Training in progress, step 42500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41b6909441f7de13c5d62068c2fcf877da46015ccd10a732f71be64e4c2d409
+oid sha256:593f133c02dc0b40edaff649516e8501c8e64f556b5efae3423c331a3c32593d
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a91551f99ab1fe26122730b0bc1357cda51f770809e413171d16ee620c0a4ea0
+oid sha256:79a2cbd6011075367bb5d9cbbf7c14f484d822c74bdb6b1b994a6f7d1fe6e400
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f20426a61d8ffba768d72e14505bb658c34b86095f56e0b014a4febbc3964541
+oid sha256:29081a0c5c25020eb37cd8894af2e1bf2dd5321cd84e2a6bb48d6cfdb045ad5a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5697387340947937,
-  "global_step": 42000,
+  "epoch": 0.5765213380721127,
+  "global_step": 42500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -510,11 +510,17 @@
       "learning_rate": 0.0,
       "loss": 0.035,
       "step": 42000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0,
+      "loss": 0.0377,
+      "step": 42500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 4.388488201057075e+16,
+  "total_flos": 4.440729620525875e+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:cdc28a5bdb5bdbe9bf94ab995af0c504761cae0bc76fb9a11a999e16d50c23bd
-size 58957
+oid sha256:5dd98f9d7a633585cf5838c3e3c7cc7b3851b6ecfeb7a1af0138e959e327c4f1
+size 59117