Training in progress, step 100, checkpoint

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text

last-checkpoint/optimizer_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a46305e3757310e77967a48f6f11d15dfc04610ea3c47a9bd6ee19032f5fc4
+size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc524e1e0f2bbb2aa7bd8fc85f80889fb087fdbf15913cf3227a448698db4d3
+size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f210d79701c31a8728abbaa75ca5098abbb357129ef21ed227bb12f2e0c6b33a
+size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a87e9a3a425e050d4146d55acd7be2eb5cc974709dce64d85331e2bea7cc69
+size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1bd75bc46a472f464e9532b7a6daaa31e5da4560d81565ed28b4156ca464f31
+size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48f0f5bb540bdd18c2802a4e5af94100f865676faf0344ea7c5186b16b1f49d
+size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261c1b32e6e85d926db710ea3b8dd1f22809034a427f74459a910de7cdb7de21
+size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76abdc7f5c34fb4c661e0afc2ebe81e08f46908f89daf2844f603fa1b3ab1ec6
+size 6966784

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2802629a8b6a5a32d68d046b59f24bee6a21ee25aa49bdbba2f7a8d4018d1fe6
+size 14960

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f659849723764ebc7cfbfc3f893d143a37183e5570e1e25c92b6ea995c4e87
+size 14960

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:404d6ca0dbbc29d798a06f1f7e0f1c9d8611ff0b41e99f5d5a3fd2d842d36ed0
+size 14960

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6502ae4b4e410f7072d0f0b3c97ba5d07126e4539f6b6fd906affb11eae0809
+size 14960

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b22e1a00a41d052f99562afa9f0ed110a591c8372e7fba4cb2c36dacd761533
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,805 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.07654037504783773,
+  "eval_steps": 20,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0,
+      "eval_accuracy": 0.648014440433213,
+      "eval_f1": 0.5578231292517006,
+      "eval_loss": 0.6320980787277222,
+      "eval_precision": 0.5125,
+      "eval_recall": 0.6119402985074627,
+      "eval_runtime": 43.0693,
+      "eval_samples_per_second": 6.989,
+      "eval_steps_per_second": 0.232,
+      "step": 0
+    },
+    {
+      "epoch": 0.0007654037504783774,
+      "grad_norm": 2.9013254642486572,
+      "learning_rate": 1.5267175572519085e-07,
+      "loss": 0.7916,
+      "step": 1
+    },
+    {
+      "epoch": 0.0015308075009567547,
+      "grad_norm": 2.805720567703247,
+      "learning_rate": 3.053435114503817e-07,
+      "loss": 0.7752,
+      "step": 2
+    },
+    {
+      "epoch": 0.002296211251435132,
+      "grad_norm": 2.7805535793304443,
+      "learning_rate": 4.5801526717557257e-07,
+      "loss": 0.7902,
+      "step": 3
+    },
+    {
+      "epoch": 0.0030616150019135095,
+      "grad_norm": 3.5079779624938965,
+      "learning_rate": 6.106870229007634e-07,
+      "loss": 0.7335,
+      "step": 4
+    },
+    {
+      "epoch": 0.003827018752391887,
+      "grad_norm": 2.8343734741210938,
+      "learning_rate": 7.633587786259543e-07,
+      "loss": 0.7026,
+      "step": 5
+    },
+    {
+      "epoch": 0.004592422502870264,
+      "grad_norm": 3.3417398929595947,
+      "learning_rate": 9.160305343511451e-07,
+      "loss": 0.7486,
+      "step": 6
+    },
+    {
+      "epoch": 0.005357826253348641,
+      "grad_norm": 3.5592422485351562,
+      "learning_rate": 1.068702290076336e-06,
+      "loss": 0.7085,
+      "step": 7
+    },
+    {
+      "epoch": 0.006123230003827019,
+      "grad_norm": 4.005152702331543,
+      "learning_rate": 1.2213740458015268e-06,
