Training in progress, step 1800, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85962da1d94a1d14005b4253e4a50e923d9a39cbc0e312870a33b7168aa8374a
+oid sha256:8b85cfa532e3be66559e4eded0079f59370684d0066f69df72c3c9400a7beff1
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56782b0e4caa6d241d8b3d4783c5dcd4d145f869ac96de46fdaa0a8151220694
+oid sha256:006b7270ce13a5f5dc6c6a33b3cff5a74eb16868579d3e30b1763ba1e93c404e
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7511705737a7793f9a8f8c9b36c92d09abd33de20c399c92c82066fed75b855e
+oid sha256:76fb1455319679d06cc858e9dcdfaa6350bfd77929cb26479f070cf1390648b7
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6137155b55fbd8cc41045482398a6956043c027297043052e7964e5fc63de66
+oid sha256:ff50ca45d668f5ecdc7cd80ec4261fe42369ac91ece544c0f807f49f4cf7ec9b
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ef07e22a52809f46a7c2ae75dc39dc6e0bdbdeab0633c8ccc880b16e4925013
+oid sha256:066b8637e1804a15a6478d4144b24ac2b27af8920ee58edf2c6d9a0550266da5
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d5138e76782812b7a39315541ceba25964dac848a1c0c2e5ebffa25fe3746e
+oid sha256:3279d5ccb156c3893823aae49726395635fa6e716ad7192103c8ce3199585117
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d07999800664897d6fb1a2323f007d63051d8ed7a7651443e9e8e9f617aa90e
+oid sha256:e9e61b3efbb77c5def50573a42ce6977dc365728552420a3be0f27de4b665dd3
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e22ffa3459b7d0a79f52d958a6a4da9fd7f5643e9390d5ead2fba778e8869c5
+oid sha256:ca72d98e1539ac78ef5f48fd38c13952c6ddf6f9976d7f506cb6d755e8df2db7
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0acf66cdd3277c619b1c7a0e3c8cc4f09bd0828ecf9d9ef0d0ad811d21f43758
+oid sha256:473f41c5ecf5a91a8877bf819cd4fb40af5726999f740a4900d1725a79f97652
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f737e8534bf0d32d635cae39e128503c41f663422801b91c42be0efcf1c3c0
+oid sha256:214988d608c94f3b98fd14e7214497626c32df0dc44c1828bebcce6a105eb939
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e4ea9c22a4dd3329392569ee322c6a72133d25e8dc310620585148dbb3b1d0
+oid sha256:3b17baeb1a788abd9072f968ef0c2b9f4a57cac0fce20296a5a188b25a744f6e
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72cd63d54bf626b1ec79250977df50a1d78b2a6059d11ce4a343f6b001f610c7
+oid sha256:dec491f21fa25d9c558566ae69f94017b4507d08b4e301cbc032a487f686fc1c
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c051cdb67600fb9bc7d89ced7dd0d6982fb8567a894f2c94b0adbb1ef594dfb
+oid sha256:e6da1eeff6bbf88f1aa9e5a37469b6c8087c23d3160c8f0dc8d1272c55df086e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25082995204721503,
+  "epoch": 0.26558465510881596,
   "eval_steps": 20,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12939,6 +12939,766 @@
       "eval_samples_per_second": 5.774,
       "eval_steps_per_second": 0.198,
       "step": 1700
+    },
+    {
+      "epoch": 0.25097749907783107,
+      "grad_norm": 1.9432036876678467,
+      "learning_rate": 1.8643464790013847e-05,
+      "loss": 0.0727,
+      "step": 1701
+    },
+    {
+      "epoch": 0.25112504610844705,
+      "grad_norm": 2.7673637866973877,
+      "learning_rate": 1.8640873224028264e-05,
+      "loss": 0.0993,
+      "step": 1702
+    },
+    {
+      "epoch": 0.2512725931390631,
+      "grad_norm": 3.1381680965423584,
