Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75a0187432d05655fa95e9e4af04e889f2b84a4214d4995b5dcbc3829f6fa995
+oid sha256:8fdbb9af804d15f5110973d90186ec84defa2a665a8482fd83c11a269501602d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb7dc038fae5860bd92fb49fcb23e213f7099623915ac6963ae71d0e53c7159
+oid sha256:6e8eed0cff93a66dd9f7dc35bf13769c84be7bd70a4333fe001f86cc9ee212ba
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f6e8ef6ff0cccff7f602f9c9f7831d1edbb8062fe6f8d796324be0b7257b7f
+oid sha256:2ca0d52bc1b71ba08e7156c2b45d758a196d38988c6eda67b4df0e9d832fe78c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be5c125c7805acd88ceb3e79bd43e0a5bfe5ffe9cebeb5d64fd8beda77909cd
+oid sha256:574db7da084c9454e4a06ea3487f7cdcb4dd46faa4038c9a6b4a085fb43bd4b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26666666666666666,
+  "epoch": 0.3,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,41 @@
       "learning_rate": 1.8223111111111114e-05,
       "loss": 0.0621,
       "step": 4000
+    },
+    {
+      "epoch": 0.2733333333333333,
+      "grad_norm": 0.2718330919742584,
+      "learning_rate": 1.817866666666667e-05,
+      "loss": 0.0736,
+      "step": 4100
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.25370103120803833,
+      "learning_rate": 1.8134222222222224e-05,
+      "loss": 0.0758,
+      "step": 4200
+    },
+    {
+      "epoch": 0.2866666666666667,
+      "grad_norm": 0.1705348938703537,
+      "learning_rate": 1.808977777777778e-05,
+      "loss": 0.0723,
+      "step": 4300
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.152600958943367,
+      "learning_rate": 1.8045333333333335e-05,
+      "loss": 0.0671,
+      "step": 4400
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.24814434349536896,
+      "learning_rate": 1.800088888888889e-05,
+      "loss": 0.0752,
+      "step": 4500
     }
   ],
   "logging_steps": 100,
@@ -306,7 +341,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9743326248960000.0,
+  "total_flos": 1.096124203008e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null