Upload folder using huggingface_hub

README.md

@@ -201,4 +201,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ### Framework versions
 
-- PEFT 0.8.0
+- PEFT 0.8.2

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b797e68e1903aee340b6795ffe7aac96fbe37ace77181e8bcb279718b29a3cc
+oid sha256:5d886d8a1186e5d9fc2b04555a1c93c86cdb3b1c7be92f6b5a8133b1948b2132
 size 113271504

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9258b5f5a1e06f93e3c4dee1200ee1f7dcc874f2620c456019a5786b545bcb49
+oid sha256:ade5fe5578ba3e45093e76239079cd7c674acb39b067f0e411cdc84c9684db50
 size 226609018

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:791cdbf24c147c2dd133d90d5a8de86fa10a682bb77632d84519c54378ad98ac
+oid sha256:f8234de6fbee7c16a8cba461197c3f2fb0819f0d8a1076e2e7a621c8abecf598
 size 14244

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

trainer_state.json

@@ -11,145 +11,145 @@
     {
       "epoch": 0.04,
       "learning_rate": 2e-05,
-      "loss": 1.7309,
+      "loss": 1.6185,
       "step": 2
     },
     {
       "epoch": 0.08,
       "learning_rate": 2e-05,
-      "loss": 1.8735,
+      "loss": 1.737,
       "step": 4
     },
     {
       "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.9019,
+      "loss": 1.7356,
       "step": 6
     },
     {
       "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 2.0468,
+      "loss": 1.8628,
       "step": 8
     },
     {
       "epoch": 0.21,
       "learning_rate": 2e-05,
-      "loss": 2.165,
+      "loss": 1.9513,
       "step": 10
     },
     {
       "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 2.3337,
+      "loss": 1.915,
       "step": 12
     },
     {
       "epoch": 0.29,
       "learning_rate": 2e-05,
-      "loss": 1.6342,
+      "loss": 1.5832,
       "step": 14
     },
     {
       "epoch": 0.33,
       "learning_rate": 2e-05,
-      "loss": 1.5568,
+      "loss": 1.4809,
       "step": 16
     },
     {
       "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.848,
+      "loss": 1.7592,
       "step": 18
     },
     {
       "epoch": 0.41,
       "learning_rate": 2e-05,
-      "loss": 1.6945,
+      "loss": 1.5888,
       "step": 20
     },
     {
       "epoch": 0.45,
       "learning_rate": 2e-05,
-      "loss": 1.9699,
+      "loss": 1.8435,
       "step": 22
     },
     {
       "epoch": 0.49,
       "learning_rate": 2e-05,
-      "loss": 1.9858,
+      "loss": 1.7471,
       "step": 24
     },
     {
       "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.5434,
+      "loss": 1.5115,
       "step": 26
     },
     {
       "epoch": 0.57,
       "learning_rate": 2e-05,
-      "loss": 1.7222,
+      "loss": 1.6771,
       "step": 28
     },
     {
       "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.88,
+      "loss": 1.8267,
       "step": 30
     },
     {
       "epoch": 0.66,
       "learning_rate": 2e-05,
-      "loss": 1.7122,
+      "loss": 1.655,
       "step": 32
     },
     {
       "epoch": 0.7,
       "learning_rate": 2e-05,
-      "loss": 1.71,
+      "loss": 1.6435,
       "step": 34
     },
     {
       "epoch": 0.74,
       "learning_rate": 2e-05,
-      "loss": 1.8865,
+      "loss": 1.7765,
       "step": 36
     },
     {
       "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 1.5926,
+      "loss": 1.5843,
       "step": 38
     },
     {
       "epoch": 0.82,
       "learning_rate": 2e-05,
-      "loss": 1.7483,
+      "loss": 1.7277,
       "step": 40
     },
     {
       "epoch": 0.86,
       "learning_rate": 2e-05,
-      "loss": 1.8441,
+      "loss": 1.8202,
       "step": 42
     },
     {
       "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.8675,
+      "loss": 1.8437,
       "step": 44
     },
     {
       "epoch": 0.94,
       "learning_rate": 2e-05,
-      "loss": 1.7398,
+      "loss": 1.7047,
       "step": 46
     },
     {
       "epoch": 0.98,
       "learning_rate": 2e-05,
-      "loss": 1.7315,
+      "loss": 1.6657,
       "step": 48
     }
   ],
@@ -158,7 +158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.6886766261215232e+16,
+  "total_flos": 1.6801826776547328e+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 sha256:4a2edf670764d433a0d096397c0455256a8d41441da8b525abb55fef0a5238ac
+oid sha256:8cbf67042848e44a431e847ef49dd5be7f2d49ddc5ef66eddad11f895d3225a4
 size 4728