Upload folder using huggingface_hub

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881f2340c02d4d32c10f3e9d78bb208dcbce12b61a20156f43514be608ff8250
+oid sha256:74d3c94430da216e49b2f1edfd4d47a96775b1caf13c23787dde2966ddb28ff6
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97ad97485f7553240a4bd1e25597aeed805c4600a59cc77473faa5f96a97efa
+oid sha256:db0cfcb41260dc3ac3f0d2d7b951d685f8708331d34c01bad2d150ab37755fec
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c75855cec5126735fc2188235300e2c81959c32df6ee02c5ff30127dcdc657
+oid sha256:e8400da4ebd11656aee565d96885e25350dc287eec4ad76194986bfeef69bcc7
 size 14244

special_tokens_map.json

@@ -30,7 +30,7 @@
     "single_word": false
   },
   "pad_token": {
-    "content": "<|endoftext|>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -250,6 +250,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 50279,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -216,6 +216,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "50279": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -226,7 +234,7 @@
   "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": 2.3604,
+      "loss": 2.3426,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.4466,
+      "loss": 2.3786,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.8212,
+      "loss": 2.6959,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.638,
+      "loss": 2.792,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.8046,
+      "loss": 2.8302,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 3.2636,
+      "loss": 3.3717,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2681,
+      "loss": 2.2267,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.3826,
+      "loss": 2.5093,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.6718,
+      "loss": 2.7368,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.6197,
+      "loss": 2.5378,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.573,
+      "loss": 2.6,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 3.1306,
+      "loss": 3.0639,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.2594,
+      "loss": 2.1673,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.4572,
+      "loss": 2.4645,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.4869,
+      "loss": 2.4987,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.6306,
+      "loss": 2.3191,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.6139,
+      "loss": 2.7003,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.8307,
+      "loss": 2.8433,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.204,
+      "loss": 2.2216,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.2423,
+      "loss": 2.346,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.3021,
+      "loss": 2.3354,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.3643,
+      "loss": 2.4828,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.6392,
+      "loss": 2.6882,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.9109,
+      "loss": 2.7263,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 2058945513185280.0,
+  "total_flos": 2061789415243776.0,
   "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:e3eeebac40f73e5cebd2ccfc5dbebb5cb8c8e9abdf4f8fae6ceab6d2b7c8eb9f
+oid sha256:2d2faca9fc2994cb010b4af1851a2b88208d18c68e81e002db967e23a8aae6e1
 size 4728