Training in progress, step 43000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:593f133c02dc0b40edaff649516e8501c8e64f556b5efae3423c331a3c32593d
+oid sha256:359a05257c508dcfff95aded5b4018be1e85ffab63634771533744dc2e7a2123
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a2cbd6011075367bb5d9cbbf7c14f484d822c74bdb6b1b994a6f7d1fe6e400
+oid sha256:ff5fc7b81879a73dd8208d45aa09095a474fc709a50fc5058242a5c0e802c418
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29081a0c5c25020eb37cd8894af2e1bf2dd5321cd84e2a6bb48d6cfdb045ad5a
+oid sha256:753db2e9a5104fefeee7a440bb756f3ca24935ac1c74bf08693046a8c598bc56
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5765213380721127,
-  "global_step": 42500,
+  "epoch": 0.5833039420494316,
+  "global_step": 43000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -516,11 +516,17 @@
       "learning_rate": 0.0,
       "loss": 0.0377,
       "step": 42500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0,
+      "loss": 0.0391,
+      "step": 43000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 4.440729620525875e+16,
+  "total_flos": 4.492971039994675e+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 sha256:5dd98f9d7a633585cf5838c3e3c7cc7b3851b6ecfeb7a1af0138e959e327c4f1
-size 59117
+oid sha256:5e1ba4b55baaa4152949f94b8aa1fbbe2c69c733e1aa979f4c0fe06b0ef71845
+size 59277