
-      "content": "                              ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50259": {
-      "content": "                             ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50260": {
-      "content": "                            ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50261": {
-      "content": "                           ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50262": {
-      "content": "                          ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50263": {
-      "content": "                         ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50264": {
-      "content": "                        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50265": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50266": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50267": {
-      "content": "                     ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50268": {
-      "content": "                    ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50269": {
-      "content": "                   ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50270": {
-      "content": "                  ",
+    "1": {
+      "content": "<s>",
       "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,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50283": {
-      "content": "     ",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
       "special": false
     },
-    "50284": {
-      "content": "    ",
+    "32000": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50285": {
-      "content": "   ",
+    "32001": {
+      "content": "<|assistant|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50286": {
-      "content": "  ",
+    "32002": {
+      "content": "<|placeholder1|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50287": {
-      "content": "\t\t\t\t\t\t\t\t\t",
+    "32003": {
+      "content": "<|placeholder2|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50288": {
-      "content": "\t\t\t\t\t\t\t\t",
+    "32004": {
+      "content": "<|placeholder3|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50289": {
-      "content": "\t\t\t\t\t\t\t",
+    "32005": {
+      "content": "<|placeholder4|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50290": {
-      "content": "\t\t\t\t\t\t",
+    "32006": {
+      "content": "<|system|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50291": {
-      "content": "\t\t\t\t\t",
+    "32007": {
+      "content": "<|end|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50292": {
-      "content": "\t\t\t\t",
+    "32008": {
+      "content": "<|placeholder5|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50293": {
-      "content": "\t\t\t",
+    "32009": {
+      "content": "<|placeholder6|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     },
-    "50294": {
-      "content": "\t\t",
+    "32010": {
+      "content": "<|user|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
+      "normalized": false,
+      "rstrip": true,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "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,
   "eos_token": "<|endoftext|>",
-  "errors": "replace",
+  "legacy": false,
   "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
-  "return_token_type_ids": false,
-  "tokenizer_class": "CodeGenTokenizer",
-  "unk_token": "<|endoftext|>"
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "total_flos": 0.0,
-    "train_loss": 0.4417308241713281,
-    "train_runtime": 112.6516,
-    "train_samples_per_second": 5.406,
-    "train_steps_per_second": 1.811
+    "train_loss": 0.4158199636959562,
+    "train_runtime": 99.4711,
+    "train_samples_per_second": 6.122,
+    "train_steps_per_second": 2.051
 }

trainer_state.json

@@ -10,152 +10,152 @@
   "log_history": [
     {
       "epoch": 0.14705882352941177,
-      "grad_norm": 5.014659881591797,
+      "grad_norm": 1.1240489482879639,
       "learning_rate": 9.509803921568627e-05,
-      "loss": 0.8047,
+      "loss": 3.006,
       "step": 10
     },
     {
       "epoch": 0.29411764705882354,
-      "grad_norm": 3.9647512435913086,
+      "grad_norm": 0.9972021579742432,
       "learning_rate": 9.019607843137255e-05,
-      "loss": 0.572,
+      "loss": 0.3771,
       "step": 20
     },
     {
       "epoch": 0.4411764705882353,
-      "grad_norm": 3.050414800643921,
+      "grad_norm": 1.274720549583435,
       "learning_rate": 8.529411764705883e-05,
-      "loss": 0.5933,
+      "loss": 0.4497,
       "step": 30
     },
     {
