Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:196f0ec635e698bf3dd473c9d3c6b5326a1e64ddaf8c97fcb3a34e3e68a134ba
+oid sha256:2e09283677180e00d442fe3b4ab19dcf7ff5412ba2b7458854f7b79bfeb5bb28
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d25b483c4c9ebc2b09cdfd9b9dc2ff7f3400985c3c30fc3c7f66893548c477db
+oid sha256:0a0ebf03042fa02beb3e8266a31815f5d456796b309a08eb95940ed1ba6323de
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7c2c6889489e88d23048787444b150bfd24d0342706104cf2a0e3719fcc7d3
+oid sha256:38c24bcf45e53a4cc78a87451f451897ccd30442038e8997c70341d3d503f861
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d23290f09d2127ca8198403a77e319b783a12d8fcf81756f51ef5695c491adbd
+oid sha256:1ac41801a97e47677175a43c4edf9de5a5d83090675917774e24b53c8664713d
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b911940bdf86ae7e1f217f9bf9f400780319e842159e75db8115406aa532903a
+oid sha256:2953e888fcadc989fed40774279f6b8f341c37014ceb7f5076d3ac543f58ccb8
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00233722676358367,
+  "epoch": 0.0035058401453755047,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,146 @@
       "learning_rate": 0.00019999999516049713,
       "loss": 41.33089599609375,
       "step": 400
+    },
+    {
+      "epoch": 0.0023956574326732616,
+      "grad_norm": 328746.15625,
+      "learning_rate": 0.00019999999413344217,
+      "loss": 41.90570983886719,
+      "step": 410
+    },
+    {
+      "epoch": 0.0024540881017628535,
+      "grad_norm": 6136.6533203125,
+      "learning_rate": 0.0001999999930076319,
+      "loss": 41.43394165039062,
+      "step": 420
+    },
+    {
+      "epoch": 0.002512518770852445,
+      "grad_norm": 17034646.0,
+      "learning_rate": 0.00019999999178306637,
+      "loss": 42.87438049316406,
+      "step": 430
+    },
+    {
+      "epoch": 0.0025709494399420367,
+      "grad_norm": 629740.0625,
+      "learning_rate": 0.00019999999045974555,
+      "loss": 43.224603271484376,
+      "step": 440
+    },
+    {
+      "epoch": 0.0026293801090316285,
+      "grad_norm": 38.82156753540039,
+      "learning_rate": 0.00019999998903766944,
+      "loss": 43.59588623046875,
+      "step": 450
+    },
+    {
+      "epoch": 0.0026878107781212203,
+      "grad_norm": 62.95846176147461,
+      "learning_rate": 0.00019999998751683804,
+      "loss": 42.37510681152344,
+      "step": 460
+    },
+    {
+      "epoch": 0.002746241447210812,
+      "grad_norm": 263.49127197265625,
+      "learning_rate": 0.0001999999858972514,
+      "loss": 39.93461608886719,
+      "step": 470
+    },
+    {
+      "epoch": 0.0028046721163004036,
+      "grad_norm": 5088.94482421875,
+      "learning_rate": 0.00019999998417890945,
+      "loss": 40.548788452148436,
+      "step": 480
+    },
+    {
+      "epoch": 0.0028631027853899954,
+      "grad_norm": 31.414766311645508,
+      "learning_rate": 0.00019999998236181225,
+      "loss": 40.34054260253906,
+      "step": 490
+    },
+    {
+      "epoch": 0.0029215334544795872,
+      "grad_norm": 27.641599655151367,
+      "learning_rate": 0.0001999999804459598,
+      "loss": 40.16330261230469,
+      "step": 500
+    },
+    {
+      "epoch": 0.002979964123569179,
+      "grad_norm": 35.540000915527344,
+      "learning_rate": 0.00019999997843135202,
+      "loss": 38.760552978515626,
+      "step": 510
+    },
+    {
+      "epoch": 0.003038394792658771,
+      "grad_norm": 34.06961441040039,
+      "learning_rate": 0.00019999997631798904,
+      "loss": 38.795037841796876,
+      "step": 520
+    },
+    {
+      "epoch": 0.0030968254617483623,
+      "grad_norm": 33.19498062133789,
+      "learning_rate": 0.00019999997410587078,
+      "loss": 39.20487976074219,
+      "step": 530
+    },
+    {
+      "epoch": 0.003155256130837954,
+      "grad_norm": 42.77100372314453,
+      "learning_rate": 0.00019999997179499722,
+      "loss": 38.75799560546875,
+      "step": 540
+    },
+    {
+      "epoch": 0.003213686799927546,
+      "grad_norm": 45.82843017578125,
+      "learning_rate": 0.0001999999693853684,
+      "loss": 38.78368225097656,
+      "step": 550
+    },
+    {
+      "epoch": 0.003272117469017138,
+      "grad_norm": 36.43661117553711,
+      "learning_rate": 0.00019999996687698437,
+      "loss": 38.06520385742188,
+      "step": 560
+    },
+    {
+      "epoch": 0.0033305481381067296,
+      "grad_norm": 1284758.625,
+      "learning_rate": 0.00019999996426984504,
+      "loss": 37.71627197265625,
+      "step": 570
+    },
+    {
+      "epoch": 0.003388978807196321,
+      "grad_norm": 9164.9052734375,
+      "learning_rate": 0.0001999999615639505,
+      "loss": 38.672061157226565,
+      "step": 580
+    },
+    {
+      "epoch": 0.003447409476285913,
+      "grad_norm": 50178.6484375,
+      "learning_rate": 0.00019999995875930068,
+      "loss": 38.9878662109375,
+      "step": 590
+    },
+    {
+      "epoch": 0.0035058401453755047,
+      "grad_norm": 38.927513122558594,
+      "learning_rate": 0.00019999995585589562,
+      "loss": 39.09903564453125,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -307,7 +447,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3201536247736320.0,
+  "total_flos": 4809381153761280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null