Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6974752fe7a3b14089ab2e7053fc764710e6d0ddbd1d7314081904519abc3ca2
+oid sha256:f892f103723425ad14b38db6edb9aa4c6ee7b516549322cb183cac27a585cd69
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da8b0c6ec3a28101585919798344dd1a4d2e616af339b16dae843b9a7667d51
+oid sha256:67301da5c57c64e98efb14ecf294eab870a5a0a4e3004242e9e40668fa0a2e5b
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43badff6712b33504459f872ac58be74afdf5ffa731e863439dbed8d3f3b0658
+oid sha256:b4b76f2c1c39522b8c5498459c7e9113970762ae114e0e7f40cb836dc8984719
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12eac59d8227e48f0e6fc2526645da1f69a0138bb2904859d6e0d18216ba63d7
+oid sha256:f50e3306f3c9c6adbe0dedc2fd97abc1244264dc24b6104e59c24eb9f7554450
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c12b9a050992357585c15ce67795abc69719e584223ec4ccbae89612840d277
+oid sha256:34913556519b4f5ff6ee3a99f05254dcc26ba55b30a512aa1a424a8163b3da18
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da83cd5eef961d44e4becc44e4089edf261063947ef5a08e30404cfbd611e2c3
+oid sha256:2a622b9945abec665a29f44d02e606edae0902d7c858f03471fc439ffb78c8bd
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfd920f545c0711cea231c43d68bcba64df0cc8fd9e536bc95aea4ceced55b64
+oid sha256:c2db92a63182f2a8e74f6f8ba8a49330276140c1b1e68be053bb7958ff88aa05
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e310e83ca23aa2c5186dec200b69809f8eb565d4f17f262d28f343cd531776
+oid sha256:c1dfcf1def0fab315df7efa0e82058c17d657f7d1e24a0863e66bae75531cfbf
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67aa5039be38b0a461bcbf305aaf4eb5ca5764f1670f75af2089e433b412f3af
+oid sha256:7d41bf7a36b12290d0668a17db5481f4d9bac1fb69402aa3433a16ac534f0d78
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c15db3462043815a7b702c6ec5d03f93688f7392547928696d4f1b5bc14356
+oid sha256:e3f52f2981f6a10064b9d54b23539047132389d938a031ae78cc1e296c5a1748
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31938cdcda9330861d9a6c5fa22f1c1b3736037ca4758e7ec127110a6ee0d1a
+oid sha256:2d5d1546bfb69154c942dddcbbbdf46b8cffa1900144b2ba63a8323dfd94157b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16666666666666666,
+  "epoch": 0.3333333333333333,
   "eval_steps": 250,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -96,6 +96,94 @@
       "eval_samples_per_second": 16.827,
       "eval_steps_per_second": 0.538,
       "step": 500
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 330.5375061035156,
+      "learning_rate": 0.0003809654104932039,
+      "loss": 1856.43828125,
+      "step": 550
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 462.14501953125,
+      "learning_rate": 0.00037599957197558643,
+      "loss": 1845.416875,
+      "step": 600
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 348.27215576171875,
+      "learning_rate": 0.0003704992285423923,
+      "loss": 1836.4821875,
+      "step": 650
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 348.34326171875,
+      "learning_rate": 0.0003644810845558505,
+      "loss": 1828.6059375,
+      "step": 700
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 478.7774353027344,
+      "learning_rate": 0.00035796341692145183,
+      "loss": 1821.568125,
+      "step": 750
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.1680097751710655,
+      "eval_loss": 60.21141815185547,
+      "eval_runtime": 7.4388,
+      "eval_samples_per_second": 16.804,
+      "eval_steps_per_second": 0.538,
+      "step": 750
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 353.61517333984375,
+      "learning_rate": 0.0003509660195815883,
+      "loss": 1817.4553125,
+      "step": 800
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 335.4817810058594,
+      "learning_rate": 0.0003435101434020002,
+      "loss": 1810.23265625,
+      "step": 850
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 580.8027954101562,
+      "learning_rate": 0.0003356184316335953,
+      "loss": 1802.5071875,
+      "step": 900
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 463.22943115234375,
+      "learning_rate": 0.00032731485114564034,
+      "loss": 1796.794375,
+      "step": 950
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 435.9424133300781,
+      "learning_rate": 0.0003186246196391665,
+      "loss": 1792.77296875,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_accuracy": 0.1721837732160313,
+      "eval_loss": 59.25102233886719,
+      "eval_runtime": 7.0046,
+      "eval_samples_per_second": 17.845,
+      "eval_steps_per_second": 0.571,
+      "step": 1000
     }
   ],
   "logging_steps": 50,