Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10500d6936226928862f57d6cd94f4497878f0b1bb025edca400a181e583d0e9
+oid sha256:26d8f5a8a6c2b2142e1a897b44d8d10c4b31cd9bfb6af9a2f209cb1c664219db
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60868e053ffcd706a9db40ce51977df10a098297affcd57b93e91fffd802ca7e
+oid sha256:d5e3926040695ffd36b68b04adaa45e63e11c719919bb0b1c4e2bd27ee1e14c0
 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": 58.981,
       "step": 3500
+    },
+    {
+      "epoch": 0.2723593609145137,
+      "grad_norm": 51.17266082763672,
+      "learning_rate": 7.27635415068283e-05,
+      "loss": 58.9879,
+      "step": 3550
+    },
+    {
+      "epoch": 0.2761954082513378,
+      "grad_norm": 48.200164794921875,
+      "learning_rate": 7.237992941537518e-05,
+      "loss": 58.5352,
+      "step": 3600
+    },
+    {
+      "epoch": 0.28003145558816195,
+      "grad_norm": 37.883766174316406,
+      "learning_rate": 7.199631732392206e-05,
+      "loss": 58.6675,
+      "step": 3650
+    },
+    {
+      "epoch": 0.2838675029249861,
+      "grad_norm": 45.00859832763672,
+      "learning_rate": 7.161270523246893e-05,
+      "loss": 58.7792,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2877035502618102,
+      "grad_norm": 26.977285385131836,
+      "learning_rate": 7.12290931410158e-05,
+      "loss": 58.4862,
+      "step": 3750
+    },
+    {
+      "epoch": 0.29153959759863435,
+      "grad_norm": 38.32195281982422,
+      "learning_rate": 7.08454810495627e-05,
+      "loss": 58.3661,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2953756449354585,
+      "grad_norm": 63.87961196899414,
+      "learning_rate": 7.046186895810957e-05,
+      "loss": 58.25,
+      "step": 3850
+    },
+    {
+      "epoch": 0.2992116922722826,
+      "grad_norm": 35.58587646484375,
+      "learning_rate": 7.007825686665645e-05,
+      "loss": 58.3304,
+      "step": 3900
+    },
+    {
+      "epoch": 0.3030477396091068,
+      "grad_norm": 60.112632751464844,
+      "learning_rate": 6.969464477520332e-05,
+      "loss": 58.1747,
+      "step": 3950
+    },
+    {
+      "epoch": 0.30688378694593094,
+      "grad_norm": 41.148353576660156,
+      "learning_rate": 6.93110326837502e-05,
+      "loss": 57.8954,
+      "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