Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: stabilityai/stablelm-3b-4e1t
+base_model: mistralai/Mistral-7B-v0.1
 ---
 
 # Model Card for Model ID

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "down_proj",
     "up_proj",
-    "down_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34971e310337415b7f227f380b3576b3161815c99a12f174132a7dd57b885e3e
-size 58221088
+oid sha256:462da6b1dacec1acdde5d63ab626a28225936bab7d9c87b93cd08f076623b652
+size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44030903c0ad03d92218ac628bda5032e2353a3cd2922f4d62514bec700ac13b
-size 116508154
+oid sha256:d7e0a7cd7e3e5186cb2c3598458545087a5cc9c0c97aae42ac53aa6b237e0ae6
+size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70553799efce26ec5b73a5df5d7b9bd22b63a05aaa58944a4204ed64ea249fad
+oid sha256:e223434d2640d399673ae6c1909d730176bd2783c0124f8ea83ce13965cd95a8
 size 14244

special_tokens_map.json

@@ -1,37 +1,21 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": {
-    "content": "<|endoftext|>",
+    "content": "<s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": "</s>",
   "unk_token": {
-    "content": "<|endoftext|>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,8 +1,9 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<|endoftext|>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,207 +11,15 @@
       "special": true
     },
     "1": {
-      "content": "<|padding|>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50254": {
-      "content": "                        ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50255": {
-      "content": "                       ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50256": {
-      "content": "                      ",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "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": "        ",
-      "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": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50278": {
-      "content": "<|im_start|>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -218,15 +27,16 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<|im_end|>",
-    "<|im_start|>"
-  ],
-  "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "GPTNeoXTokenizer",
-  "unk_token": "<|endoftext|>"
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.8763,
+      "loss": 1.7128,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 2.2545,
+      "loss": 1.8515,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 2.31,
+      "loss": 1.8735,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 2.394,
+      "loss": 2.0181,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 2.664,
+      "loss": 2.1375,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 3.2972,
+      "loss": 2.3034,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.9397,
+      "loss": 1.6288,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.94,
+      "loss": 1.5506,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 2.2578,
+      "loss": 1.8434,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 2.2072,
+      "loss": 1.6927,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 2.521,
+      "loss": 1.9721,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 2.9765,
+      "loss": 1.9983,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.8495,
+      "loss": 1.5436,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 2.1343,
+      "loss": 1.7244,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 2.3914,
+      "loss": 1.8803,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 2.1701,
+      "loss": 1.7137,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 2.2561,
+      "loss": 1.7194,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 2.8575,
+      "loss": 1.8995,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.8819,
+      "loss": 1.5938,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 2.1998,
+      "loss": 1.7493,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 2.3208,
+      "loss": 1.8429,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 2.3829,
+      "loss": 1.8747,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 2.2179,
+      "loss": 1.7454,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 2.7775,
+      "loss": 1.7541,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 6759056164313088.0,
+  "total_flos": 1.6885823916957696e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98bba17031f248cade791f27c9fb624e489376ca991d51785e12dfad5ada2c2
+oid sha256:34cbce6bccba8280ee82dc757f6360bcde7994e7543d19b82190f9cc8a5487be
 size 4728