Upload folder using huggingface_hub

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense_h_to_4h",
+    "dense_4h_to_h",
     "dense",
-    "dense_4h_to_h"
+    "dense_h_to_4h",
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1498a003705f5dc06807d024876b15d8df8a44c2e04b42e597c51d06c3780b0
+oid sha256:ff225d7cd93c9354fe146f6b33e9f90435dbb7291d293690f9dd87ff7d35928f
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b38ca7b86273250274e0d6a3a5676932493365d4eb943ac6e711970cb97cd73
+oid sha256:1fe1233fbe6e7880347093fdca26f5f414e52348c16039e94627c15ecd4fd308
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98fe5f2173f9e5ac71064e84ba62ff7741e3d2ed1014d512a7a0fcde357a9886
+oid sha256:c48d238a5896aebf0de11d918fdfa448e01e704d941b7d64bc881878d172f396
 size 14244

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -232,6 +232,15 @@
       "rstrip": false,
       "normalized": true,
       "special": false
+    },
+    {
+      "id": 50277,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -200,13 +200,21 @@
       "rstrip": false,
       "single_word": false,
       "special": false
+    },
+    "50277": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
   "tokenizer_class": "GPTNeoXTokenizer",
   "unk_token": "<|endoftext|>"
 }

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.2696,
+      "loss": 2.2963,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.4542,
+      "loss": 2.377,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.3623,
+      "loss": 2.4958,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.5283,
+      "loss": 2.5016,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.5501,
+      "loss": 2.439,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 2.7343,
+      "loss": 2.8349,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.1721,
+      "loss": 2.2263,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.2801,
+      "loss": 2.3421,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.4526,
+      "loss": 2.5675,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.4499,
+      "loss": 2.5763,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.4254,
+      "loss": 2.5332,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 2.6891,
+      "loss": 2.8075,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.2323,
+      "loss": 2.3415,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.1318,
+      "loss": 2.2512,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.6934,
+      "loss": 2.533,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.4916,
+      "loss": 2.555,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.6042,
+      "loss": 2.6089,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.6981,
+      "loss": 2.5684,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.3111,
+      "loss": 2.1186,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.3537,
+      "loss": 2.3147,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.5255,
+      "loss": 2.4782,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.3537,
+      "loss": 2.25,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.5072,
+      "loss": 2.501,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.4306,
+      "loss": 2.705,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2047338095837184.0,
+  "total_flos": 2049661840859136.0,
   "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:ee130089c2b6cb201cbccea96e2e23972d6b73ac0c5bb342769e44977ea7d1af
+oid sha256:2304f2bd39d21efc47c500cd5068601045aac2e65032bd864752914da7a71dbf
 size 4728