Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b5c2fa25230472627d940460895c534ed27b85ef53b9f0a5466accf948277a
+oid sha256:9993b4aee4707a90fc1f27543cac0e203e28ba1768fb63012607990b51f37b40
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc8ed763166fa26a00e73bbabd4a9baf358e39b6b90f3aa25bb39e6f1c00e48
+oid sha256:7af45039fde02815db8a6ba3a9ec303d7ee704a6c7d63838f9d556684ec06d78
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3d79454d3c2da06e5b39360aeff94dce41003d9dbce81c7318e822557d350e
+oid sha256:8500ebc53a3a1be76459cb51778376911ed2048b944c4b1881690163a47d4171
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12886947556906048,
-  "global_step": 9500,
+  "epoch": 0.13565207954637945,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -120,11 +120,17 @@
       "learning_rate": 0.0,
       "loss": 0.0378,
       "step": 9500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0,
+      "loss": 0.0362,
+      "step": 10000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 9927959355850752.0,
+  "total_flos": 1.0450373550538752e+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 sha256:3e0d5d0a45f3fa10fe27c7baff9c396fbff7caa089fae631d4f2cd0533446cf8
-size 48596
+oid sha256:f7a5c9a081626414899a8ccec01263c8937d70e3479a27cf4d02c27fe1618bf5
+size 48753