Upload folder using huggingface_hub

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "down_proj",
     "gate_proj",
+    "k_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
-    "o_proj",
-    "up_proj"
+    "q_proj",
+    "o_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:b809515d6a1499e324e71cabfe1e5be837e5bbf0d293f84cce2f4d88fdb810bd
+oid sha256:e25142d852c6940ad957a923e3fe68ca5f5f8b3ce880dee1752c4c41264d7ab4
 size 242266152

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a5e0e7dae38ca6f2ebfd99ccaae9570e2f2b91aa8db1c1c11255015e47e470
+oid sha256:4b6be3cc008feeded06cde5e56a5bf99a1070589e2edbe0b4c69a7736d19099a
 size 484650042

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bde0336a267c111569a8143afc5a48a7cefcfc2b02d9ae756ea1799ded6e26
+oid sha256:e33a6d44a2283d71de5c5a65eec778978acfc2025c73f1fc9173a25b45f34436
 size 14244

trainer_state.json

@@ -11,199 +11,199 @@
     {
       "epoch": 0.03,
       "learning_rate": 0.0002,
-      "loss": 2.7261,
+      "loss": 2.7359,
       "step": 2
     },
     {
       "epoch": 0.06,
       "learning_rate": 0.0002,
-      "loss": 1.6055,
+      "loss": 1.7382,
       "step": 4
     },
     {
       "epoch": 0.09,
       "learning_rate": 0.0002,
-      "loss": 1.7313,
+      "loss": 1.5779,
       "step": 6
     },
     {
       "epoch": 0.12,
       "learning_rate": 0.0002,
-      "loss": 1.6077,
+      "loss": 1.4905,
       "step": 8
     },
     {
       "epoch": 0.15,
       "learning_rate": 0.0002,
-      "loss": 1.3076,
+      "loss": 1.3959,
       "step": 10
     },
     {
       "epoch": 0.18,
       "learning_rate": 0.0002,
-      "loss": 1.6665,
+      "loss": 1.5667,
       "step": 12
     },
     {
       "epoch": 0.21,
       "learning_rate": 0.0002,
-      "loss": 1.7677,
+      "loss": 1.7249,
       "step": 14
     },
     {
       "epoch": 0.24,
       "learning_rate": 0.0002,
-      "loss": 2.0045,
+      "loss": 2.2016,
       "step": 16
     },
     {
       "epoch": 0.27,
       "learning_rate": 0.0002,
-      "loss": 2.2517,
+      "loss": 2.2788,
       "step": 18
     },
     {
       "epoch": 0.3,
       "learning_rate": 0.0002,
-      "loss": 1.804,
+      "loss": 1.7629,
       "step": 20
     },
     {
       "epoch": 0.33,
       "learning_rate": 0.0002,
-      "loss": 1.5239,
+      "loss": 1.414,
       "step": 22
     },
     {
       "epoch": 0.36,
       "learning_rate": 0.0002,
-      "loss": 1.4906,
+      "loss": 1.3766,
       "step": 24
     },
     {
       "epoch": 0.39,
       "learning_rate": 0.0002,
-      "loss": 1.2528,
+      "loss": 1.2258,
       "step": 26
     },
     {
       "epoch": 0.42,
       "learning_rate": 0.0002,
-      "loss": 1.4291,
+      "loss": 1.3666,
       "step": 28
     },
     {
       "epoch": 0.45,
       "learning_rate": 0.0002,
-      "loss": 1.5944,
+      "loss": 1.5935,
       "step": 30
     },
     {
       "epoch": 0.48,
       "learning_rate": 0.0002,
-      "loss": 1.5373,
+      "loss": 1.5005,
       "step": 32
     },
     {
       "epoch": 0.51,
       "learning_rate": 0.0002,
-      "loss": 2.1024,
+      "loss": 1.9383,
       "step": 34
     },
     {
       "epoch": 0.54,
       "learning_rate": 0.0002,
-      "loss": 1.54,
+      "loss": 1.5443,
       "step": 36
     },
     {
       "epoch": 0.57,
       "learning_rate": 0.0002,
-      "loss": 1.3825,
+      "loss": 1.4088,
       "step": 38
     },
     {
       "epoch": 0.6,
       "learning_rate": 0.0002,
-      "loss": 1.3484,
+      "loss": 1.4293,
       "step": 40
     },
     {
       "epoch": 0.63,
       "learning_rate": 0.0002,
-      "loss": 1.1742,
+      "loss": 1.1608,
       "step": 42
     },
     {
       "epoch": 0.66,
       "learning_rate": 0.0002,
-      "loss": 1.1066,
+      "loss": 1.2382,
       "step": 44
     },
     {
       "epoch": 0.69,
       "learning_rate": 0.0002,
-      "loss": 1.3872,
+      "loss": 1.4817,
       "step": 46
     },
     {
       "epoch": 0.72,
       "learning_rate": 0.0002,
-      "loss": 1.5933,
+      "loss": 1.5242,
       "step": 48
     },
     {
       "epoch": 0.75,
       "learning_rate": 0.0002,
-      "loss": 2.4941,
+      "loss": 2.5209,
       "step": 50
     },
     {
       "epoch": 0.78,
       "learning_rate": 0.0002,
-      "loss": 1.4775,
+      "loss": 1.346,
       "step": 52
     },
     {
       "epoch": 0.81,
       "learning_rate": 0.0002,
-      "loss": 1.3824,
+      "loss": 1.5437,
       "step": 54
     },
     {
       "epoch": 0.84,
       "learning_rate": 0.0002,
-      "loss": 1.4725,
+      "loss": 1.4825,
       "step": 56
     },
     {
       "epoch": 0.86,
       "learning_rate": 0.0002,
-      "loss": 1.016,
+      "loss": 1.1331,
       "step": 58
     },
     {
       "epoch": 0.89,
       "learning_rate": 0.0002,
-      "loss": 1.4422,
+      "loss": 1.3705,
       "step": 60
     },
     {
       "epoch": 0.92,
       "learning_rate": 0.0002,
-      "loss": 1.5599,
+      "loss": 1.4236,
       "step": 62
     },
     {
       "epoch": 0.95,
       "learning_rate": 0.0002,
-      "loss": 1.4125,
+      "loss": 1.4443,
       "step": 64
     },
     {
       "epoch": 0.98,
       "learning_rate": 0.0002,
-      "loss": 1.6476,
+      "loss": 1.6586,
       "step": 66
     }
   ],
@@ -212,7 +212,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 4514637286858752.0,
+  "total_flos": 4514520321982464.0,
   "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 sha256:4667e3901a1c079d9b7aa778dedf56c4a3dfba011d8938f203581921b096ab2b
+oid sha256:ccbbef329ba894e258c57aa7b70826f7d56a2abde99647c6fe9d6743de3ffefe
 size 4728