Training in progress, step 545, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c96ebe863ff3466272b3ab2c8447b3aca22869b17cb07ec332ff2f920b6b49e
+oid sha256:34dff9b81c5a01b4e58e26af9ff3d94726dcf3fbfd8df467a5b2b3ca91f55c31
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf43448dcb4f245500eca4da91ce018a0ed0cb1998dc0a1fa8423feb43ece1aa
+oid sha256:3f5055a21ea311851fcf516b2248e5a06f15c0402c2bc16301d1bcb3390e648c
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedba96dcac876f28e2be6306578220e85fa67624b620e4b7d8b2b9b53c25230
+oid sha256:0baef92f29724762003fb5a5e60a068b25f0dcaabdd1738999cdd71657bcdcc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8032cf65e0ff4317d8e367449a794976c91fc02ffa62a4c4ec4e22022cce0247
+oid sha256:0c07f2bd0b59249f39d32534072619919b7f36bea7e48a381937d6e08de9e282
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6988029763830476,
+  "epoch": 0.7052733743125202,
   "eval_steps": 386,
-  "global_step": 540,
+  "global_step": 545,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3803,6 +3803,41 @@
       "learning_rate": 9.597407348941865e-05,
       "loss": 0.7678,
       "step": 540
+    },
+    {
+      "epoch": 0.7000970559689421,
+      "grad_norm": 0.7815922498703003,
+      "learning_rate": 9.59578496623617e-05,
+      "loss": 0.8866,
+      "step": 541
+    },
+    {
+      "epoch": 0.7013911355548367,
+      "grad_norm": 0.9351438283920288,
+      "learning_rate": 9.594159458822257e-05,
+      "loss": 0.9607,
+      "step": 542
+    },
+    {
+      "epoch": 0.7026852151407311,
+      "grad_norm": 0.8216230869293213,
+      "learning_rate": 9.592530827805322e-05,
+      "loss": 1.0062,
+      "step": 543
+    },
+    {
+      "epoch": 0.7039792947266257,
+      "grad_norm": 0.8280504941940308,
+      "learning_rate": 9.59089907429268e-05,
+      "loss": 0.8715,
+      "step": 544
+    },
+    {
+      "epoch": 0.7052733743125202,
+      "grad_norm": 0.9679670929908752,
+      "learning_rate": 9.589264199393776e-05,
+      "loss": 1.0543,
+      "step": 545
     }
   ],
   "logging_steps": 1,
@@ -3822,7 +3857,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.036860727145267e+17,
+  "total_flos": 6.092757585729946e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null