Training in progress, step 57500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e05c164d0c7a856fc8fcae002b15c7846d97b2fb1470df8da90e3124384dbc
+oid sha256:34b85f3ede5f6bb7d67b4ab4c08f22803099a91e9386661c8a0fef4e3a3a38bd
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067b6b19e86ccc75ce5436f62316ad3495ef00df86b43bd296e8ea4a12c10c2e
+oid sha256:a0866d3019caabedb035289c3a741ca5c353e2744a19a8962f81974ec76dd996
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bb39a3fe69e19566bb502be6761e7f06c1c7aef0458267e5c05222717c3e82
+oid sha256:55225b8883f4c39dfc4d05bd17ea55a0024a2a40da8987250d1d5df16b8ba275
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7732168534143629,
-  "global_step": 57000,
+  "epoch": 0.7799994573916819,
+  "global_step": 57500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -690,11 +690,17 @@
       "learning_rate": 0.0,
       "loss": 0.0395,
       "step": 57000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0,
+      "loss": 0.039,
+      "step": 57500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 5.955730785121075e+16,
+  "total_flos": 6.007972204589875e+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 sha256:16b7eeee3fa459dfc912b8c4d217a5e8f39f1247e4ee5f79a1c8de7e9b8c9432
-size 63757
+oid sha256:92e095a2484818226a79d557c400fc5f3e65d10c6dca40dded3a912be7c6c881
+size 63917