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 0.7.2.dev0
+- PEFT 0.8.1.dev0

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22752e35bdb61ee34953f8b703375848a3db2c155e7dbaa37b2c8ab59f4feabf
+oid sha256:4596e771ab7f76dd4ba77e071f5ff81ff6f34f8611ff29e512dc1be8777b7a51
 size 134235712

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd2190146ef39a84faeb3192ab6640ab2ffd6eee4f47a114b870fcbbe44c726
+oid sha256:27b362e466a0afa9cb87877f5695b95b9d7774c8d0582c2ee43fa70b58afa483
 size 268514874

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c398e459ddc0d0eea0a5e40d93d15d770f725d809e498a814b2045f61b54f82f
+oid sha256:eb9532303a09e41d637185a576b59ba1e5615a6364440294f01c29cf61c440cd
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
 size 1064

trainer_state.json

@@ -1,320 +1,164 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9944064636420137,
+  "epoch": 0.9846153846153847,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02,
+      "epoch": 0.04,
       "learning_rate": 0.0002,
-      "loss": 2.9084,
+      "loss": 2.3108,
       "step": 2
     },
     {
-      "epoch": 0.04,
+      "epoch": 0.08,
       "learning_rate": 0.0002,
-      "loss": 2.7567,
+      "loss": 2.4875,
       "step": 4
     },
     {
-      "epoch": 0.06,
+      "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 2.4718,
+      "loss": 2.6289,
       "step": 6
     },
     {
-      "epoch": 0.08,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 2.5822,
+      "loss": 2.6313,
       "step": 8
     },
     {
-      "epoch": 0.1,
+      "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 2.5266,
+      "loss": 2.4607,
       "step": 10
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.25,
       "learning_rate": 0.0002,
-      "loss": 2.4351,
+      "loss": 3.0292,
       "step": 12
     },
     {
-      "epoch": 0.14,
+      "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.3991,
+      "loss": 2.2534,
       "step": 14
     },
     {
-      "epoch": 0.16,
+      "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 2.4939,
+      "loss": 2.2002,
       "step": 16
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.37,
       "learning_rate": 0.0002,
-      "loss": 2.3929,
+      "loss": 2.5392,
       "step": 18
     },
     {
-      "epoch": 0.2,
+      "epoch": 0.41,
       "learning_rate": 0.0002,
-      "loss": 2.2716,
+      "loss": 2.5274,
       "step": 20
     },
     {
-      "epoch": 0.22,
+      "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 2.385,
+      "loss": 2.7531,
       "step": 22
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.49,
       "learning_rate": 0.0002,
-      "loss": 2.502,
+      "loss": 2.7366,
       "step": 24
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.53,
       "learning_rate": 0.0002,
-      "loss": 2.22,
+      "loss": 2.1837,
       "step": 26
     },
     {
-      "epoch": 0.28,
+      "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 2.2473,
+      "loss": 2.3765,
       "step": 28
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.62,
       "learning_rate": 0.0002,
-      "loss": 2.3497,
+      "loss": 2.4551,
       "step": 30
     },
     {
-      "epoch": 0.32,
+      "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 2.2763,
+      "loss": 2.4169,
       "step": 32
     },
     {
-      "epoch": 0.34,
+      "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 2.3384,
+      "loss": 2.5244,
       "step": 34
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 2.2627,
+      "loss": 2.6772,
       "step": 36
     },
     {
-      "epoch": 0.38,
+      "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 2.3317,
+      "loss": 2.2779,
       "step": 38
     },
     {
-      "epoch": 0.4,
+      "epoch": 0.82,
       "learning_rate": 0.0002,
-      "loss": 2.4054,
+      "loss": 2.3669,
       "step": 40
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 2.1966,
+      "loss": 2.4285,
       "step": 42
     },
     {
-      "epoch": 0.44,
+      "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 2.2012,
+      "loss": 2.5265,
       "step": 44
     },
     {
-      "epoch": 0.46,
+      "epoch": 0.94,
       "learning_rate": 0.0002,
-      "loss": 2.2417,
+      "loss": 2.4748,
       "step": 46
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 2.1286,
+      "loss": 2.5528,
       "step": 48
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.0002,
-      "loss": 2.3857,
-      "step": 50
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.0002,
-      "loss": 2.4254,
-      "step": 52
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.0002,
-      "loss": 2.3185,
-      "step": 54
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0002,
-      "loss": 2.2981,
-      "step": 56
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0002,
-      "loss": 2.3821,
-      "step": 58
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.0002,
-      "loss": 2.2838,
-      "step": 60
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.0002,
-      "loss": 2.3335,
-      "step": 62
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0002,
-      "loss": 2.274,
-      "step": 64
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.0002,
-      "loss": 2.2696,
-      "step": 66
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.0002,
-      "loss": 2.0829,
-      "step": 68
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.0002,
-      "loss": 2.0368,
-      "step": 70
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0002,
-      "loss": 2.1695,
-      "step": 72
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.0002,
-      "loss": 2.116,
-      "step": 74
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0002,
-      "loss": 2.1157,
-      "step": 76
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.0002,
-      "loss": 2.3132,
-      "step": 78
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.0002,
-      "loss": 2.2322,
-      "step": 80
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.0002,
-      "loss": 2.2643,
-      "step": 82
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.0002,
-      "loss": 2.2758,
-      "step": 84
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.0002,
-      "loss": 2.2514,
-      "step": 86
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0002,
-      "loss": 2.3033,
-      "step": 88
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0002,
-      "loss": 2.2307,
-      "step": 90
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.0002,
-      "loss": 2.2363,
-      "step": 92
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.0002,
-      "loss": 2.0307,
-      "step": 94
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002,
-      "loss": 1.963,
-      "step": 96
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.0002,
-      "loss": 2.0864,
-      "step": 98
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.0002,
-      "loss": 2.1501,
-      "step": 100
     }
   ],
   "logging_steps": 2,
-  "max_steps": 100,
+  "max_steps": 48,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 8558618648248320.0,
+  "total_flos": 2065520976592896.0,
   "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 sha256:61365ab9c9c37bb856874a9e6eb2b021ea0ea3c990d6e7063744ff4ba2d7b882
+oid sha256:6ae7fe3ab3dba256391a270703ac29ff397f6085f8bd1d8aa8ef5a2cf003c5a1
 size 4728