Training in progress, step 5000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20fc434684e1c220dded60a920c7c3e830ddf7a8e90d46fa95a04dab4f98aae
+oid sha256:cdd321134135383b64ea7b8e95b5a66f7a77fca288a6fb5c138a268d854a7e53
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3c9145f761afa6aa2f997a1915883807b35a6937675ab3074cea5a3943af18
+oid sha256:2faa6f41a415b4ad42a0abbcf44a851887f2691bd4f70d3892be1b3003efba9c
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af85a35a5a3e291c8ebc2c37560f3c094f4ca4bcccdfda5e66c17755083a1033
+oid sha256:0a8fcb288ac1e758409258c3d51315b4f7db43a6ace374e544d5b4264c6980a4
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06104343579587075,
-  "global_step": 4500,
+  "epoch": 0.06782603977318973,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,11 +60,17 @@
       "learning_rate": 0.0,
       "loss": 0.0357,
       "step": 4500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0,
+      "loss": 0.0388,
+      "step": 5000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 4703817408970752.0,
+  "total_flos": 5226231603658752.0,
   "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 sha256:3b32a35fa1fecb0e76157e7cff746e04dacf1aa1c531fe5d3bd0c48512db8c65
-size 47026
+oid sha256:fc35396fa9bbdc4d15326289ef3de4732e7a859b94cf1b977f69ec6040a94385
+size 47183