Upload folder using huggingface_hub

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
     "down_proj",
+    "o_proj",
     "gate_proj",
     "k_proj",
-    "up_proj",
     "v_proj",
-    "q_proj",
-    "o_proj"
+    "q_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:e25142d852c6940ad957a923e3fe68ca5f5f8b3ce880dee1752c4c41264d7ab4
+oid sha256:82f0584a9fdecad22b26d4b43b9759f406a5219824727c031f1c8d8557e8792f
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6be3cc008feeded06cde5e56a5bf99a1070589e2edbe0b4c69a7736d19099a
+oid sha256:b6cbf7903fa258b793125361ef6b4c1b93c52baafc3b11c52784b5bac1e483d4
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e33a6d44a2283d71de5c5a65eec778978acfc2025c73f1fc9173a25b45f34436
+oid sha256:619dbcc06b74b236aa1e4a20235db3ddb6093a74fe192b6d650a68dea86629c7
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824a429c5f95423b97fd2ff7dc1e1dffcd96691286babb37392f00bfcecaeb1b
+oid sha256:53465f7cbdf87cbc584b429a13bf1f7b1601c644d5e6387bef7542821ec7e747
 size 1064

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9990680335507922,
+  "epoch": 0.992,
   "eval_steps": 500,
-  "global_step": 67,
+  "global_step": 62,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,208 +11,196 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.7359,
+      "loss": 1.8763,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.7382,
+      "loss": 1.6551,
       "step": 4
     },
     {
-      "epoch": 0.09,
+      "epoch": 0.1,
       "learning_rate": 0.0002,
-      "loss": 1.5779,
+      "loss": 1.6117,
       "step": 6
     },
     {
-      "epoch": 0.12,
+      "epoch": 0.13,
       "learning_rate": 0.0002,
-      "loss": 1.4905,
+      "loss": 1.4364,
       "step": 8
     },
     {
-      "epoch": 0.15,
+      "epoch": 0.16,
       "learning_rate": 0.0002,
-      "loss": 1.3959,
+      "loss": 1.3856,
       "step": 10
     },
     {
-      "epoch": 0.18,
+      "epoch": 0.19,
       "learning_rate": 0.0002,
-      "loss": 1.5667,
+      "loss": 1.888,
       "step": 12
     },
     {
-      "epoch": 0.21,
+      "epoch": 0.22,
       "learning_rate": 0.0002,
-      "loss": 1.7249,
+      "loss": 2.7773,
       "step": 14
     },
     {
-      "epoch": 0.24,
+      "epoch": 0.26,
       "learning_rate": 0.0002,
-      "loss": 2.2016,
+      "loss": 2.7147,
       "step": 16
     },
     {
-      "epoch": 0.27,
+      "epoch": 0.29,
       "learning_rate": 0.0002,
-      "loss": 2.2788,
+      "loss": 1.6225,
       "step": 18
     },
     {
-      "epoch": 0.3,
+      "epoch": 0.32,
       "learning_rate": 0.0002,
-      "loss": 1.7629,
+      "loss": 1.4844,
       "step": 20
     },
     {
-      "epoch": 0.33,
+      "epoch": 0.35,
       "learning_rate": 0.0002,
-      "loss": 1.414,
+      "loss": 1.2329,
       "step": 22
     },
     {
-      "epoch": 0.36,
+      "epoch": 0.38,
       "learning_rate": 0.0002,
-      "loss": 1.3766,
+      "loss": 1.0668,
       "step": 24
     },
     {
-      "epoch": 0.39,
+      "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.2258,
+      "loss": 1.0695,
       "step": 26
     },
     {
-      "epoch": 0.42,
+      "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.3666,
+      "loss": 1.8005,
       "step": 28
     },
     {
-      "epoch": 0.45,
+      "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.5935,
+      "loss": 2.2701,
       "step": 30
     },
     {
-      "epoch": 0.48,
+      "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 1.5005,
+      "loss": 1.7467,
       "step": 32
     },
     {
-      "epoch": 0.51,
+      "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.9383,
+      "loss": 1.416,
       "step": 34
     },
     {
-      "epoch": 0.54,
+      "epoch": 0.58,
       "learning_rate": 0.0002,
-      "loss": 1.5443,
+      "loss": 1.3106,
       "step": 36
     },
     {
-      "epoch": 0.57,
+      "epoch": 0.61,
       "learning_rate": 0.0002,
-      "loss": 1.4088,
+      "loss": 0.8445,
       "step": 38
     },
     {
-      "epoch": 0.6,
+      "epoch": 0.64,
       "learning_rate": 0.0002,
-      "loss": 1.4293,
+      "loss": 1.0193,
       "step": 40
     },
     {
-      "epoch": 0.63,
+      "epoch": 0.67,
       "learning_rate": 0.0002,
-      "loss": 1.1608,
+      "loss": 1.5088,
       "step": 42
     },
     {
-      "epoch": 0.66,
+      "epoch": 0.7,
       "learning_rate": 0.0002,
-      "loss": 1.2382,
+      "loss": 1.7339,
       "step": 44
     },
     {
-      "epoch": 0.69,
+      "epoch": 0.74,
       "learning_rate": 0.0002,
-      "loss": 1.4817,
+      "loss": 2.137,
       "step": 46
     },
     {
-      "epoch": 0.72,
+      "epoch": 0.77,
       "learning_rate": 0.0002,
-      "loss": 1.5242,
+      "loss": 1.3696,
       "step": 48
     },
     {
-      "epoch": 0.75,
+      "epoch": 0.8,
       "learning_rate": 0.0002,
-      "loss": 2.5209,
+      "loss": 1.338,
       "step": 50
     },
     {
-      "epoch": 0.78,
+      "epoch": 0.83,
       "learning_rate": 0.0002,
-      "loss": 1.346,
+      "loss": 1.2948,
       "step": 52
     },
     {
-      "epoch": 0.81,
+      "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.5437,
+      "loss": 0.9147,
       "step": 54
     },
     {
-      "epoch": 0.84,
+      "epoch": 0.9,
       "learning_rate": 0.0002,
-      "loss": 1.4825,
+      "loss": 1.1057,
       "step": 56
     },
     {
-      "epoch": 0.86,
+      "epoch": 0.93,
       "learning_rate": 0.0002,
-      "loss": 1.1331,
+      "loss": 1.4985,
       "step": 58
     },
     {
-      "epoch": 0.89,
+      "epoch": 0.96,
       "learning_rate": 0.0002,
-      "loss": 1.3705,
+      "loss": 1.9006,
       "step": 60
     },
     {
-      "epoch": 0.92,
+      "epoch": 0.99,
       "learning_rate": 0.0002,
-      "loss": 1.4236,
+      "loss": 1.1481,
       "step": 62
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.0002,
-      "loss": 1.4443,
-      "step": 64
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.0002,
-      "loss": 1.6586,
-      "step": 66
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 62,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 4514520321982464.0,
+  "total_flos": 3204864602185728.0,
   "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:ccbbef329ba894e258c57aa7b70826f7d56a2abde99647c6fe9d6743de3ffefe
+oid sha256:0681cd1910c2b08abb29c099e64819599db5cbd9791249e18d756090b563b039
 size 4728