Training in progress, step 3696, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c7a4d08506415802460518fcb729f0c7fa99115f2453ab74343c19228c7e499
+oid sha256:42c867da4435a602e7276ba7c21ae683ab39d13daad7fc0e5fd657358ebda620
 size 44871152

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c08127b2390de9a85623fb1ea3cde43d846de61c6970c236c162bec79885e54
+oid sha256:b9470208149ac9e2bfb288d43778f6d989ad837fe56f4630894d2046af831eed
 size 23160933

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a31fe9427b5edf19d3cba7a6d0ee5882f2dad28a03649a8428f087ea702adf
+oid sha256:42d95b7b22877f7a7369647179abfb3ef136059915c0ffc1326249b0c778809b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b978e87444ff5a374e8500386ea492ac3d452eb5f59cc18e6decf2b410d3a2
+oid sha256:eb10833e49807d33253596a702add34258667ceb930380e040a68c918c50145e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4791645336336643,
+  "epoch": 1.5135660898945429,
   "eval_steps": 500,
-  "global_step": 3612,
+  "global_step": 3696,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2535,6 +2535,62 @@
       "learning_rate": 3.367055234185191e-05,
       "loss": 0.41823325157165525,
       "step": 3610
+    },
+    {
+      "epoch": 1.4824408723251765,
+      "grad_norm": 0.15578892827033997,
+      "learning_rate": 3.317570108031889e-05,
+      "loss": 0.376281213760376,
+      "step": 3620
+    },
+    {
+      "epoch": 1.486536295689567,
+      "grad_norm": 0.19605852663516998,
+      "learning_rate": 3.268378899615621e-05,
+      "loss": 0.36276628971099856,
+      "step": 3630
+    },
+    {
+      "epoch": 1.4906317190539573,
+      "grad_norm": 0.22443526983261108,
+      "learning_rate": 3.219483772545861e-05,
+      "loss": 0.39970669746398924,
+      "step": 3640
+    },
+    {
+      "epoch": 1.4947271424183475,
+      "grad_norm": 0.20385168492794037,
+      "learning_rate": 3.1708868774093534e-05,
+      "loss": 0.3872653007507324,
+      "step": 3650
+    },
+    {
+      "epoch": 1.4988225657827379,
+      "grad_norm": 0.25204744935035706,
+      "learning_rate": 3.1225903516754964e-05,
+      "loss": 0.38168063163757326,
+      "step": 3660
+    },
+    {
+      "epoch": 1.502917989147128,
+      "grad_norm": 0.2082594484090805,
+      "learning_rate": 3.0745963196023555e-05,
+      "loss": 0.3588885307312012,
+      "step": 3670
+    },
+    {
+      "epoch": 1.5070134125115184,
+      "grad_norm": 0.21136775612831116,
+      "learning_rate": 3.0269068921432032e-05,
+      "loss": 0.39031205177307127,
+      "step": 3680
+    },
+    {
+      "epoch": 1.5111088358759086,
+      "grad_norm": 0.18526561558246613,
+      "learning_rate": 2.9795241668536977e-05,
+      "loss": 0.40956802368164064,
+      "step": 3690
     }
   ],
   "logging_steps": 10,
@@ -2554,7 +2610,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.268303103674614e+17,
+  "total_flos": 6.413772993948795e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null