+      "loss": 0.7904,
+      "step": 8
+    },
+    {
+      "epoch": 0.006888633754305396,
+      "grad_norm": 3.1045947074890137,
+      "learning_rate": 1.3740458015267178e-06,
+      "loss": 0.7956,
+      "step": 9
+    },
+    {
+      "epoch": 0.007654037504783774,
+      "grad_norm": 2.570974826812744,
+      "learning_rate": 1.5267175572519086e-06,
+      "loss": 0.7206,
+      "step": 10
+    },
+    {
+      "epoch": 0.008419441255262151,
+      "grad_norm": 2.293649911880493,
+      "learning_rate": 1.6793893129770995e-06,
+      "loss": 0.6451,
+      "step": 11
+    },
+    {
+      "epoch": 0.009184845005740528,
+      "grad_norm": 2.148493528366089,
+      "learning_rate": 1.8320610687022903e-06,
+      "loss": 0.5701,
+      "step": 12
+    },
+    {
+      "epoch": 0.009950248756218905,
+      "grad_norm": 3.934507131576538,
+      "learning_rate": 1.984732824427481e-06,
+      "loss": 0.7146,
+      "step": 13
+    },
+    {
+      "epoch": 0.010715652506697282,
+      "grad_norm": 2.8026010990142822,
+      "learning_rate": 2.137404580152672e-06,
+      "loss": 0.7812,
+      "step": 14
+    },
+    {
+      "epoch": 0.011481056257175661,
+      "grad_norm": 2.6908481121063232,
+      "learning_rate": 2.2900763358778625e-06,
+      "loss": 0.6653,
+      "step": 15
+    },
+    {
+      "epoch": 0.012246460007654038,
+      "grad_norm": 2.2652783393859863,
+      "learning_rate": 2.4427480916030536e-06,
+      "loss": 0.6606,
+      "step": 16
+    },
+    {
+      "epoch": 0.013011863758132415,
+      "grad_norm": 3.234048843383789,
+      "learning_rate": 2.595419847328244e-06,
+      "loss": 0.7316,
+      "step": 17
+    },
+    {
+      "epoch": 0.013777267508610792,
+      "grad_norm": 2.967696189880371,
+      "learning_rate": 2.7480916030534356e-06,
+      "loss": 0.6979,
+      "step": 18
+    },
+    {
+      "epoch": 0.01454267125908917,
+      "grad_norm": 3.8475921154022217,
+      "learning_rate": 2.900763358778626e-06,
+      "loss": 0.8055,
+      "step": 19
+    },
+    {
+      "epoch": 0.015308075009567547,
+      "grad_norm": 2.42297101020813,
+      "learning_rate": 3.0534351145038173e-06,
+      "loss": 0.6598,
+      "step": 20
+    },
+    {
+      "epoch": 0.015308075009567547,
+      "eval_accuracy": 0.6552346570397112,
+      "eval_f1": 0.5526932084309133,
+      "eval_loss": 0.6283615231513977,
+      "eval_precision": 0.5221238938053098,
+      "eval_recall": 0.5870646766169154,
+      "eval_runtime": 43.704,
+      "eval_samples_per_second": 6.887,
+      "eval_steps_per_second": 0.229,
+      "step": 20
+    },
+    {
+      "epoch": 0.016073478760045924,
+      "grad_norm": 2.063398838043213,
+      "learning_rate": 3.206106870229008e-06,
+      "loss": 0.6512,
+      "step": 21
+    },
+    {
+      "epoch": 0.016838882510524303,
+      "grad_norm": 2.4448840618133545,
+      "learning_rate": 3.358778625954199e-06,
+      "loss": 0.567,
+      "step": 22
+    },
+    {
+      "epoch": 0.017604286261002678,
+      "grad_norm": 3.497593641281128,
+      "learning_rate": 3.5114503816793895e-06,
+      "loss": 0.7674,
+      "step": 23
+    },
+    {
+      "epoch": 0.018369690011481057,
+      "grad_norm": 1.899181842803955,
+      "learning_rate": 3.6641221374045806e-06,
+      "loss": 0.6927,
+      "step": 24
+    },
+    {
+      "epoch": 0.019135093761959432,
+      "grad_norm": 1.9708737134933472,
+      "learning_rate": 3.816793893129772e-06,
+      "loss": 0.7301,
+      "step": 25
+    },
+    {
+      "epoch": 0.01990049751243781,
+      "grad_norm": 2.531264543533325,
+      "learning_rate": 3.969465648854962e-06,
+      "loss": 0.7908,