+      "learning_rate": 1.8638279365380313e-05,
+      "loss": 0.0613,
+      "step": 1703
+    },
+    {
+      "epoch": 0.25142014016967906,
+      "grad_norm": 2.2705259323120117,
+      "learning_rate": 1.8635683214758213e-05,
+      "loss": 0.0616,
+      "step": 1704
+    },
+    {
+      "epoch": 0.2515676872002951,
+      "grad_norm": 1.7805274724960327,
+      "learning_rate": 1.86330847728508e-05,
+      "loss": 0.0541,
+      "step": 1705
+    },
+    {
+      "epoch": 0.2517152342309111,
+      "grad_norm": 2.0656790733337402,
+      "learning_rate": 1.8630484040347513e-05,
+      "loss": 0.0557,
+      "step": 1706
+    },
+    {
+      "epoch": 0.2518627812615271,
+      "grad_norm": 2.5722081661224365,
+      "learning_rate": 1.8627881017938392e-05,
+      "loss": 0.0742,
+      "step": 1707
+    },
+    {
+      "epoch": 0.2520103282921431,
+      "grad_norm": 3.1926660537719727,
+      "learning_rate": 1.8625275706314094e-05,
+      "loss": 0.077,
+      "step": 1708
+    },
+    {
+      "epoch": 0.25215787532275913,
+      "grad_norm": 2.3915457725524902,
+      "learning_rate": 1.8622668106165883e-05,
+      "loss": 0.0217,
+      "step": 1709
+    },
+    {
+      "epoch": 0.25230542235337516,
+      "grad_norm": 1.8211325407028198,
+      "learning_rate": 1.8620058218185624e-05,
+      "loss": 0.0851,
+      "step": 1710
+    },
+    {
+      "epoch": 0.25245296938399114,
+      "grad_norm": 2.756812810897827,
+      "learning_rate": 1.8617446043065796e-05,
+      "loss": 0.047,
+      "step": 1711
+    },
+    {
+      "epoch": 0.2526005164146072,
+      "grad_norm": 3.6415255069732666,
+      "learning_rate": 1.8614831581499477e-05,
+      "loss": 0.0554,
+      "step": 1712
+    },
+    {
+      "epoch": 0.25274806344522316,
+      "grad_norm": 4.068582534790039,
+      "learning_rate": 1.8612214834180357e-05,
+      "loss": 0.1054,
+      "step": 1713
+    },
+    {
+      "epoch": 0.2528956104758392,
+      "grad_norm": 1.3567254543304443,
+      "learning_rate": 1.860959580180273e-05,
+      "loss": 0.0349,
+      "step": 1714
+    },
+    {
+      "epoch": 0.2530431575064552,
+      "grad_norm": 1.8216665983200073,
+      "learning_rate": 1.8606974485061503e-05,
+      "loss": 0.0471,
+      "step": 1715
+    },
+    {
+      "epoch": 0.2531907045370712,
+      "grad_norm": 2.0203757286071777,
+      "learning_rate": 1.8604350884652175e-05,
+      "loss": 0.0454,
+      "step": 1716
+    },
+    {
+      "epoch": 0.2533382515676872,
+      "grad_norm": 3.666323184967041,
+      "learning_rate": 1.8601725001270868e-05,
+      "loss": 0.0352,
+      "step": 1717
+    },
+    {
+      "epoch": 0.2534857985983032,
+      "grad_norm": 2.4993855953216553,
+      "learning_rate": 1.8599096835614298e-05,
+      "loss": 0.0631,
+      "step": 1718
+    },
+    {
+      "epoch": 0.2536333456289192,
+      "grad_norm": 0.7023165225982666,
+      "learning_rate": 1.8596466388379793e-05,
+      "loss": 0.007,
+      "step": 1719
+    },
+    {
+      "epoch": 0.25378089265953524,
+      "grad_norm": 4.019131183624268,
+      "learning_rate": 1.8593833660265274e-05,
+      "loss": 0.0401,
+      "step": 1720
+    },
+    {
+      "epoch": 0.25378089265953524,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9571788413098237,
