Training in progress, step 9500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:187ff8467f37c4354e252a3aaf52724fe028cb52c99ec5a311cadca2f29ab841
+oid sha256:43b5c2fa25230472627d940460895c534ed27b85ef53b9f0a5466accf948277a
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:815be2ff53522d3ad5e31766833ef0a78648323df7e41b9bfe3dede4ac36cd5f
+oid sha256:3cc8ed763166fa26a00e73bbabd4a9baf358e39b6b90f3aa25bb39e6f1c00e48
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef759f036eac2fd0be45a9f6056b9240256ef10d2c300da948f631ca9d46d61
+oid sha256:de3d79454d3c2da06e5b39360aeff94dce41003d9dbce81c7318e822557d350e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1220868715917415,
-  "global_step": 9000,
+  "epoch": 0.12886947556906048,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,11 +114,17 @@
       "learning_rate": 0.0,
       "loss": 0.036,
       "step": 9000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0,
+      "loss": 0.0378,
+      "step": 9500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 9405545161162752.0,
+  "total_flos": 9927959355850752.0,
   "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:b983a67ed8b4766c0377a238ced5c75c6ab36bc874938b9e234baa518080874b
-size 48439
+oid sha256:3e0d5d0a45f3fa10fe27c7baff9c396fbff7caa089fae631d4f2cd0533446cf8
+size 48596