Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: stabilityai/stablelm-3b-4e1t
+base_model: Deci/DeciLM-7B
 ---
 
 # 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": "Deci/DeciLM-7B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "up_proj",
     "gate_proj",
-    "up_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f10448dd7937e1c357b8e7d1f4d0092760348b6815e6e146983bb9a845775a6
-size 58221088
+oid sha256:ea2439ac05d42add5cc002f82d1104479bea155615f9a2c4abecd84fb58a7923
+size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b12a0408c37b861c861255496b1e39574c74d10cbd5b03ccffd757e3b769c0
-size 116508154
+oid sha256:cecbf0dda5daf4dd895fcff4f7de99c4b831c5e2e15e4ec73818664e33d264bf
+size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44fb8f53b6cea475e11703fe1dbf083571edccb2c91ea70df2890844d840560e
+oid sha256:90d1ebed1f3fe5977ea9a067e652c5cc8099fdf0f640441d00f2343d300bbf5c
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea217589f6a52e6e5bf252b883fdc2c5bb872bd2fee80104e01128c8070232c3
+oid sha256:7677cdbf46bc07af44ed81cd4e9c5271b5fe5d7d48afb5d71264d1f11c7901f3
 size 1064

special_tokens_map.json

@@ -1,21 +1,21 @@
 {
   "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,
@@ -10,203 +11,32 @@
       "special": true
     },
     "1": {
-      "content": "<|padding|>",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50254": {
-      "content": "                        ",
+    "2": {
+      "content": "</s>",
       "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,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": false
+      "special": true
     }
   },
-  "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": true
 }

