Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8153813283c4389ef5a9863dfbf03bd90de9af06723c2ed7469560d2f6cb9016
+oid sha256:75a0187432d05655fa95e9e4af04e889f2b84a4214d4995b5dcbc3829f6fa995
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3c6d028cc61eb16c10cfeb96ae472b416bf61c2430d616409a7e075447463c
+oid sha256:7eb7dc038fae5860bd92fb49fcb23e213f7099623915ac6963ae71d0e53c7159
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b21a8df05d6c8e0e6fd608ca76fd60fcfc2fde098551b903447e393817425942
+oid sha256:e2f6e8ef6ff0cccff7f602f9c9f7831d1edbb8062fe6f8d796324be0b7257b7f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3da069d23e3fc76f1f7013dd495a2b0f4544633e580b179d33500b4d99b2575
+oid sha256:6be5c125c7805acd88ceb3e79bd43e0a5bfe5ffe9cebeb5d64fd8beda77909cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23333333333333334,
+  "epoch": 0.26666666666666666,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -252,6 +252,41 @@
       "learning_rate": 1.8445333333333334e-05,
       "loss": 0.0726,
       "step": 3500
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.27142712473869324,
+      "learning_rate": 1.840088888888889e-05,
+      "loss": 0.0763,
+      "step": 3600
+    },
+    {
+      "epoch": 0.24666666666666667,
+      "grad_norm": 0.3764208257198334,
+      "learning_rate": 1.8356444444444445e-05,
+      "loss": 0.0816,
+      "step": 3700
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.2864600718021393,
+      "learning_rate": 1.8312e-05,
+      "loss": 0.0707,
+      "step": 3800
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.2760820686817169,
+      "learning_rate": 1.8267555555555555e-05,
+      "loss": 0.0759,
+      "step": 3900
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.14416909217834473,
+      "learning_rate": 1.8223111111111114e-05,
+      "loss": 0.0621,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -271,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8525410467840000.0,
+  "total_flos": 9743326248960000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null