Training in progress, step 14000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3648ae184284690da64d033408a4e1c928e53021b7bd6df7a313bcef841a388
+oid sha256:9d7595fb3e59ca048769e488207a524c0c61e8cc1c128e8eb72db4ac11b640ae
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a0bf62cb56f8fa94d93d12e8ccff7ba866ba9c1211d68a2a880de0146e02f6
+oid sha256:1afc5c555efbb51ab1a4afaf82a02fa0c21048a22fe3a3905683e67f884c2cfc
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28aae5db0e1ae54faa4522277a82d676fd0ecaf0026b05414b8112197b8aedd1
+oid sha256:9cd0caeb935968f8a2d143b7498492f19a09aa3b9980670a530934169781ab4b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18313030738761224,
-  "global_step": 13500,
+  "epoch": 0.18991291136493121,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -168,11 +168,17 @@
       "learning_rate": 0.0,
       "loss": 0.0408,
       "step": 13500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0,
+      "loss": 0.0378,
+      "step": 14000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.4107272913354752e+16,
+  "total_flos": 1.4629687108042752e+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 sha256:7e435bdac3e08a03bc1e4f3a1225efa47ec23a6bbb1be897518b249022fbfbad
-size 49852
+oid sha256:9fadf2e8ac11ddf24f735ccca846e748c90810786db2d10b32e356ddd9087a74
+size 50009