Training in progress, step 21000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3702274d7a95faceafcbea8cd0e5dafc985c359de6548b7e487c7e90269244b
+oid sha256:63b3518d5a70a6d701bb25281aa47d913e0c849d8637426b6cd1fceaf936c70f
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9e38fcd0287499ca5156d923b74bd90c56d35ba790bf260e9abbd0b25045c97
+oid sha256:7cbbefcbc874e7429c80b4d4fc60621b7eea83de7f4a25b96ca3b009f8ffc31f
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649bbdfbeec85216131a421de183149588599d4cc591288a3ee666b21b788817
+oid sha256:4610c48f288ccf6972031e091d182e5cdfaa284c08cb662e253c62ab351d758e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.27808676307007785,
-  "global_step": 20500,
+  "epoch": 0.28486936704739685,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,11 +252,17 @@
       "learning_rate": 0.0,
       "loss": 0.0369,
       "step": 20500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0,
+      "loss": 0.0397,
+      "step": 21000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.142107163898675e+16,
+  "total_flos": 2.194348583367475e+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:f52a2093c17d9cc5f076b7063f200b158556bc51fbe04501bfda39de9eb435af
-size 52077
+oid sha256:702aad273a367730813acf09521e7fb5b05c284757fc66d44849f5b6b88d956a
+size 52237