Model save

README.md

@@ -50,8 +50,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.0
+- PEFT 0.13.1
 - Transformers 4.45.2
-- Pytorch 2.4.0
-- Datasets 2.21.0
+- Pytorch 2.4.1
 - Tokenizers 0.20.0

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "k_proj",
+    "q_proj",
     "gate_proj",
-    "v_proj",
+    "down_proj",
     "up_proj",
-    "q_proj",
-    "down_proj"
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d14821c09af9d8c759cd33f0d395dcdc4e73ecb506c1703f6c540efc107b38
+oid sha256:39922ffb5f02f9d8789a865ec5315b1b6656a7e7016c1af19856418a3a045f90
 size 1635969696

trainer_state.json

@@ -10,67 +10,67 @@
   "log_history": [
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.9584088921546936,
+      "grad_norm": 0.9415706992149353,
       "learning_rate": 8.794946550048592e-05,
-      "loss": 0.8701,
+      "loss": 0.8636,
       "step": 250
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.7143980264663696,
+      "grad_norm": 0.6905472278594971,
       "learning_rate": 7.580174927113704e-05,
-      "loss": 0.4271,
+      "loss": 0.4257,
       "step": 500
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.627783477306366,
+      "grad_norm": 0.6437392234802246,
       "learning_rate": 6.365403304178815e-05,
-      "loss": 0.3804,
+      "loss": 0.3792,
       "step": 750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.6241222620010376,
+      "grad_norm": 0.6311036348342896,
       "learning_rate": 5.150631681243926e-05,
-      "loss": 0.3638,
+      "loss": 0.3628,
       "step": 1000
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 0.6115825176239014,
+      "grad_norm": 0.6062882542610168,
       "learning_rate": 3.9358600583090386e-05,
-      "loss": 0.3522,
+      "loss": 0.3511,
       "step": 1250
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.639370322227478,
+      "grad_norm": 0.6469098925590515,
       "learning_rate": 2.72108843537415e-05,
-      "loss": 0.3439,
+      "loss": 0.3425,
       "step": 1500
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 0.6484368443489075,
+      "grad_norm": 0.6484191417694092,
       "learning_rate": 1.5063168124392615e-05,
-      "loss": 0.3313,
+      "loss": 0.329,
       "step": 1750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.6229206919670105,
+      "grad_norm": 0.6347299218177795,
       "learning_rate": 2.915451895043732e-06,
-      "loss": 0.3234,
+      "loss": 0.3209,
       "step": 2000
     },
     {
       "epoch": 4.0,
       "step": 2060,
       "total_flos": 1.4445804612483994e+18,
-      "train_loss": 0.42104607832084584,
-      "train_runtime": 30133.5745,
-      "train_samples_per_second": 17.5,
+      "train_loss": 0.4188447378214123,
+      "train_runtime": 30284.0025,
+      "train_samples_per_second": 17.413,
       "train_steps_per_second": 0.068
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81da159f8e27ac8bb61e3f1aa284bb40d5b444177144114b63e2020a44f0308a
+oid sha256:aef97ff5f47dce62db3654e9a89a27e915a0ff99aa25be9c7a88d60a99a91224
 size 5240