Upload folder using huggingface_hub

README.md

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

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Deci/DeciLM-7B",
+  "base_model_name_or_path": "stabilityai/stablelm-3b-4e1t",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6340c6c21b5a2555d42ebd094af6dcbb30003201bf607ea3b4adc9d3ad4f77
-size 113271504
+oid sha256:34971e310337415b7f227f380b3576b3161815c99a12f174132a7dd57b885e3e
+size 58221088

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fc782651d7d4e153c7b3fc44ecb67c9b5bd2d26d8f36da68c08c212696a1dd9
-size 226609018
+oid sha256:44030903c0ad03d92218ac628bda5032e2353a3cd2922f4d62514bec700ac13b
+size 116508154

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc28ac068ae9c17cfe666f59e9991687067bf7efa8f8c46d52a54671ec543b7e
+oid sha256:70553799efce26ec5b73a5df5d7b9bd22b63a05aaa58944a4204ed64ea249fad
 size 14244

special_tokens_map.json

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

tokenizer_config.json

@@ -1,9 +1,8 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<unk>",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -11,15 +10,207 @@
       "special": true
     },
     "1": {
-      "content": "<s>",
+      "content": "<|padding|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "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|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -27,17 +218,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '### User:\n' + message['content'] }}\n{% elif message['role'] == 'system' %}\n{{ '### System:\n' + message['content'] }}\n{% elif message['role'] == 'assistant' %}\n{{ '### Assistant:\n'  + message['content'] }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '### Assistant:' }}\n{% endif %}\n{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
+  "additional_special_tokens": [
+    "<|im_end|>",
+    "<|im_start|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
 }

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.6155,
+      "loss": 1.8763,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 1.8405,
+      "loss": 2.2545,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.8135,
+      "loss": 2.31,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 1.8887,
+      "loss": 2.394,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 1.9344,
+      "loss": 2.664,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 1.7029,
+      "loss": 3.2972,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.6576,
+      "loss": 1.9397,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.531,
+      "loss": 1.94,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.8376,
+      "loss": 2.2578,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.623,
+      "loss": 2.2072,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.8216,
+      "loss": 2.521,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 1.6551,
+      "loss": 2.9765,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.581,
+      "loss": 1.8495,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.7052,
+      "loss": 2.1343,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.8765,
+      "loss": 2.3914,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.6884,
+      "loss": 2.1701,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 1.6657,
+      "loss": 2.2561,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 1.7195,
+      "loss": 2.8575,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.651,
+      "loss": 1.8819,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 1.8102,
+      "loss": 2.1998,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 1.8821,
+      "loss": 2.3208,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.8894,
+      "loss": 2.3829,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 1.7385,
+      "loss": 2.2179,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 1.6107,
+      "loss": 2.7775,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.930658693426381e+16,
+  "total_flos": 6759056164313088.0,
   "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:f76c7a494c5168464248de6e1be6d88051452d6dd246508974e2c5a27d3dbff3
+oid sha256:d98bba17031f248cade791f27c9fb624e489376ca991d51785e12dfad5ada2c2
 size 4728