+      "eval_loss": 0.08183550834655762,
+      "eval_precision": 0.9947643979057592,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 51.288,
+      "eval_samples_per_second": 5.674,
+      "eval_steps_per_second": 0.195,
+      "step": 1720
+    },
+    {
+      "epoch": 0.2539284396901512,
+      "grad_norm": 1.3719967603683472,
+      "learning_rate": 1.8591198651969286e-05,
+      "loss": 0.0428,
+      "step": 1721
+    },
+    {
+      "epoch": 0.25407598672076726,
+      "grad_norm": 2.008892774581909,
+      "learning_rate": 1.858856136419097e-05,
+      "loss": 0.0452,
+      "step": 1722
+    },
+    {
+      "epoch": 0.25422353375138323,
+      "grad_norm": 0.8016170263290405,
+      "learning_rate": 1.8585921797630064e-05,
+      "loss": 0.0162,
+      "step": 1723
+    },
+    {
+      "epoch": 0.25437108078199927,
+      "grad_norm": 6.163304328918457,
+      "learning_rate": 1.8583279952986924e-05,
+      "loss": 0.1614,
+      "step": 1724
+    },
+    {
+      "epoch": 0.25451862781261525,
+      "grad_norm": 2.027590274810791,
+      "learning_rate": 1.8580635830962498e-05,
+      "loss": 0.0829,
+      "step": 1725
+    },
+    {
+      "epoch": 0.2546661748432313,
+      "grad_norm": 2.659754753112793,
+      "learning_rate": 1.8577989432258352e-05,
+      "loss": 0.0459,
+      "step": 1726
+    },
+    {
+      "epoch": 0.25481372187384727,
+      "grad_norm": 5.089884281158447,
+      "learning_rate": 1.8575340757576647e-05,
+      "loss": 0.1173,
+      "step": 1727
+    },
+    {
+      "epoch": 0.2549612689044633,
+      "grad_norm": 3.7841427326202393,
+      "learning_rate": 1.8572689807620144e-05,
+      "loss": 0.1242,
+      "step": 1728
+    },
+    {
+      "epoch": 0.2551088159350793,
+      "grad_norm": 1.6784816980361938,
+      "learning_rate": 1.8570036583092218e-05,
+      "loss": 0.0231,
+      "step": 1729
+    },
+    {
+      "epoch": 0.2552563629656953,
+      "grad_norm": 2.5521578788757324,
+      "learning_rate": 1.8567381084696846e-05,
+      "loss": 0.0475,
+      "step": 1730
+    },
+    {
+      "epoch": 0.25540390999631135,
+      "grad_norm": 2.2968292236328125,
+      "learning_rate": 1.8564723313138595e-05,
+      "loss": 0.0776,
+      "step": 1731
+    },
+    {
+      "epoch": 0.25555145702692733,
+      "grad_norm": 5.221238136291504,
+      "learning_rate": 1.8562063269122654e-05,
+      "loss": 0.0677,
+      "step": 1732
+    },
+    {
+      "epoch": 0.25569900405754337,
+      "grad_norm": 3.9754536151885986,
+      "learning_rate": 1.8559400953354804e-05,
+      "loss": 0.0611,
+      "step": 1733
+    },
+    {
+      "epoch": 0.25584655108815935,
+      "grad_norm": 1.1239689588546753,
+      "learning_rate": 1.855673636654143e-05,
+      "loss": 0.0145,
+      "step": 1734
+    },
+    {
+      "epoch": 0.2559940981187754,
+      "grad_norm": 2.755523443222046,
+      "learning_rate": 1.8554069509389522e-05,
+      "loss": 0.0504,
+      "step": 1735
+    },
+    {
+      "epoch": 0.25614164514939136,
+      "grad_norm": 2.0224733352661133,
+      "learning_rate": 1.8551400382606666e-05,
+      "loss": 0.0286,
+      "step": 1736
+    },
+    {
+      "epoch": 0.2562891921800074,
+      "grad_norm": 2.5080149173736572,
+      "learning_rate": 1.8548728986901063e-05,
+      "loss": 0.0417,
