Upload folder using huggingface_hub

Aligned-Lambda_0.01/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc5bd77463f6960a25f5e61acd5747ba018bd70789d97a3072991ec5011c2707
+oid sha256:c2e45c93f2c9a1bc3bbd3debe593d29c4892ad1e22042ba6d421dd6607453334
 size 816784440

Aligned-Lambda_0.01/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355bab60eae9d0d1b496e7f9899ea416cee7589c5dcd28d12b61fecbf5469e27
-size 1633695418
+oid sha256:5929e1de42a6585c3fff66c4a8793456272f5f9c4005370a94e2e66fba0838ee
+size 1621691322

Aligned-Lambda_0.01/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99004c1fd84e57572d9f83eba4950606de6bd58e5072453bb997c850d270379d
+oid sha256:8827c23778eb132d4af0295d85486efedc52cc8e7d8260084819c1f5b168cedd
 size 14244

Aligned-Lambda_0.01/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5d476c12da381846e3dd23747ce593bb7d9068ba7200583b801a8ee542adb9c
+oid sha256:24d1adeb5a474175a1cb9c0c1efabaa9fd87343414b2349dd1c68b0a5ef6eb54
 size 1064

Aligned-Lambda_0.01/trainer_state.json

@@ -3,49 +3,63 @@
   "best_model_checkpoint": null,
   "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 980,
+  "global_step": 1960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 1.4304096334510379,
-      "las": 71.23526844172851,
-      "step": 196,
-      "uas": 80.8380619816674
+      "eval_loss": 1.3433195443616972,
+      "las": 72.15189873417721,
+      "step": 392,
+      "uas": 81.66739415102575
+    },
+    {
+      "epoch": 1.2755102040816326,
+      "grad_norm": 3.317138433456421,
+      "learning_rate": 0.00014897959183673472,
+      "loss": 0.8116,
+      "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.6784026655885909,
-      "las": 71.97730248799651,
-      "step": 392,
-      "uas": 81.09995635093846
+      "eval_loss": 1.6489886807070837,
+      "las": 73.24312527280664,
+      "step": 784,
+      "uas": 81.92928852029682
     },
     {
       "epoch": 2.5510204081632653,
-      "grad_norm": 3.334646701812744,
+      "grad_norm": 2.6405985355377197,
       "learning_rate": 9.79591836734694e-05,
-      "loss": 0.6566,
-      "step": 500
+      "loss": 0.2626,
+      "step": 1000
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.840693520175086,
-      "las": 73.98515931907464,
-      "step": 588,
-      "uas": 82.19118288956787
+      "eval_loss": 1.7524571418762207,
+      "las": 73.15582714971627,
+      "step": 1176,
+      "uas": 82.36577913574858
+    },
+    {
+      "epoch": 3.826530612244898,
+      "grad_norm": 2.158872365951538,
+      "learning_rate": 4.6938775510204086e-05,
+      "loss": 0.1222,
+      "step": 1500
     },
     {
       "epoch": 4.0,
-      "eval_loss": 2.0934243467119007,
-      "las": 75.03273679615889,
-      "step": 784,
-      "uas": 83.23876036665212
+      "eval_loss": 2.07165447043048,
+      "las": 75.46922741161065,
+      "step": 1568,
+      "uas": 84.37363596682671
     }
   ],
   "logging_steps": 500,
-  "max_steps": 980,
+  "max_steps": 1960,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
@@ -62,7 +76,7 @@
     }
   },
   "total_flos": 2.157644595068928e+16,
-  "train_batch_size": 128,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null
 }

Aligned-Lambda_0.01/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af0b7394ee2616ee6e9aafc0bc0af72d9263830be872095653d6f2828f4da29e
+oid sha256:7326d9c14a114d21305aad1da3809b18ba888b85d0a6856daaf707da4ee5a7a0
 size 5432