Training in progress, step 18000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d722dd48084253e30edcdf2b9c7c11a74b1b8db5e9fdd03e44b6b8722f9fe4
+oid sha256:5163584c22b230a285b507e8fe2e44bfe9c5791489c457ec3f5dae50ef6a9d4e
 size 386379

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc6390d79743c341e54409953964ed7435ac3ae79f72a9c0b2a61d5bfa4014e
+oid sha256:ea5c1de12275b49f3c217c8fb0f7b7f68cd81b837676a213fd5cbc5529e41d84
 size 1540661735

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dcdb042e82db2feeaf162fa2c2cb05728354faf3a44aadef50aea6b23b1d50f
+oid sha256:6d32ac62864aa24d38961f967a353dbdc0c209a83a9a14bd5c6430acf5218f70
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2e4e7d621db7965ac0d0149ed05a3a6f4a8f4d9ee38752c9f0d6d1b7c145e73
+oid sha256:af8916051f16387fb69685f7e072b99274ccf08a163a3cca2253ee5f3a7d6975
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508d87a75853c2525702937f0b29e20460fd10ed4559a13863d962226c0b64f6
+oid sha256:838f0bffb8a21a934a0dd82575abe5438ad86fa4e56f88f4502576bfc1452b15
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e58646a1d294f0200655cb40f9e0932383e71653f6e1881d789b0865a448d379
+oid sha256:a4277fe562ff3ebc8bf0029b649400f1d520bbe1f14e9fb0ddeb5516160e4f1e
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12049670dc229efa48859b2adaa7bab30026005b65de953934912e8618042ff1
+oid sha256:2aca493fa7cb3a1e93f1a9b8b666fdc3f1dff09789426df3cc65d5126aa02b10
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cb0f9f2044cff462979fc73428559a94af22b0f0ccb7178a43a2c54c6bd489
+oid sha256:454e7b124610176fbeace81b35b4d3891f06294dd70b8c450a31971fb9d0f6e5
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5d3e29a67a07d0732605625beeef4e37c068d24accf9b8ee268df48cbfb581
+oid sha256:8a2463c5e875ad508adb42e7029d59e6e8bcbb4d858d11906a1c0881a41dee45
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a884f7fff4609aa43572eb70b86f31ae319b33f5de3caf0a4442a33602de76c4
+oid sha256:8f3ee3875e552d5e8fd915d17b82bcf736028026d7ebd8fb029b832116243bc7
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5763ed75e068d243df01e54fda7497cd86e57ed3e9ed4dadca20a2d87ccb859e
+oid sha256:218c7072bdbb7a0145270cf1a07d80a739b3014f750ae43e7b4b16e30b41a003
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.64,
+  "epoch": 0.72,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -1272,6 +1272,164 @@
       "eval_samples_per_second": 17.185,
       "eval_steps_per_second": 0.55,
       "step": 16000
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 1.2762759923934937,
+      "learning_rate": 0.001126799788845827,
+      "loss": 42.4043359375,
+      "step": 16100
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 1.4422513246536255,
+      "learning_rate": 0.0011042495226358784,
+      "loss": 43.033349609375,
+      "step": 16200
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 1.816651463508606,
+      "learning_rate": 0.0010818408190361227,
+      "loss": 42.873017578125,
+      "step": 16300
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 2.664728879928589,
+      "learning_rate": 0.0010595772194731657,
+      "loss": 42.72642578125,
+      "step": 16400
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 2.1422553062438965,
+      "learning_rate": 0.0010374622424416619,
+      "loss": 42.725224609375,
+      "step": 16500
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 2.044825315475464,
+      "learning_rate": 0.0010154993829482593,
+      "loss": 42.5387841796875,
+      "step": 16600
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 1.400777816772461,
+      "learning_rate": 0.0009936921119592535,
+      "loss": 42.594912109375,
+      "step": 16700
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 1.5564935207366943,
+      "learning_rate": 0.0009720438758520462,
+      "loss": 42.6428369140625,
+      "step": 16800
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 2.554816961288452,
+      "learning_rate": 0.0009505580958704852,
+      "loss": 42.628232421875,
+      "step": 16900
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 1.2824437618255615,
+      "learning_rate": 0.0009292381675841768,
+      "loss": 42.5581103515625,
+      "step": 17000
+    },
+    {
+      "epoch": 0.68,
+      "eval_accuracy": 0.22342913000977518,
+      "eval_loss": 42.39310836791992,
+      "eval_runtime": 7.1782,
+      "eval_samples_per_second": 17.414,
+      "eval_steps_per_second": 0.557,
+      "step": 17000
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 1.755340576171875,
+      "learning_rate": 0.0009080874603518585,
+      "loss": 42.472861328125,
+      "step": 17100
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 1.1157244443893433,
+      "learning_rate": 0.0008871093167889121,
+      "loss": 42.5861279296875,
+      "step": 17200
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 1.2528804540634155,
+      "learning_rate": 0.0008663070522391008,
+      "loss": 42.4558740234375,
+      "step": 17300
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 1.7521710395812988,
+      "learning_rate": 0.0008456839542506229,
+      "loss": 42.712470703125,
+      "step": 17400
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.830307960510254,
+      "learning_rate": 0.0008252432820565525,
+      "loss": 42.67123046875,
+      "step": 17500
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 1.6736066341400146,
+      "learning_rate": 0.0008049882660597558,
+      "loss": 42.42759765625,
+      "step": 17600
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 1.5861881971359253,
+      "learning_rate": 0.0007849221073223665,
+      "loss": 42.5102734375,
+      "step": 17700
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 1.659502387046814,
+      "learning_rate": 0.0007650479770598948,
+      "loss": 42.2067578125,
+      "step": 17800
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 1.2964304685592651,
+      "learning_rate": 0.0007453690161400562,
+      "loss": 42.520947265625,
+      "step": 17900
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.7349175214767456,
+      "learning_rate": 0.000725888334586394,
+      "loss": 42.7132568359375,
+      "step": 18000
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.224316715542522,
+      "eval_loss": 42.29633331298828,
+      "eval_runtime": 7.2524,
+      "eval_samples_per_second": 17.236,
+      "eval_steps_per_second": 0.552,
+      "step": 18000
     }
   ],
   "logging_steps": 100,