+      "step": 1737
+    },
+    {
+      "epoch": 0.2564367392106234,
+      "grad_norm": 2.173332452774048,
+      "learning_rate": 1.8546055322981498e-05,
+      "loss": 0.0264,
+      "step": 1738
+    },
+    {
+      "epoch": 0.2565842862412394,
+      "grad_norm": 4.695002555847168,
+      "learning_rate": 1.854337939155738e-05,
+      "loss": 0.0752,
+      "step": 1739
+    },
+    {
+      "epoch": 0.2567318332718554,
+      "grad_norm": 1.4090908765792847,
+      "learning_rate": 1.85407011933387e-05,
+      "loss": 0.0215,
+      "step": 1740
+    },
+    {
+      "epoch": 0.2567318332718554,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9571788413098237,
+      "eval_loss": 0.06773916631937027,
+      "eval_precision": 0.9947643979057592,
+      "eval_recall": 0.9223300970873787,
+      "eval_runtime": 50.6257,
+      "eval_samples_per_second": 5.748,
+      "eval_steps_per_second": 0.198,
+      "step": 1740
+    },
+    {
+      "epoch": 0.2568793803024714,
+      "grad_norm": 1.6555758714675903,
+      "learning_rate": 1.8538020729036056e-05,
+      "loss": 0.0399,
+      "step": 1741
+    },
+    {
+      "epoch": 0.2570269273330874,
+      "grad_norm": 2.4466981887817383,
+      "learning_rate": 1.8535337999360655e-05,
+      "loss": 0.0532,
+      "step": 1742
+    },
+    {
+      "epoch": 0.25717447436370344,
+      "grad_norm": 1.5140111446380615,
+      "learning_rate": 1.8532653005024296e-05,
+      "loss": 0.0407,
+      "step": 1743
+    },
+    {
+      "epoch": 0.2573220213943194,
+      "grad_norm": 4.404722690582275,
+      "learning_rate": 1.8529965746739382e-05,
+      "loss": 0.0865,
+      "step": 1744
+    },
+    {
+      "epoch": 0.25746956842493546,
+      "grad_norm": 2.450817346572876,
+      "learning_rate": 1.8527276225218917e-05,
+      "loss": 0.0475,
+      "step": 1745
+    },
+    {
+      "epoch": 0.25761711545555144,
+      "grad_norm": 4.185603618621826,
+      "learning_rate": 1.852458444117651e-05,
+      "loss": 0.0627,
+      "step": 1746
+    },
+    {
+      "epoch": 0.2577646624861675,
+      "grad_norm": 2.810720443725586,
+      "learning_rate": 1.8521890395326362e-05,
+      "loss": 0.0803,
+      "step": 1747
+    },
+    {
+      "epoch": 0.25791220951678345,
+      "grad_norm": 1.0313979387283325,
+      "learning_rate": 1.851919408838327e-05,
+      "loss": 0.0125,
+      "step": 1748
+    },
+    {
+      "epoch": 0.2580597565473995,
+      "grad_norm": 3.1539950370788574,
+      "learning_rate": 1.8516495521062656e-05,
+      "loss": 0.0782,
+      "step": 1749
+    },
+    {
+      "epoch": 0.25820730357801547,
+      "grad_norm": 6.985763072967529,
+      "learning_rate": 1.851379469408051e-05,
+      "loss": 0.1116,
+      "step": 1750
+    },
+    {
+      "epoch": 0.2583548506086315,
+      "grad_norm": 1.3113516569137573,
+      "learning_rate": 1.851109160815344e-05,
+      "loss": 0.0102,
+      "step": 1751
+    },
+    {
+      "epoch": 0.2585023976392475,
+      "grad_norm": 3.379911184310913,
+      "learning_rate": 1.850838626399865e-05,
+      "loss": 0.0657,
+      "step": 1752
+    },
+    {
+      "epoch": 0.2586499446698635,
+      "grad_norm": 4.795577526092529,
+      "learning_rate": 1.8505678662333945e-05,
+      "loss": 0.1243,
+      "step": 1753
+    },
