Training in progress, step 38000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb4b42822185ff6de3a099bd12e446126b1f17c7c250ddabf54e56243c862a1
+oid sha256:0ee0d129a625293adc4406fc31eadf9b340d55aea1a185de8708df582a498366
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50b235de4cfd799bb024b69eea169055f02fe1cecc5bcce10a2da6744a87c7c
+oid sha256:86c5761e3f2cc6e5e195f5c2476359faf1d361098277a9e221c6bd613d0c647e
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec9329dc974fda8dadf5c0c0a430ff62cd423eaa0e3ae231403d5ad36af450c5
+oid sha256:0e026a9b93a89f560dcb613090989590e8b9684616c39a7c9e924f056ae4e6e8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5086952982989229,
-  "global_step": 37500,
+  "epoch": 0.5154779022762419,
+  "global_step": 38000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -456,11 +456,17 @@
       "learning_rate": 0.0,
       "loss": 0.039,
       "step": 37500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0,
+      "loss": 0.0397,
+      "step": 38000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 3.918315425837875e+16,
+  "total_flos": 3.970556845306675e+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 sha256:59a414ff563f273bf9a0e9cd59e892cab70ece1ce9798491a50b15324e7a9780
-size 57517
+oid sha256:a8e76c2214ec7105f7f3b80cd91ae785a8f4996738a65eddffca76ae3264df9a
+size 57677