Training in progress, step 2000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e5418e608b5dc6cf6036f67b88a21c5a94f9cee4f0ef1f77fda59bfbb020ed
+oid sha256:38b092dfda9074f5157e4bd86a0328d554b8e72a5626a9bc321321cc36f072ce
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a70eb1c7ed1b7b50ca88a0d58b195bbbd43ac81f49980750c437ba42b82ae9
+oid sha256:cd51c2fa4070296203cb870e417cf342a24d6f4daf52267069468a9392c81b1e
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9837d8c5d08d60f65b3e9bc1340820f89ab7a8ce6c532d4ccb9b38bffd601d0
+oid sha256:3b1f479ec258d6cf215c17bde71062cb3b074d6531e1ee5dc85695a575ebeead
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020347811931956918,
-  "global_step": 1500,
+  "epoch": 0.02713041590927589,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,11 +24,17 @@
       "learning_rate": 0.0,
       "loss": 0.0381,
       "step": 1500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0,
+      "loss": 0.0369,
+      "step": 2000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1569332240842752.0,
+  "total_flos": 2091746435530752.0,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct16_21-59-35_1b3a04926831/events.out.tfevents.1665958666.1b3a04926831.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ac275ce1f5cc306eda57deeca0657115b496acbb5f405f829fe3451014f32c4
-size 46084
+oid sha256:04bd9ada616b26937701694f4651f64b06a163cdec854668486234de616027e9
+size 46241