Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f87a1a364a4c3b074d33d923c337d1857c4daa5fb358a1762ecbe5edd921a65
+oid sha256:6b9b8a5b43dd8d9de9a3ff93b46f59b51e0f503f1bc70951bfb02ea39bc09a63
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:050bb814577fa11d9d1653fc91c52cba6e25bf23abddb567aab775e12c1b1db4
+oid sha256:3a5b8fe8bc5ff747c45994317b6f2e200ec28e7106f8c993157a590d2f3d77bd
 size 5365108834

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d018acbbeceb8f6ded094ffbf67a030bf83c1f54ca6f31bd5f038a52ac85034
+oid sha256:3df16cd49a0b8eec2098a33dc0dadf0a4d79c497ced439bd157f2e6ac5bab8f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8fbc117afd7b27eea894ff76f1b04973418f72f10dadd713f6dfa7c4713012d
+oid sha256:a70f7b5ef6b95e383628d6376d70e07135c11cad9f40dc480e0188454cbb3db6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd2a75ef074977893e3dd803f93d5726cebe2149302e0d0ae3ef1370abb200d
+oid sha256:a34fd3f02bff6d02d805d0bdeac374c0ebc02a92b9a3f16e79223d2bbb10e2b9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f1adac70acfa8a2122e4d3f5566d6d9f1d3efc180b57f0dbc4b7b17090217f
+oid sha256:d927d2976f1a532e1dfa460599187ed9bfa9e5f16421e7569e35526248d81762
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a199cc7b81fba53fabd1b994537c465f58151394382535a6c542ffe0cc02930
+oid sha256:2b32f7bc8829feee7543ba545ec8f492f6a76931d31cd30ffef13d25c9c59f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26852331357768955,
+  "epoch": 0.30688378694593094,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -497,6 +497,76 @@
       "learning_rate": 7.314715359828143e-05,
       "loss": 61.2952,
       "step": 3500
+    },
+    {
+      "epoch": 0.2723593609145137,
+      "grad_norm": 22.69503402709961,
+      "learning_rate": 7.27635415068283e-05,
+      "loss": 61.2368,
+      "step": 3550
+    },
+    {
+      "epoch": 0.2761954082513378,
+      "grad_norm": 22.553903579711914,
+      "learning_rate": 7.237992941537518e-05,
+      "loss": 60.8539,
+      "step": 3600
+    },
+    {
+      "epoch": 0.28003145558816195,
+      "grad_norm": 56.599422454833984,
+      "learning_rate": 7.199631732392206e-05,
+      "loss": 60.8724,
+      "step": 3650
+    },
+    {
+      "epoch": 0.2838675029249861,
+      "grad_norm": 54.43523025512695,
+      "learning_rate": 7.161270523246893e-05,
+      "loss": 61.0066,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2877035502618102,
+      "grad_norm": 21.187387466430664,
+      "learning_rate": 7.12290931410158e-05,
+      "loss": 60.7629,
+      "step": 3750
+    },
+    {
+      "epoch": 0.29153959759863435,
+      "grad_norm": 13.791070938110352,
+      "learning_rate": 7.08454810495627e-05,
+      "loss": 60.6954,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2953756449354585,
+      "grad_norm": 18.809253692626953,
+      "learning_rate": 7.046186895810957e-05,
+      "loss": 60.6031,
+      "step": 3850
+    },
+    {
+      "epoch": 0.2992116922722826,
+      "grad_norm": 12.76346206665039,
+      "learning_rate": 7.007825686665645e-05,
+      "loss": 60.772,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3030477396091068,
+      "grad_norm": 39.48878479003906,
+      "learning_rate": 6.969464477520332e-05,
+      "loss": 60.5169,
+      "step": 3950
+    },
+    {
+      "epoch": 0.30688378694593094,
+      "grad_norm": 61.519203186035156,
+      "learning_rate": 6.93110326837502e-05,
+      "loss": 60.3146,
+      "step": 4000
     }
   ],
   "logging_steps": 50,
@@ -516,7 +586,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.99843679544279e+18,
+  "total_flos": 6.855218432384696e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null