       "epoch": 0.5882352941176471,
-      "grad_norm": 1.585654377937317,
+      "grad_norm": 0.8991940021514893,
       "learning_rate": 8.039215686274511e-05,
-      "loss": 0.4563,
+      "loss": 0.3536,
       "step": 40
     },
     {
       "epoch": 0.7352941176470589,
-      "grad_norm": 1.262968897819519,
+      "grad_norm": 0.9119272828102112,
       "learning_rate": 7.549019607843137e-05,
-      "loss": 0.4342,
+      "loss": 0.3353,
       "step": 50
     },
     {
       "epoch": 0.8823529411764706,
-      "grad_norm": 0.7713326215744019,
+      "grad_norm": 0.6662648320198059,
       "learning_rate": 7.058823529411765e-05,
-      "loss": 0.4967,
+      "loss": 0.4034,
       "step": 60
     },
     {
       "epoch": 1.0294117647058822,
-      "grad_norm": 1.4584881067276,
+      "grad_norm": 0.7458919882774353,
       "learning_rate": 6.568627450980392e-05,
-      "loss": 0.5211,
+      "loss": 0.4318,
       "step": 70
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 2.0033822059631348,
+      "grad_norm": 0.937239944934845,
       "learning_rate": 6.078431372549019e-05,
-      "loss": 0.3788,
+      "loss": 0.2594,
       "step": 80
     },
     {
       "epoch": 1.3235294117647058,
-      "grad_norm": 2.14152455329895,
+      "grad_norm": 0.8029321432113647,
       "learning_rate": 5.588235294117647e-05,
-      "loss": 0.4405,
+      "loss": 0.2861,
       "step": 90
     },
     {
       "epoch": 1.4705882352941178,
-      "grad_norm": 2.8985249996185303,
+      "grad_norm": 0.7472988367080688,
       "learning_rate": 5.0980392156862745e-05,
-      "loss": 0.3855,
+      "loss": 0.2578,
       "step": 100
     },
     {
       "epoch": 1.6176470588235294,
-      "grad_norm": 2.2722222805023193,
+      "grad_norm": 0.6276091933250427,
       "learning_rate": 4.607843137254902e-05,
-      "loss": 0.3668,
+      "loss": 0.2554,
       "step": 110
     },
     {
       "epoch": 1.7647058823529411,
-      "grad_norm": 1.7401117086410522,
+      "grad_norm": 0.551144540309906,
       "learning_rate": 4.11764705882353e-05,
-      "loss": 0.4555,
+      "loss": 0.3111,
       "step": 120
     },
     {
       "epoch": 1.9117647058823528,
-      "grad_norm": 2.3890228271484375,
+      "grad_norm": 1.0049179792404175,
       "learning_rate": 3.627450980392157e-05,
-      "loss": 0.4121,
+      "loss": 0.2822,
       "step": 130
     },
     {
       "epoch": 2.0588235294117645,
-      "grad_norm": 2.051992654800415,
+      "grad_norm": 0.6848428845405579,
       "learning_rate": 3.137254901960784e-05,
-      "loss": 0.3758,
+      "loss": 0.2257,
       "step": 140
     },
     {
       "epoch": 2.2058823529411766,
-      "grad_norm": 2.088096857070923,
+      "grad_norm": 0.7736006379127502,
       "learning_rate": 2.647058823529412e-05,
-      "loss": 0.3738,
+      "loss": 0.2035,
       "step": 150
     },
     {
       "epoch": 2.3529411764705883,
-      "grad_norm": 1.384030818939209,
+      "grad_norm": 0.640957236289978,
       "learning_rate": 2.1568627450980395e-05,
-      "loss": 0.393,
+      "loss": 0.2181,
       "step": 160
     },
     {
       "epoch": 2.5,
-      "grad_norm": 1.6448745727539062,
+      "grad_norm": 1.5639573335647583,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.2952,
+      "loss": 0.1645,
       "step": 170
     },
     {
       "epoch": 2.6470588235294117,
-      "grad_norm": 1.227141261100769,
+      "grad_norm": 0.870328962802887,
       "learning_rate": 1.1764705882352942e-05,
-      "loss": 0.3821,
+      "loss": 0.1894,
       "step": 180
     },
     {
       "epoch": 2.7941176470588234,
-      "grad_norm": 2.20298433303833,
+      "grad_norm": 1.0381242036819458,
       "learning_rate": 6.862745098039216e-06,
-      "loss": 0.3722,
+      "loss": 0.2089,
       "step": 190
     },
     {
       "epoch": 2.9411764705882355,
-      "grad_norm": 1.9124171733856201,
+      "grad_norm": 1.1926450729370117,
       "learning_rate": 1.96078431372549e-06,
-      "loss": 0.36,
+      "loss": 0.1855,
       "step": 200
     },
     {
       "epoch": 3.0,
       "step": 204,
       "total_flos": 0.0,
-      "train_loss": 0.4417308241713281,
-      "train_runtime": 112.6516,
-      "train_samples_per_second": 5.406,
-      "train_steps_per_second": 1.811
+      "train_loss": 0.4158199636959562,
+      "train_runtime": 99.4711,
+      "train_samples_per_second": 6.122,
+      "train_steps_per_second": 2.051
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4e8f2d3250958257fd416d205e9505bf49a86acfd66fa7e8bdd8b8358c882d
+oid sha256:2952133924800416bdb80493b0f16baf261b3a81b8d0a0bcd5bfedc4aed9112f
 size 5432