Training in progress, step 12000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5f848615af7284182bf34bb526cf66a4611210963f90a45f3c9021871e1d85
+oid sha256:895b25ff701dcc070741cf42351fb18c429fa56d815b15c7ba3c867f23a10980
 size 1600779

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4c790553f3e4092f7857a64225265bb38246a5d8a25fe76b1107d5f0509e1f
+oid sha256:1313ea19ff807c10147842a59b9051e7021a8c028fe68e36adab013243f36b38
 size 621149155

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189ca5f500a151c520561b912184d219fb4a14e37e0545ece3a7916f40a7b6f6
+oid sha256:f794b047026bd2e455c2f0c1a40191bfadaa2e43fd08fedee4185a5059db1b48
 size 14469

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585e6d762d92f384f163db69802c96c5f70ee11af325886531da1e25dbdd3c46
+oid sha256:a5541088e5d274181d6c9ef46a5b103eb5b8bf402d2abae7634635f86f3865ab
 size 14469

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23411dc088849538602b2c97c02e11f26fb822081e4a284d2b43ea9891ec5924
+oid sha256:da6b2d1e9271342e1e302bb1b26316b143cfc6c4934d2ed389c10bb161aa25ef
 size 14469

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96d850263b64569ae2096b8d72bc91a5ebdd71deb02d3267c85822dd6891262
+oid sha256:7900dd4bec725410e9ff4f8c55274ea9809b523a68297edbd3a83622136595cd
 size 14469

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14acad3fcc328519114bc488b787139326de9b018d7a082a9a787fbad2c61513
+oid sha256:d05d56cf9a1650f01c1af9b1a787ec6db7126c64049f267e937381c9944e1282
 size 14469

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9d4bb8960e987a9f4826d17f0ffbf80325efd81a2b4fbccc2aba1b74b8cb51
+oid sha256:9be3515ba8ff34af4f0c40faacd8a5a9e8e607850863dcb77d772f0606a1ae0c
 size 14469

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2326a5fbe6bf3c05da0cff924b9b40c864d3c0c3f624c13f7edec4700ef239
+oid sha256:d2e3e189e1259797127a8750045cf99ca33e22e9a0c01f4e0afcdf1fa22431dd
 size 14469

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1ed186896b3430710bec5fd2c1b85c275cbb3ef74ad87064fdc0302116db5c
+oid sha256:3a9afcf27fe2dffd21d9ec60d55b8d2840fcdcf2a30cdfc9362419caa2813c93
 size 14469

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833776bf99a0597a4bf38df86be38e8ac151736eba1d084c9cbb84cab1caf4e9
+oid sha256:43ab2089bb2cb7b873a77ac8e24a3b3b2416ededca3811b6bb0922f61bea4c99
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.24,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": false,
   "is_world_process_zero": true,
@@ -798,6 +798,164 @@
       "eval_samples_per_second": 39.294,
       "eval_steps_per_second": 0.629,
       "step": 10000
+    },
+    {
+      "epoch": 0.202,
+      "grad_norm": 1.518142819404602,
+      "learning_rate": 0.0018763385407335963,
+      "loss": 32.7453,
+      "step": 10100
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 1.908083200454712,
+      "learning_rate": 0.001873133519711602,
+      "loss": 32.9035,
+      "step": 10200
+    },
+    {
+      "epoch": 0.206,
+      "grad_norm": 2.4479877948760986,
+      "learning_rate": 0.0018698903050008956,
+      "loss": 32.3298,
+      "step": 10300
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 1.403601050376892,
+      "learning_rate": 0.0018666090384701947,
+      "loss": 32.0576,
+      "step": 10400
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.7655203342437744,
+      "learning_rate": 0.001863289863652727,
+      "loss": 32.8307,
+      "step": 10500
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 1.317898154258728,
+      "learning_rate": 0.0018599329257399516,
+      "loss": 32.8206,
+      "step": 10600
+    },
+    {
+      "epoch": 0.214,
+      "grad_norm": 1.6275999546051025,
+      "learning_rate": 0.0018565383715752083,
+      "loss": 33.1208,
+      "step": 10700
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 1.350576639175415,
+      "learning_rate": 0.0018531063496472927,
+      "loss": 33.09,
+      "step": 10800
+    },
+    {
+      "epoch": 0.218,
+      "grad_norm": 2.071432590484619,
+      "learning_rate": 0.0018496370100839622,
+      "loss": 32.4823,
+      "step": 10900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.756463646888733,
+      "learning_rate": 0.0018461305046453683,
+      "loss": 32.3173,
+      "step": 11000
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.29537964774951075,
+      "eval_loss": 32.61259078979492,
+      "eval_runtime": 3.1999,
+      "eval_samples_per_second": 39.064,
+      "eval_steps_per_second": 0.625,
+      "step": 11000
+    },
+    {
+      "epoch": 0.222,
+      "grad_norm": 2.6366186141967773,
+      "learning_rate": 0.0018425869867174187,
+      "loss": 32.0905,
+      "step": 11100
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 1.3121482133865356,
+      "learning_rate": 0.0018390066113050665,
+      "loss": 32.2553,
+      "step": 11200
+    },
+    {
+      "epoch": 0.226,
+      "grad_norm": 8.878124237060547,
+      "learning_rate": 0.0018353895350255317,
+      "loss": 33.1959,
+      "step": 11300
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 2.0059814453125,
+      "learning_rate": 0.0018317359161014477,
+      "loss": 32.804,
+      "step": 11400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.3689004182815552,
+      "learning_rate": 0.001828045914353943,
+      "loss": 32.6974,
+      "step": 11500
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 1.6248316764831543,
+      "learning_rate": 0.0018243196911956476,
+      "loss": 32.5622,
+      "step": 11600
+    },
+    {
+      "epoch": 0.234,
+      "grad_norm": 1.3218642473220825,
+      "learning_rate": 0.0018205574096236336,
+      "loss": 32.348,
+      "step": 11700
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 1.4009215831756592,
+      "learning_rate": 0.0018167592342122857,
+      "loss": 31.677,
+      "step": 11800
+    },
+    {
+      "epoch": 0.238,
+      "grad_norm": 1.8492565155029297,
+      "learning_rate": 0.0018129253311061002,
+      "loss": 31.6381,
+      "step": 11900
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.3902571201324463,
+      "learning_rate": 0.0018090558680124193,
+      "loss": 32.4851,
+      "step": 12000
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.300720156555773,
+      "eval_loss": 32.26734161376953,
+      "eval_runtime": 3.3297,
+      "eval_samples_per_second": 37.54,
+      "eval_steps_per_second": 0.601,
+      "step": 12000
     }
   ],
   "logging_steps": 100,