Training in progress, step 58000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b85f3ede5f6bb7d67b4ab4c08f22803099a91e9386661c8a0fef4e3a3a38bd
+oid sha256:6852d2448a4ca58782272d1e6b3a903fccd6f56b1c886945c6bc00e23e47ccf5
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0866d3019caabedb035289c3a741ca5c353e2744a19a8962f81974ec76dd996
+oid sha256:b0351d584090f89b3a4b18c34eb92c06a9443712751f3ba46cdea37a49bbf393
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55225b8883f4c39dfc4d05bd17ea55a0024a2a40da8987250d1d5df16b8ba275
+oid sha256:b880fa41c721c57220381b9eee2e090a50277bad3913211285fc679f9012ba88
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7799994573916819,
-  "global_step": 57500,
+  "epoch": 0.7867820613690008,
+  "global_step": 58000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -696,11 +696,17 @@
       "learning_rate": 0.0,
       "loss": 0.039,
       "step": 57500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0,
+      "loss": 0.0363,
+      "step": 58000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 6.007972204589875e+16,
+  "total_flos": 6.060213624058675e+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 sha256:92e095a2484818226a79d557c400fc5f3e65d10c6dca40dded3a912be7c6c881
-size 63917
+oid sha256:3b9e33b20d401c772ba5afc789cced24cad455d5429e45e2be05d818755fba5a
+size 64077