Training in progress, step 107780

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1777e896d61479cc9ed84fe5afa72fd7ffbbf7490858dfb4e9f222bbc07ab423
+oid sha256:66bee3b0a57e429d1e41b17774ce1e4cb53868e59ca3e96b92b478a8cab1502d
 size 133845253

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e522821ed97932d589ba0c4ad5a8a58fad9d75c2eda4f4e237c5b163b96dbf
+oid sha256:1340a29af6f65337d57c67d690c4635184e349901956fb2a74c845e1dc398013
 size 266267309

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:601b0f5e6b3cf18abc0aa01c7adf3b860d3e67ac728b814bc1c64b0ee5196942
+oid sha256:6e83ad7ffa8f84644ff6a66224648e7531293eca5c65b342d7753e1d77ea83e1
 size 14511

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58e5109c88232419418f6892fe1d47612449af820166625fcf4b6426cc02819b
+oid sha256:19571ad9ed8aa394d3dfe767a357a80c87260a1219f15b33b1e18fd6b335a086
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.75,
-  "global_step": 102391,
+  "epoch": 5.0,
+  "global_step": 107780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1262,11 +1262,77 @@
       "learning_rate": 1.3679583596214512e-06,
       "loss": 0.0946,
       "step": 102000
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 1.2496228613843015e-06,
+      "loss": 0.0966,
+      "step": 102500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.1312873631471517e-06,
+      "loss": 0.0905,
+      "step": 103000
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 1.0129518649100018e-06,
+      "loss": 0.0961,
+      "step": 103500
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 8.946163666728521e-07,
+      "loss": 0.0922,
+      "step": 104000
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 7.762808684357024e-07,
+      "loss": 0.0922,
+      "step": 104500
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 6.579453701985527e-07,
+      "loss": 0.0946,
+      "step": 105000
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 5.396098719614028e-07,
+      "loss": 0.0903,
+      "step": 105500
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 4.2127437372425313e-07,
+      "loss": 0.0938,
+      "step": 106000
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 3.029388754871034e-07,
+      "loss": 0.0959,
+      "step": 106500
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 1.8460337724995362e-07,
+      "loss": 0.0952,
+      "step": 107000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 6.626787901280386e-08,
+      "loss": 0.0936,
+      "step": 107500
     }
   ],
   "max_steps": 107780,
   "num_train_epochs": 5,
-  "total_flos": 1.7361002410889134e+18,
+  "total_flos": 1.8274692319096934e+18,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e522821ed97932d589ba0c4ad5a8a58fad9d75c2eda4f4e237c5b163b96dbf
+oid sha256:1340a29af6f65337d57c67d690c4635184e349901956fb2a74c845e1dc398013
 size 266267309