Training in progress, step 1500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f892f103723425ad14b38db6edb9aa4c6ee7b516549322cb183cac27a585cd69
+oid sha256:6524a89004f895ebb40c163fb000120939b69136f746115239717cf901755d3e
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67301da5c57c64e98efb14ecf294eab870a5a0a4e3004242e9e40668fa0a2e5b
+oid sha256:5d455c6c55f12ede83a7170a5f2cf7f7d3b794ba66628ebfc430a5dcafdf7926
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b76f2c1c39522b8c5498459c7e9113970762ae114e0e7f40cb836dc8984719
+oid sha256:aab1a00b4d9b32049303ef4af942ff14a8e5e82dd0b87eb74624773875cbfec6
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f50e3306f3c9c6adbe0dedc2fd97abc1244264dc24b6104e59c24eb9f7554450
+oid sha256:6c8e5122a2511d9698fdb40ad4c5e9dba86073caa4528bb29f64b0c2db36211e
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34913556519b4f5ff6ee3a99f05254dcc26ba55b30a512aa1a424a8163b3da18
+oid sha256:53292cfa81423e3fba0ca0eaeede4a19951968275bcc1cc60812a11cce946cc0
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a622b9945abec665a29f44d02e606edae0902d7c858f03471fc439ffb78c8bd
+oid sha256:01fd44eef4683e280cb94994fe3453eb9c8fba26a61d8293ecd10ee8d79014a0
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2db92a63182f2a8e74f6f8ba8a49330276140c1b1e68be053bb7958ff88aa05
+oid sha256:767578033895723160df2c072f5a3b9649854a2a5038024ad00d035a11ada228
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1dfcf1def0fab315df7efa0e82058c17d657f7d1e24a0863e66bae75531cfbf
+oid sha256:73a2c821a372ebcef6a65ed2212135f44619cf13f3a82318285c44a3c0e93134
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d41bf7a36b12290d0668a17db5481f4d9bac1fb69402aa3433a16ac534f0d78
+oid sha256:31bc6ada37be16d9b94ba875e83129ab0a1becdb21d7e0dd9569e43988e69d1a
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f52f2981f6a10064b9d54b23539047132389d938a031ae78cc1e296c5a1748
+oid sha256:5c264b2b347d872eccfee31d56f07535129be708a2786a1f9335f4447665abd9
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d5d1546bfb69154c942dddcbbbdf46b8cffa1900144b2ba63a8323dfd94157b
+oid sha256:08b58c9897520381532a491e6de506782301d0c07a05fa690317ee93b73255c6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3333333333333333,
+  "epoch": 0.5,
   "eval_steps": 250,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -184,6 +184,94 @@
       "eval_samples_per_second": 17.845,
       "eval_steps_per_second": 0.571,
       "step": 1000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 428.2043151855469,
+      "learning_rate": 0.00030957412906164035,
+      "loss": 1789.57328125,
+      "step": 1050
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 514.5044555664062,
+      "learning_rate": 0.0003001908654554865,
+      "loss": 1784.348125,
+      "step": 1100
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 431.8824462890625,
+      "learning_rate": 0.00029050332548388074,
+      "loss": 1780.343125,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 544.1112670898438,
+      "learning_rate": 0.00028054092988732,
+      "loss": 1776.639375,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 489.1014099121094,
+      "learning_rate": 0.0002703339341338006,
+      "loss": 1775.20375,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "eval_accuracy": 0.17473020527859237,
+      "eval_loss": 58.67676544189453,
+      "eval_runtime": 7.7117,
+      "eval_samples_per_second": 16.209,
+      "eval_steps_per_second": 0.519,
+      "step": 1250
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 434.31243896484375,
+      "learning_rate": 0.00025991333653395637,
+      "loss": 1772.2684375,
+      "step": 1300
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 329.494873046875,
+      "learning_rate": 0.00024931078410020814,
+      "loss": 1769.61375,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 606.4137573242188,
+      "learning_rate": 0.00023855847643582703,
+      "loss": 1765.89265625,
+      "step": 1400
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 486.37298583984375,
+      "learning_rate": 0.00022768906794579753,
+      "loss": 1762.6784375,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 426.2013854980469,
+      "learning_rate": 0.00021673556866646317,
+      "loss": 1761.15328125,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.1763401759530792,
+      "eval_loss": 58.22502517700195,
+      "eval_runtime": 7.3798,
+      "eval_samples_per_second": 16.938,
+      "eval_steps_per_second": 0.542,
+      "step": 1500
     }
   ],
   "logging_steps": 50,