+      "step": 26
+    },
+    {
+      "epoch": 0.02066590126291619,
+      "grad_norm": 3.4307644367218018,
+      "learning_rate": 4.122137404580153e-06,
+      "loss": 0.7273,
+      "step": 27
+    },
+    {
+      "epoch": 0.021431305013394564,
+      "grad_norm": 2.6872708797454834,
+      "learning_rate": 4.274809160305344e-06,
+      "loss": 0.7336,
+      "step": 28
+    },
+    {
+      "epoch": 0.022196708763872943,
+      "grad_norm": 3.0511341094970703,
+      "learning_rate": 4.427480916030535e-06,
+      "loss": 0.6708,
+      "step": 29
+    },
+    {
+      "epoch": 0.022962112514351322,
+      "grad_norm": 2.479977607727051,
+      "learning_rate": 4.580152671755725e-06,
+      "loss": 0.7374,
+      "step": 30
+    },
+    {
+      "epoch": 0.023727516264829697,
+      "grad_norm": 3.206690549850464,
+      "learning_rate": 4.732824427480917e-06,
+      "loss": 0.7716,
+      "step": 31
+    },
+    {
+      "epoch": 0.024492920015308076,
+      "grad_norm": 2.561702013015747,
+      "learning_rate": 4.885496183206107e-06,
+      "loss": 0.8201,
+      "step": 32
+    },
+    {
+      "epoch": 0.02525832376578645,
+      "grad_norm": 2.986666679382324,
+      "learning_rate": 5.038167938931297e-06,
+      "loss": 0.7439,
+      "step": 33
+    },
+    {
+      "epoch": 0.02602372751626483,
+      "grad_norm": 1.9290986061096191,
+      "learning_rate": 5.190839694656488e-06,
+      "loss": 0.6164,
+      "step": 34
+    },
+    {
+      "epoch": 0.026789131266743208,
+      "grad_norm": 2.402761459350586,
+      "learning_rate": 5.34351145038168e-06,
+      "loss": 0.7119,
+      "step": 35
+    },
+    {
+      "epoch": 0.027554535017221583,
+      "grad_norm": 2.68208384513855,
+      "learning_rate": 5.496183206106871e-06,
+      "loss": 0.6692,
+      "step": 36
+    },
+    {
+      "epoch": 0.028319938767699962,
+      "grad_norm": 2.0670857429504395,
+      "learning_rate": 5.648854961832062e-06,
+      "loss": 0.6724,
+      "step": 37
+    },
+    {
+      "epoch": 0.02908534251817834,
+      "grad_norm": 2.9470982551574707,
+      "learning_rate": 5.801526717557252e-06,
+      "loss": 0.66,
+      "step": 38
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 2.172914981842041,
+      "learning_rate": 5.9541984732824435e-06,
+      "loss": 0.6567,
+      "step": 39
+    },
+    {
+      "epoch": 0.030616150019135095,
+      "grad_norm": 2.658773183822632,
+      "learning_rate": 6.1068702290076346e-06,
+      "loss": 0.6948,
+      "step": 40
+    },
+    {
+      "epoch": 0.030616150019135095,
+      "eval_accuracy": 0.6787003610108303,
+      "eval_f1": 0.5,
+      "eval_loss": 0.6222203373908997,
+      "eval_precision": 0.5741935483870968,
+      "eval_recall": 0.4427860696517413,
+      "eval_runtime": 43.9963,
+      "eval_samples_per_second": 6.841,
+      "eval_steps_per_second": 0.227,
+      "step": 40
+    },
+    {
+      "epoch": 0.03138155376961347,
+      "grad_norm": 2.3062996864318848,
+      "learning_rate": 6.259541984732826e-06,
+      "loss": 0.7169,
+      "step": 41
+    },
+    {
+      "epoch": 0.03214695752009185,
+      "grad_norm": 2.899698495864868,
+      "learning_rate": 6.412213740458016e-06,
+      "loss": 0.65,
+      "step": 42
+    },
+    {
+      "epoch": 0.03291236127057023,
+      "grad_norm": 2.191978931427002,
+      "learning_rate": 6.564885496183207e-06,
+      "loss": 0.6741,
+      "step": 43
+    },
+    {
+      "epoch": 0.033677765021048606,
+      "grad_norm": 2.6911063194274902,
+      "learning_rate": 6.717557251908398e-06,
+      "loss": 0.652,
+      "step": 44
+    },
+    {
+      "epoch": 0.03444316877152698,
+      "grad_norm": 2.832355260848999,
