Training in progress, step 61000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b66cd8b87197478fe70aefda272fe9b6c81878745094e94f52d4e760118d6c4
+oid sha256:cbd3aa4835eda866362ab4dcdad437c3161c2671b078d48f40d0b466a306faa8
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d458060a0eaae0b82eb270e7216053eadf0d13442f0eedf6861fff59cd54a324
+oid sha256:8ec9980e0e4d49a11c107c88863e01c8ed67819546b646e61e0a1dcaaf5d9232
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f443eff8e9a5f695c18d85849550699925a072bd5e5008cfe067f387353cf7d
+oid sha256:1870e5202c053630af17ca6753d7633957238bdb562ccf838a946b0036bd987c
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8206950812555956,
-  "global_step": 60500,
+  "epoch": 0.8274776852329147,
+  "global_step": 61000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -732,11 +732,17 @@
       "learning_rate": 0.0,
       "loss": 0.0381,
       "step": 60500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0,
+      "loss": 0.0389,
+      "step": 61000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 6.321420721402675e+16,
+  "total_flos": 6.373662140871475e+16,
   "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 sha256:19509998b63d3d1355830a49cfd49d2922665080bd1e6d8228ba66c8eaa1a7ae
-size 64877
+oid sha256:679a87613e5155f8f4ff03ef619ee305f77511e9dd483a0863578a08e61cf0a7
+size 65037