Training in progress, step 44000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e012daaa9bc5bf2de4140a645c67740428ce9d82b2315fa6bb23f770694a5c8
+oid sha256:91a58c25c964c876219d163ee743fc33ab6b82acc20aeb75efc653b0fffeb242
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae81fd670707f5179576fcf288b6a9ab62657364cd68b0dc32f64e4d5cb98d55
+oid sha256:a18296bc1b9671a3aca1485e1fd2afac4ea2f4dc0e32dc40355e2778dfacd2c0
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369bd15595b57c84596d05932951741c1832bc1a8844c3a3b7d37f256cff4dc4
+oid sha256:7d84fc13ad3dac46c5030905525144950b6071e4acfbfbc31c734cb586f14915
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5900865460267506,
-  "global_step": 43500,
+  "epoch": 0.5968691500040696,
+  "global_step": 44000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -528,11 +528,17 @@
       "learning_rate": 0.0,
       "loss": 0.0389,
       "step": 43500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0,
+      "loss": 0.039,
+      "step": 44000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 4.545212459463475e+16,
+  "total_flos": 4.597453878932275e+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 sha256:3df7aca8ee6dd965a13f86844c4f097d66ca932ed4b53d9905dab87b40ddbfeb
-size 59437
+oid sha256:55c72240b5283af4107ab57b80aefe7738234418b449e01ab0f95a3cdee6503b
+size 59597