+      "learning_rate": 6.870229007633589e-06,
+      "loss": 0.7163,
+      "step": 45
+    },
+    {
+      "epoch": 0.035208572522005356,
+      "grad_norm": 2.7549805641174316,
+      "learning_rate": 7.022900763358779e-06,
+      "loss": 0.6482,
+      "step": 46
+    },
+    {
+      "epoch": 0.035973976272483735,
+      "grad_norm": 2.533820390701294,
+      "learning_rate": 7.17557251908397e-06,
+      "loss": 0.6657,
+      "step": 47
+    },
+    {
+      "epoch": 0.03673938002296211,
+      "grad_norm": 2.542445182800293,
+      "learning_rate": 7.328244274809161e-06,
+      "loss": 0.6803,
+      "step": 48
+    },
+    {
+      "epoch": 0.03750478377344049,
+      "grad_norm": 2.254171848297119,
+      "learning_rate": 7.480916030534352e-06,
+      "loss": 0.6628,
+      "step": 49
+    },
+    {
+      "epoch": 0.038270187523918864,
+      "grad_norm": 2.2992422580718994,
+      "learning_rate": 7.633587786259543e-06,
+      "loss": 0.6237,
+      "step": 50
+    },
+    {
+      "epoch": 0.03903559127439724,
+      "grad_norm": 2.2923660278320312,
+      "learning_rate": 7.786259541984733e-06,
+      "loss": 0.636,
+      "step": 51
+    },
+    {
+      "epoch": 0.03980099502487562,
+      "grad_norm": 3.348690986633301,
+      "learning_rate": 7.938931297709924e-06,
+      "loss": 0.7033,
+      "step": 52
+    },
+    {
+      "epoch": 0.040566398775354,
+      "grad_norm": 2.794326066970825,
+      "learning_rate": 8.091603053435115e-06,
+      "loss": 0.7764,
+      "step": 53
+    },
+    {
+      "epoch": 0.04133180252583238,
+      "grad_norm": 2.662022352218628,
+      "learning_rate": 8.244274809160306e-06,
+      "loss": 0.6787,
+      "step": 54
+    },
+    {
+      "epoch": 0.04209720627631076,
+      "grad_norm": 2.623007297515869,
+      "learning_rate": 8.396946564885497e-06,
+      "loss": 0.6481,
+      "step": 55
+    },
+    {
+      "epoch": 0.04286261002678913,
+      "grad_norm": 2.626187801361084,
+      "learning_rate": 8.549618320610688e-06,
+      "loss": 0.5648,
+      "step": 56
+    },
+    {
+      "epoch": 0.04362801377726751,
+      "grad_norm": 3.5378401279449463,
+      "learning_rate": 8.702290076335879e-06,
+      "loss": 0.7537,
+      "step": 57
+    },
+    {
+      "epoch": 0.044393417527745886,
+      "grad_norm": 2.221616744995117,
+      "learning_rate": 8.85496183206107e-06,
+      "loss": 0.5946,
+      "step": 58
+    },
+    {
+      "epoch": 0.045158821278224265,
+      "grad_norm": 2.4003000259399414,
+      "learning_rate": 9.007633587786259e-06,
+      "loss": 0.6146,
+      "step": 59
+    },
+    {
+      "epoch": 0.045924225028702644,
+      "grad_norm": 3.179100751876831,
+      "learning_rate": 9.16030534351145e-06,
+      "loss": 0.6394,
+      "step": 60
+    },
+    {
+      "epoch": 0.045924225028702644,
+      "eval_accuracy": 0.6877256317689531,
+      "eval_f1": 0.4507936507936508,
+      "eval_loss": 0.6186545491218567,
+      "eval_precision": 0.6228070175438597,
+      "eval_recall": 0.35323383084577115,
+      "eval_runtime": 43.6865,
+      "eval_samples_per_second": 6.89,
+      "eval_steps_per_second": 0.229,
+      "step": 60
+    },
+    {
+      "epoch": 0.046689628779181015,
+      "grad_norm": 2.6747021675109863,
+      "learning_rate": 9.312977099236641e-06,
+      "loss": 0.6995,
+      "step": 61
+    },
+    {
+      "epoch": 0.047455032529659394,
+      "grad_norm": 2.2150821685791016,
+      "learning_rate": 9.465648854961834e-06,
+      "loss": 0.6553,
+      "step": 62
+    },
+    {
+      "epoch": 0.04822043628013777,
+      "grad_norm": 4.880781173706055,
+      "learning_rate": 9.618320610687025e-06,
