Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766f39cf2aa03b06ce0544465f23f42d796935dadd6619740980847fa379f296
+oid sha256:101dd85060f77fe6ab87ec8a72c51f4493aee0cd0bb19e810811a805ed98aad4
 size 579824888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad971091ff30bc232ebf11b75c27a84c1325701e13bc4a6246fcc2d26e336bb4
+oid sha256:54ba4d04e29776946b001a6f6920fd7c30f03e9863aff3ad6b551f23caea0b60
 size 1159794763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232768e06875e03d77948d18a567c6062bc64ee278f8d41937981a714e6a2d53
+oid sha256:ee44ef43900d0428f565a6ab0fb42d678379f6436ece4e4a6239f399d8eada96
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5343924a6852b4d8168211c95036da6881053e86461e5c21fd663c6b1f4a7b
+oid sha256:bf7545cbdf140980776a20b719262192e6070ee27cb1c9a27c369c20b3d411df
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.52,
+  "epoch": 0.56,
   "eval_steps": 1000,
-  "global_step": 26000,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2062,6 +2062,164 @@
       "eval_samples_per_second": 297.843,
       "eval_steps_per_second": 18.721,
       "step": 26000
+    },
+    {
+      "epoch": 0.522,
+      "grad_norm": 0.14482583105564117,
+      "learning_rate": 0.0004677556825558636,
+      "loss": 3.380513000488281,
+      "step": 26100
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 0.1740926057100296,
+      "learning_rate": 0.0004646118569767831,
+      "loss": 3.3777206420898436,
+      "step": 26200
+    },
+    {
+      "epoch": 0.526,
+      "grad_norm": 0.13794536888599396,
+      "learning_rate": 0.00046146943688121875,
+      "loss": 3.3788577270507814,
+      "step": 26300
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 0.14884917438030243,
+      "learning_rate": 0.00045832854707424044,
+      "loss": 3.372579345703125,
+      "step": 26400
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.14392748475074768,
+      "learning_rate": 0.0004551893123001399,
+      "loss": 3.369126281738281,
+      "step": 26500
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 0.1415095329284668,
+      "learning_rate": 0.0004520518572374776,
+      "loss": 3.4073892211914063,
+      "step": 26600
+    },
+    {
+      "epoch": 0.534,
+      "grad_norm": 0.17241106927394867,
+      "learning_rate": 0.00044891630649413096,
+      "loss": 3.3727621459960937,
+      "step": 26700
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 0.1402324140071869,
+      "learning_rate": 0.0004457827846023443,
+      "loss": 3.3563668823242185,
+      "step": 26800
+    },
+    {
+      "epoch": 0.538,
+      "grad_norm": 0.13993528485298157,
+      "learning_rate": 0.0004426514160137837,
+      "loss": 3.36125244140625,
+      "step": 26900
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.14961598813533783,
+      "learning_rate": 0.000439522325094595,
+      "loss": 3.360479431152344,
+      "step": 27000
+    },
+    {
+      "epoch": 0.54,
+      "eval_accuracy": 0.37769785985999915,
+      "eval_loss": 3.3393123149871826,
+      "eval_runtime": 6.2827,
+      "eval_samples_per_second": 308.945,
+      "eval_steps_per_second": 19.418,
+      "step": 27000
+    },
+    {
+      "epoch": 0.542,
+      "grad_norm": 0.12927019596099854,
+      "learning_rate": 0.0004363956361204626,
+      "loss": 3.3508065795898436,
+      "step": 27100
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 0.15256398916244507,
+      "learning_rate": 0.0004332714732716751,
+      "loss": 3.357308044433594,
+      "step": 27200
+    },
+    {
+      "epoch": 0.546,
+      "grad_norm": 0.13779006898403168,
+      "learning_rate": 0.0004301499606281931,
+      "loss": 3.3775006103515626,
+      "step": 27300
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 0.1694018542766571,
+      "learning_rate": 0.00042703122216472094,
+      "loss": 3.3572964477539062,
+      "step": 27400
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.1522066593170166,
+      "learning_rate": 0.00042391538174578263,
+      "loss": 3.3765057373046874,
+      "step": 27500
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 0.14023618400096893,
+      "learning_rate": 0.0004208025631208036,
+      "loss": 3.355110778808594,
+      "step": 27600
+    },
+    {
+      "epoch": 0.554,
+      "grad_norm": 0.14079532027244568,
+      "learning_rate": 0.0004176928899191941,
+      "loss": 3.3566073608398437,
+      "step": 27700
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 0.14286920428276062,
+      "learning_rate": 0.0004145864856454404,
+      "loss": 3.3700027465820312,
+      "step": 27800
+    },
+    {
+      "epoch": 0.558,
+      "grad_norm": 0.13522571325302124,
+      "learning_rate": 0.00041148347367419983,
+      "loss": 3.3883221435546873,
+      "step": 27900
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.18117037415504456,
+      "learning_rate": 0.00040838397724539947,
+      "loss": 3.3707275390625,
+      "step": 28000
+    },
+    {
+      "epoch": 0.56,
+      "eval_accuracy": 0.3787030511639349,
+      "eval_loss": 3.330246925354004,
+      "eval_runtime": 6.6261,
+      "eval_samples_per_second": 292.932,
+      "eval_steps_per_second": 18.412,
+      "step": 28000
     }
   ],
   "logging_steps": 100,
@@ -2081,7 +2239,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.01918982537216e+18,
+  "total_flos": 1.09758904270848e+18,
   "train_batch_size": 120,
   "trial_name": null,
   "trial_params": null