Training in progress, step 95500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4c96364fae40b8430cff8f542d1dc7f8d0e243fbfe8427e5a8797b63e4f488
+oid sha256:e2aaa8c3f78fe5e306cf3159cbc4a4934f66043f8ab07966b8573bdaf952ca35
 size 4549998883

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6891a038b7c56b7e1cb89705c957e63cf79327cb95376b8afac6d036902342e3
-size 14439
+oid sha256:df2d99b25b78c99592aa89dc7507b4fe924199bf802c44f2dea23da0d387e186
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19562c4fc393047cbb898ac02b9797e34e77a50183e107e566552468b0f4d3b0
+oid sha256:c839bb9b3976e2a74fb7960c7d0074531497be9f73c1575558c0e913eab98462
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.838052556528824,
-  "global_step": 95000,
+  "epoch": 4.863515991036871,
+  "global_step": 95500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1146,11 +1146,17 @@
       "learning_rate": 1.5170554084334896e-05,
       "loss": 0.0,
       "step": 95000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 1.514509064982685e-05,
+      "loss": 0.0,
+      "step": 95500
     }
   ],
   "max_steps": 392720,
   "num_train_epochs": 20,
-  "total_flos": 3.6326738837643264e+17,
+  "total_flos": 3.651828436827341e+17,
   "trial_name": null,
   "trial_params": null
 }