+    {
+      "epoch": 0.25879749170047955,
+      "grad_norm": 0.8018746972084045,
+      "learning_rate": 1.8502968803877724e-05,
+      "loss": 0.0167,
+      "step": 1754
+    },
+    {
+      "epoch": 0.25894503873109553,
+      "grad_norm": 5.773539066314697,
+      "learning_rate": 1.8500256689348985e-05,
+      "loss": 0.0964,
+      "step": 1755
+    },
+    {
+      "epoch": 0.25909258576171157,
+      "grad_norm": 2.2165045738220215,
+      "learning_rate": 1.849754231946733e-05,
+      "loss": 0.1102,
+      "step": 1756
+    },
+    {
+      "epoch": 0.25924013279232755,
+      "grad_norm": 1.5358134508132935,
+      "learning_rate": 1.8494825694952955e-05,
+      "loss": 0.022,
+      "step": 1757
+    },
+    {
+      "epoch": 0.2593876798229436,
+      "grad_norm": 4.51975679397583,
+      "learning_rate": 1.849210681652666e-05,
+      "loss": 0.1497,
+      "step": 1758
+    },
+    {
+      "epoch": 0.25953522685355956,
+      "grad_norm": 1.4902085065841675,
+      "learning_rate": 1.8489385684909833e-05,
+      "loss": 0.0418,
+      "step": 1759
+    },
+    {
+      "epoch": 0.2596827738841756,
+      "grad_norm": 3.8184237480163574,
+      "learning_rate": 1.8486662300824466e-05,
+      "loss": 0.1742,
+      "step": 1760
+    },
+    {
+      "epoch": 0.2596827738841756,
+      "eval_accuracy": 0.9739507959479016,
+      "eval_f1": 0.9545454545454546,
+      "eval_loss": 0.06750224530696869,
+      "eval_precision": 0.9947368421052631,
+      "eval_recall": 0.9174757281553398,
+      "eval_runtime": 50.9325,
+      "eval_samples_per_second": 5.713,
+      "eval_steps_per_second": 0.196,
+      "step": 1760
+    },
+    {
+      "epoch": 0.2598303209147916,
+      "grad_norm": 2.709332227706909,
+      "learning_rate": 1.8483936664993152e-05,
+      "loss": 0.0462,
+      "step": 1761
+    },
+    {
+      "epoch": 0.2599778679454076,
+      "grad_norm": 3.011286497116089,
+      "learning_rate": 1.8481208778139072e-05,
+      "loss": 0.0473,
+      "step": 1762
+    },
+    {
+      "epoch": 0.2601254149760236,
+      "grad_norm": 1.5091990232467651,
+      "learning_rate": 1.8478478640986012e-05,
+      "loss": 0.0645,
+      "step": 1763
+    },
+    {
+      "epoch": 0.26027296200663963,
+      "grad_norm": 2.049199104309082,
+      "learning_rate": 1.8475746254258355e-05,
+      "loss": 0.0925,
+      "step": 1764
+    },
+    {
+      "epoch": 0.2604205090372556,
+      "grad_norm": 1.6349753141403198,
+      "learning_rate": 1.8473011618681075e-05,
+      "loss": 0.0617,
+      "step": 1765
+    },
+    {
+      "epoch": 0.26056805606787165,
+      "grad_norm": 3.4156811237335205,
+      "learning_rate": 1.847027473497975e-05,
+      "loss": 0.0825,
+      "step": 1766
+    },
+    {
+      "epoch": 0.2607156030984876,
+      "grad_norm": 1.9899978637695312,
+      "learning_rate": 1.846753560388055e-05,
+      "loss": 0.1078,
+      "step": 1767
+    },
+    {
+      "epoch": 0.26086315012910366,
+      "grad_norm": 3.2789146900177,
+      "learning_rate": 1.846479422611024e-05,
+      "loss": 0.0708,
+      "step": 1768
+    },
+    {
+      "epoch": 0.26101069715971964,
+      "grad_norm": 1.5854333639144897,
+      "learning_rate": 1.8462050602396185e-05,
+      "loss": 0.0241,
+      "step": 1769
+    },
+    {