trainer_state.json

@@ -1,320 +1,212 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9944064636420137,
+  "epoch": 0.9941747572815534,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 64,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 2.1047,
+      "loss": 1.814,
       "step": 2
     },
     {
-      "epoch": 0.04,
+      "epoch": 0.06,
       "learning_rate": 2e-05,
-      "loss": 2.1646,
+      "loss": 1.8488,
       "step": 4
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.09,
       "learning_rate": 2e-05,
-      "loss": 2.1348,
+      "loss": 1.9517,
       "step": 6
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 2.1833,
+      "loss": 2.1303,
       "step": 8
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 2.1716,
+      "loss": 2.0863,
       "step": 10
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.19,
       "learning_rate": 2e-05,
-      "loss": 2.0802,
+      "loss": 2.1774,
       "step": 12
     },
     {
-      "epoch": 0.14,
+      "epoch": 0.22,
       "learning_rate": 2e-05,
-      "loss": 2.1656,
+      "loss": 2.0094,
       "step": 14
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 2.08,
+      "loss": 2.1157,
       "step": 16
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.28,
       "learning_rate": 2e-05,
-      "loss": 1.8647,
+      "loss": 1.6814,
       "step": 18
     },
     {
-      "epoch": 0.2,
+      "epoch": 0.31,
       "learning_rate": 2e-05,
-      "loss": 1.8017,
+      "loss": 1.7955,
       "step": 20
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.34,
       "learning_rate": 2e-05,
-      "loss": 2.1878,
+      "loss": 1.5942,
       "step": 22
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.9446,
+      "loss": 1.784,
       "step": 24
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.4,
       "learning_rate": 2e-05,
-      "loss": 1.9301,
+      "loss": 1.9085,
       "step": 26
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.43,
       "learning_rate": 2e-05,
-      "loss": 1.9715,
+      "loss": 1.8719,
       "step": 28
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.47,
       "learning_rate": 2e-05,
-      "loss": 1.9009,
+      "loss": 1.7901,
       "step": 30
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.5,
       "learning_rate": 2e-05,
-      "loss": 1.9004,
+      "loss": 1.9141,
       "step": 32
     },
     {
-      "epoch": 0.34,
+      "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.9961,
+      "loss": 1.6839,
       "step": 34
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.56,
       "learning_rate": 2e-05,
-      "loss": 1.8913,
+      "loss": 1.6629,
       "step": 36
     },
     {
-      "epoch": 0.38,
+      "epoch": 0.59,
       "learning_rate": 2e-05,
-      "loss": 1.8726,
+      "loss": 1.8596,
       "step": 38
     },
     {
-      "epoch": 0.4,
+      "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.756,
+      "loss": 1.7276,
       "step": 40
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.65,
       "learning_rate": 2e-05,
-      "loss": 1.863,
+      "loss": 1.9085,
       "step": 42
     },
     {
-      "epoch": 0.44,
+      "epoch": 0.68,
       "learning_rate": 2e-05,
-      "loss": 1.7184,
+      "loss": 2.0206,
       "step": 44
     },
     {
-      "epoch": 0.46,
+      "epoch": 0.71,
       "learning_rate": 2e-05,
-      "loss": 1.7539,
+      "loss": 1.8088,
       "step": 46
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.75,
       "learning_rate": 2e-05,
-      "loss": 1.9347,
+      "loss": 1.776,
       "step": 48
     },
     {
-      "epoch": 0.5,
+      "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.689,
+      "loss": 1.6315,
       "step": 50
     },
     {
-      "epoch": 0.52,
+      "epoch": 0.81,
       "learning_rate": 2e-05,
-      "loss": 1.6629,
+      "loss": 1.7063,
       "step": 52
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.84,
       "learning_rate": 2e-05,
-      "loss": 1.873,
+      "loss": 1.8203,
       "step": 54
     },
     {
-      "epoch": 0.56,
+      "epoch": 0.87,
       "learning_rate": 2e-05,
-      "loss": 1.6941,
+      "loss": 1.7645,
       "step": 56
     },
     {
-      "epoch": 0.58,
+      "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.8841,
+      "loss": 1.7883,
       "step": 58
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.93,
       "learning_rate": 2e-05,
-      "loss": 1.7392,
+      "loss": 1.827,
       "step": 60
     },
     {
-      "epoch": 0.62,
+      "epoch": 0.96,
       "learning_rate": 2e-05,
-      "loss": 1.8437,
+      "loss": 1.751,
       "step": 62
     },
-    {
-      "epoch": 0.64,
-      "learning_rate": 2e-05,
-      "loss": 1.7183,
-      "step": 64
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 2e-05,
-      "loss": 1.6943,
-      "step": 66
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 2e-05,
-      "loss": 1.6951,
-      "step": 68
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 2e-05,
-      "loss": 1.6646,
-      "step": 70
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 2e-05,
-      "loss": 1.6268,
-      "step": 72
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 2e-05,
-      "loss": 1.6809,
-      "step": 74
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 2e-05,
-      "loss": 1.7665,
-      "step": 76
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 2e-05,
-      "loss": 1.7941,
-      "step": 78
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 2e-05,
-      "loss": 1.7835,
-      "step": 80
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 2e-05,
-      "loss": 1.7583,
-      "step": 82
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 2e-05,
-      "loss": 1.8441,
-      "step": 84
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 2e-05,
-      "loss": 1.7652,
-      "step": 86
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 2e-05,
-      "loss": 1.8324,
-      "step": 88
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 2e-05,
-      "loss": 1.66,
-      "step": 90
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 2e-05,
-      "loss": 1.7413,
-      "step": 92
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 2e-05,
-      "loss": 1.6313,
-      "step": 94
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 2e-05,
-      "loss": 1.5796,
-      "step": 96
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 2e-05,
-      "loss": 1.6447,
-      "step": 98
-    },
     {
       "epoch": 0.99,
       "learning_rate": 2e-05,
-      "loss": 1.7436,
-      "step": 100
+      "loss": 1.7058,
+      "step": 64
     }
   ],
   "logging_steps": 2,
-  "max_steps": 100,
+  "max_steps": 64,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2.9243190847850496e+16,
+  "total_flos": 3.0588064985088e+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 sha256:7892714d09655e07c8018641b8031a39fbac1aa1cf44d146fb4cbb7ecab3d579
+oid sha256:0d9cc05ece0debe876fe6711a0ac73fa7df4c720765ea36fefcd55cbd51a38d2
 size 4728