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,
@@ -19,9 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00da2a3654bb68a833f9e71b25793cd39c7f2e4a25affca2f5b8dd25887fd704
-size 113271504
+oid sha256:8f10448dd7937e1c357b8e7d1f4d0092760348b6815e6e146983bb9a845775a6
+size 58221088

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea01af1273ff7315c262dad351f1b49372552a82f992952eaabf76b1ccdebc43
-size 226609018
+oid sha256:b3b12a0408c37b861c861255496b1e39574c74d10cbd5b03ccffd757e3b769c0
+size 116508154

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75634a2d2aafc3822491cb27b09c1d537881d6adb80e81babb7515b20c6d38af
+oid sha256:44fb8f53b6cea475e11703fe1dbf083571edccb2c91ea70df2890844d840560e
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bf1e902c3114bb5312c2c178dc4d942be3a06cb5931cabbb4ddb7748d0f53ee
+oid sha256:ea217589f6a52e6e5bf252b883fdc2c5bb872bd2fee80104e01128c8070232c3
 size 1064

special_tokens_map.json

@@ -1,21 +1,21 @@
 {
   "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,
@@ -11,32 +10,203 @@
       "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": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "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
     }
   },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": true,
+  "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

@@ -1,218 +1,320 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9990680335507922,
+  "epoch": 0.9944064636420137,
   "eval_steps": 500,
-  "global_step": 67,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
+      "epoch": 0.02,
       "learning_rate": 2e-05,
-      "loss": 1.9981,
+      "loss": 2.1047,
       "step": 2
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.1241,
+      "loss": 2.1646,
       "step": 4
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.06,
       "learning_rate": 2e-05,
-      "loss": 0.903,
+      "loss": 2.1348,
       "step": 6
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 0.802,
+      "loss": 2.1833,
       "step": 8
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.1,
       "learning_rate": 2e-05,
-      "loss": 0.8679,
+      "loss": 2.1716,
       "step": 10
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 0.7797,
+      "loss": 2.0802,
       "step": 12
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.14,
       "learning_rate": 2e-05,
-      "loss": 1.1186,
+      "loss": 2.1656,
       "step": 14
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 1.1794,
+      "loss": 2.08,
       "step": 16
     },
     {
-      "epoch": 0.27,
+      "epoch": 0.18,
       "learning_rate": 2e-05,
-      "loss": 1.8361,
+      "loss": 1.8647,
       "step": 18
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.2,
       "learning_rate": 2e-05,
-      "loss": 0.9534,
+      "loss": 1.8017,
       "step": 20
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.22,
       "learning_rate": 2e-05,
-      "loss": 0.9416,
+      "loss": 2.1878,
       "step": 22
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.24,
       "learning_rate": 2e-05,
-      "loss": 0.9872,
+      "loss": 1.9446,
       "step": 24
     },
     {
-      "epoch": 0.39,
+      "epoch": 0.26,
       "learning_rate": 2e-05,
-      "loss": 0.709,
+      "loss": 1.9301,
       "step": 26
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.28,
       "learning_rate": 2e-05,
-      "loss": 0.9765,
+      "loss": 1.9715,
       "step": 28
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.3,
       "learning_rate": 2e-05,
-      "loss": 1.1499,
+      "loss": 1.9009,
       "step": 30
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.32,
       "learning_rate": 2e-05,
-      "loss": 1.0416,
+      "loss": 1.9004,
       "step": 32
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.34,
       "learning_rate": 2e-05,
-      "loss": 1.5067,
+      "loss": 1.9961,
       "step": 34
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.36,
       "learning_rate": 2e-05,
-      "loss": 1.2399,
+      "loss": 1.8913,
       "step": 36
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.38,
       "learning_rate": 2e-05,
-      "loss": 0.8517,
+      "loss": 1.8726,
       "step": 38
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.4,
       "learning_rate": 2e-05,
-      "loss": 1.0055,
+      "loss": 1.756,
       "step": 40
     },
     {
-      "epoch": 0.63,
+      "epoch": 0.42,
       "learning_rate": 2e-05,
-      "loss": 0.7505,
+      "loss": 1.863,
       "step": 42
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.44,
       "learning_rate": 2e-05,
-      "loss": 0.7689,
+      "loss": 1.7184,
       "step": 44
     },
     {
-      "epoch": 0.69,
+      "epoch": 0.46,
       "learning_rate": 2e-05,
-      "loss": 1.0528,
+      "loss": 1.7539,
       "step": 46
     },
     {
-      "epoch": 0.72,
+      "epoch": 0.48,
       "learning_rate": 2e-05,
-      "loss": 1.0274,
+      "loss": 1.9347,
       "step": 48
     },
     {
-      "epoch": 0.75,
+      "epoch": 0.5,
       "learning_rate": 2e-05,
-      "loss": 1.9261,
+      "loss": 1.689,
       "step": 50
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.52,
       "learning_rate": 2e-05,
-      "loss": 0.912,
+      "loss": 1.6629,
       "step": 52
     },
     {
-      "epoch": 0.81,
+      "epoch": 0.54,
       "learning_rate": 2e-05,
-      "loss": 0.9351,
+      "loss": 1.873,
       "step": 54
     },
     {
-      "epoch": 0.84,
+      "epoch": 0.56,
       "learning_rate": 2e-05,
-      "loss": 0.8161,
+      "loss": 1.6941,
       "step": 56
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.58,
       "learning_rate": 2e-05,
-      "loss": 0.8585,
+      "loss": 1.8841,
       "step": 58
     },
     {
-      "epoch": 0.89,
+      "epoch": 0.6,
       "learning_rate": 2e-05,
-      "loss": 0.9278,
+      "loss": 1.7392,
       "step": 60
     },
     {
-      "epoch": 0.92,
+      "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.0046,
+      "loss": 1.8437,
       "step": 62
     },
     {
-      "epoch": 0.95,
+      "epoch": 0.64,
       "learning_rate": 2e-05,
-      "loss": 0.8376,
+      "loss": 1.7183,
       "step": 64
     },
     {
-      "epoch": 0.98,
+      "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.1047,
+      "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
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 100,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2.562151273168896e+16,
+  "total_flos": 2.9243190847850496e+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 sha256:35bc91a3ec2050fc13133158eeb9d230bb8786a2281adb489299f2bfe8f04f9c
+oid sha256:7892714d09655e07c8018641b8031a39fbac1aa1cf44d146fb4cbb7ecab3d579
 size 4728