Upload folder using huggingface_hub

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
     "gate_up_proj",
-    "o_proj",
-    "down_proj"
+    "down_proj",
+    "qkv_proj",
+    "o_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:b39dd8772b475e853e665b06e47fa00dfb2a17b95b26279bc0297f19c0d7ba9d
+oid sha256:e2b650eafd945cf76bffa8082697fd3ff833a2acb3c1f999087552eb6809ceb6
 size 805341552

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05aa74d3c5b2d0bc5a611f2a701f97601a9feae7804d6394f3393cf1db9304a
+oid sha256:dbea9603a80fb64b1c940be7e3d68c3c2149fd9d9ead8a78bab625f3cb19fadf
 size 409252709

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c6b7d901b2d306ace162440a83714f86c765e01e4fd79689639982277d71e1
+oid sha256:ef51e16c6a17540db1d871c8a331f96802a104e1203e4600237ca5e9b68c6be2
 size 14645

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb3297ff8b4f6ff1294f9cbd9484ef59926708f3aa3b7602079ad0572b02c01c
+oid sha256:929791789119226e566ddaa2c943c7df8db37a661c8a6885321f70964d94fc76
 size 1465

trainer_state.json

@@ -3,35 +3,21 @@
   "best_model_checkpoint": null,
   "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 60,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.6666666666666666,
-      "grad_norm": 0.43741512298583984,
-      "learning_rate": 0.0003880691476669283,
-      "loss": 1.4419,
-      "step": 20
-    },
     {
       "epoch": 1.3333333333333333,
-      "grad_norm": 0.2456790804862976,
-      "learning_rate": 0.0002771922483335202,
-      "loss": 1.2079,
-      "step": 40
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 0.2239806205034256,
-      "learning_rate": 0.00016631534900011212,
-      "loss": 1.0725,
-      "step": 60
+      "grad_norm": 0.3045049011707306,
+      "learning_rate": 0.0002838031430723217,
+      "loss": 1.2965,
+      "step": 20
     }
   ],
   "logging_steps": 20,
-  "max_steps": 90,
+  "max_steps": 45,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
@@ -47,7 +33,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.207781792422298e+16,
+  "total_flos": 2.8436606201880576e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0faadcced2522da9b1622441cb44718c4998762acc5067959c807da287000aed
+oid sha256:e26a59f4d05a449a690d742d95dd40bfe537cb91ad5617a10895ea855b3bba8f
 size 5905