+      "epoch": 0.2611582441903357,
+      "grad_norm": 2.8847148418426514,
+      "learning_rate": 1.845930473346634e-05,
+      "loss": 0.0582,
+      "step": 1770
+    },
+    {
+      "epoch": 0.26130579122095166,
+      "grad_norm": 1.4418102502822876,
+      "learning_rate": 1.8456556620049268e-05,
+      "loss": 0.045,
+      "step": 1771
+    },
+    {
+      "epoch": 0.2614533382515677,
+      "grad_norm": 2.6730871200561523,
+      "learning_rate": 1.8453806262874113e-05,
+      "loss": 0.1407,
+      "step": 1772
+    },
+    {
+      "epoch": 0.26160088528218367,
+      "grad_norm": 1.6478065252304077,
+      "learning_rate": 1.8451053662670627e-05,
+      "loss": 0.0935,
+      "step": 1773
+    },
+    {
+      "epoch": 0.2617484323127997,
+      "grad_norm": 1.2931264638900757,
+      "learning_rate": 1.844829882016914e-05,
+      "loss": 0.0254,
+      "step": 1774
+    },
+    {
+      "epoch": 0.26189597934341574,
+      "grad_norm": 7.989828586578369,
+      "learning_rate": 1.84455417361006e-05,
+      "loss": 0.0289,
+      "step": 1775
+    },
+    {
+      "epoch": 0.2620435263740317,
+      "grad_norm": 1.3203344345092773,
+      "learning_rate": 1.8442782411196528e-05,
+      "loss": 0.057,
+      "step": 1776
+    },
+    {
+      "epoch": 0.26219107340464776,
+      "grad_norm": 1.7602546215057373,
+      "learning_rate": 1.8440020846189056e-05,
+      "loss": 0.0389,
+      "step": 1777
+    },
+    {
+      "epoch": 0.26233862043526374,
+      "grad_norm": 2.9316866397857666,
+      "learning_rate": 1.8437257041810898e-05,
+      "loss": 0.0283,
+      "step": 1778
+    },
+    {
+      "epoch": 0.26248616746587977,
+      "grad_norm": 2.4985477924346924,
+      "learning_rate": 1.843449099879537e-05,
+      "loss": 0.0767,
+      "step": 1779
+    },
+    {
+      "epoch": 0.26263371449649575,
+      "grad_norm": 2.154252529144287,
+      "learning_rate": 1.8431722717876383e-05,
+      "loss": 0.0445,
+      "step": 1780
+    },
+    {
+      "epoch": 0.26263371449649575,
+      "eval_accuracy": 0.975397973950796,
+      "eval_f1": 0.9573934837092731,
+      "eval_loss": 0.06556418538093567,
+      "eval_precision": 0.9896373056994818,
+      "eval_recall": 0.9271844660194175,
+      "eval_runtime": 50.127,
+      "eval_samples_per_second": 5.805,
+      "eval_steps_per_second": 0.199,
+      "step": 1780
+    },
+    {
+      "epoch": 0.2627812615271118,
+      "grad_norm": 4.1848578453063965,
+      "learning_rate": 1.8428952199788433e-05,
+      "loss": 0.0738,
+      "step": 1781
+    },
+    {
+      "epoch": 0.26292880855772777,
+      "grad_norm": 4.228147029876709,
+      "learning_rate": 1.8426179445266615e-05,
+      "loss": 0.0622,
+      "step": 1782
+    },
+    {
+      "epoch": 0.2630763555883438,
+      "grad_norm": 1.3042999505996704,
+      "learning_rate": 1.8423404455046626e-05,
+      "loss": 0.0486,
+      "step": 1783
+    },
+    {
+      "epoch": 0.2632239026189598,
+      "grad_norm": 2.5874569416046143,
+      "learning_rate": 1.8420627229864737e-05,
+      "loss": 0.0597,
+      "step": 1784
+    },
+    {
+      "epoch": 0.2633714496495758,
+      "grad_norm": 1.3495664596557617,
+      "learning_rate": 1.8417847770457825e-05,
+      "loss": 0.0321,
+      "step": 1785
+    },
+    {
