Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a92c66cf259a5bdf3348933aa5549869d66af9009a06edcb37ce9c9b6e699b
+oid sha256:74d751c0072f366511a4a43897212ef30910d8da6a0b0a925242500a3ec19196
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10391a5de0ba94ba223b8d9bff24f95f8b5dc2c9f96f88899b4b5ef1b6206644
+oid sha256:2d5d2c25d3143e85c974ac583b8ef8fa9e39b1f9e823fbbbc060e0fcf7f92dc4
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5e7dbcde59188700fb306e82bba45711bac385d3676a5234e58c9c458be763
+oid sha256:ddd8a26aead479323d35b6a9a3554c78e321900172f575dcf4e70b8541b00630
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2645215551154399,
-  "global_step": 19500,
+  "epoch": 0.2713041590927589,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -240,11 +240,17 @@
       "learning_rate": 0.0,
       "loss": 0.0361,
       "step": 19500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0,
+      "loss": 0.0371,
+      "step": 20000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.037624324961075e+16,
+  "total_flos": 2.089865744429875e+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 sha256:936afe7bc1da88f784820cb7a6999706f54c32246b6ac03bccab2e5f884dfab3
-size 51757
+oid sha256:191ab5c0419b06b4bc1b4306a37220c5a615b7bfce5c1570fba99ac63a87c5b6
+size 51917