+      "epoch": 0.2635189966801918,
+      "grad_norm": 3.2655980587005615,
+      "learning_rate": 1.8415066077563362e-05,
+      "loss": 0.1073,
+      "step": 1786
+    },
+    {
+      "epoch": 0.26366654371080783,
+      "grad_norm": 2.773749828338623,
+      "learning_rate": 1.8412282151919405e-05,
+      "loss": 0.0846,
+      "step": 1787
+    },
+    {
+      "epoch": 0.2638140907414238,
+      "grad_norm": 3.9619085788726807,
+      "learning_rate": 1.8409495994264607e-05,
+      "loss": 0.0737,
+      "step": 1788
+    },
+    {
+      "epoch": 0.26396163777203985,
+      "grad_norm": 4.892509937286377,
+      "learning_rate": 1.840670760533821e-05,
+      "loss": 0.1648,
+      "step": 1789
+    },
+    {
+      "epoch": 0.2641091848026558,
+      "grad_norm": 2.7034366130828857,
+      "learning_rate": 1.8403916985880054e-05,
+      "loss": 0.074,
+      "step": 1790
+    },
+    {
+      "epoch": 0.26425673183327186,
+      "grad_norm": 1.525233268737793,
+      "learning_rate": 1.8401124136630566e-05,
+      "loss": 0.0114,
+      "step": 1791
+    },
+    {
+      "epoch": 0.26440427886388784,
+      "grad_norm": 2.4368274211883545,
+      "learning_rate": 1.8398329058330767e-05,
+      "loss": 0.0171,
+      "step": 1792
+    },
+    {
+      "epoch": 0.2645518258945039,
+      "grad_norm": 1.877754807472229,
+      "learning_rate": 1.8395531751722268e-05,
+      "loss": 0.0866,
+      "step": 1793
+    },
+    {
+      "epoch": 0.26469937292511986,
+      "grad_norm": 1.8865419626235962,
+      "learning_rate": 1.8392732217547265e-05,
+      "loss": 0.0747,
+      "step": 1794
+    },
+    {
+      "epoch": 0.2648469199557359,
+      "grad_norm": 2.2851805686950684,
+      "learning_rate": 1.8389930456548563e-05,
+      "loss": 0.0929,
+      "step": 1795
+    },
+    {
+      "epoch": 0.2649944669863519,
+      "grad_norm": 1.866339921951294,
+      "learning_rate": 1.8387126469469542e-05,
+      "loss": 0.0568,
+      "step": 1796
+    },
+    {
+      "epoch": 0.2651420140169679,
+      "grad_norm": 3.043684720993042,
+      "learning_rate": 1.838432025705418e-05,
+      "loss": 0.0495,
+      "step": 1797
+    },
+    {
+      "epoch": 0.26528956104758394,
+      "grad_norm": 3.269800901412964,
+      "learning_rate": 1.8381511820047033e-05,
+      "loss": 0.0995,
+      "step": 1798
+    },
+    {
+      "epoch": 0.2654371080781999,
+      "grad_norm": 3.5884273052215576,
+      "learning_rate": 1.837870115919327e-05,
+      "loss": 0.0808,
+      "step": 1799
+    },
+    {
+      "epoch": 0.26558465510881596,
+      "grad_norm": 2.3827102184295654,
+      "learning_rate": 1.8375888275238625e-05,
+      "loss": 0.0557,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26558465510881596,
+      "eval_accuracy": 0.9782923299565847,
+      "eval_f1": 0.9629629629629629,
+      "eval_loss": 0.06993769109249115,
+      "eval_precision": 0.9798994974874372,
+      "eval_recall": 0.9466019417475728,
+      "eval_runtime": 50.1472,
+      "eval_samples_per_second": 5.803,
+      "eval_steps_per_second": 0.199,
+      "step": 1800
     }
   ],
   "logging_steps": 1,
@@ -12958,7 +13718,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.234024881879777e+17,
+  "total_flos": 5.544433821815931e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null