+      "loss": 0.695,
+      "step": 63
+    },
+    {
+      "epoch": 0.04898584003061615,
+      "grad_norm": 2.353868007659912,
+      "learning_rate": 9.770992366412214e-06,
+      "loss": 0.6338,
+      "step": 64
+    },
+    {
+      "epoch": 0.04975124378109453,
+      "grad_norm": 2.5536489486694336,
+      "learning_rate": 9.923664122137405e-06,
+      "loss": 0.6623,
+      "step": 65
+    },
+    {
+      "epoch": 0.0505166475315729,
+      "grad_norm": 2.4389688968658447,
+      "learning_rate": 1.0076335877862595e-05,
+      "loss": 0.676,
+      "step": 66
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 2.0447139739990234,
+      "learning_rate": 1.0229007633587786e-05,
+      "loss": 0.5571,
+      "step": 67
+    },
+    {
+      "epoch": 0.05204745503252966,
+      "grad_norm": 2.9738974571228027,
+      "learning_rate": 1.0381679389312977e-05,
+      "loss": 0.7705,
+      "step": 68
+    },
+    {
+      "epoch": 0.05281285878300804,
+      "grad_norm": 2.7463932037353516,
+      "learning_rate": 1.0534351145038168e-05,
+      "loss": 0.6645,
+      "step": 69
+    },
+    {
+      "epoch": 0.053578262533486416,
+      "grad_norm": 2.617324113845825,
+      "learning_rate": 1.068702290076336e-05,
+      "loss": 0.6211,
+      "step": 70
+    },
+    {
+      "epoch": 0.05434366628396479,
+      "grad_norm": 2.629154920578003,
+      "learning_rate": 1.0839694656488552e-05,
+      "loss": 0.6189,
+      "step": 71
+    },
+    {
+      "epoch": 0.05510907003444317,
+      "grad_norm": 3.0344226360321045,
+      "learning_rate": 1.0992366412213743e-05,
+      "loss": 0.7318,
+      "step": 72
+    },
+    {
+      "epoch": 0.055874473784921545,
+      "grad_norm": 2.5670666694641113,
+      "learning_rate": 1.1145038167938934e-05,
+      "loss": 0.6702,
+      "step": 73
+    },
+    {
+      "epoch": 0.056639877535399924,
+      "grad_norm": 2.1741843223571777,
+      "learning_rate": 1.1297709923664125e-05,
+      "loss": 0.6686,
+      "step": 74
+    },
+    {
+      "epoch": 0.0574052812858783,
+      "grad_norm": 2.724057674407959,
+      "learning_rate": 1.1450381679389312e-05,
+      "loss": 0.6252,
+      "step": 75
+    },
+    {
+      "epoch": 0.05817068503635668,
+      "grad_norm": 2.225811719894409,
+      "learning_rate": 1.1603053435114503e-05,
+      "loss": 0.5888,
+      "step": 76
+    },
+    {
+      "epoch": 0.05893608878683505,
+      "grad_norm": 2.8234739303588867,
+      "learning_rate": 1.1755725190839696e-05,
+      "loss": 0.5833,
+      "step": 77
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 2.3463521003723145,
+      "learning_rate": 1.1908396946564887e-05,
+      "loss": 0.6519,
+      "step": 78
+    },
+    {
+      "epoch": 0.06046689628779181,
+      "grad_norm": 2.0764167308807373,
+      "learning_rate": 1.2061068702290078e-05,
+      "loss": 0.6022,
+      "step": 79
+    },
+    {
+      "epoch": 0.06123230003827019,
+      "grad_norm": 2.889023542404175,
+      "learning_rate": 1.2213740458015269e-05,
+      "loss": 0.6466,
+      "step": 80
+    },
+    {
+      "epoch": 0.06123230003827019,
+      "eval_accuracy": 0.7148014440433214,
+      "eval_f1": 0.5752688172043011,
+      "eval_loss": 0.5946354866027832,
+      "eval_precision": 0.6257309941520468,
+      "eval_recall": 0.5323383084577115,
+      "eval_runtime": 43.854,
+      "eval_samples_per_second": 6.864,
+      "eval_steps_per_second": 0.228,
+      "step": 80
+    },
+    {
+      "epoch": 0.06199770378874857,
+      "grad_norm": 2.1842238903045654,
+      "learning_rate": 1.236641221374046e-05,
+      "loss": 0.6137,
+      "step": 81
+    },
+    {
+      "epoch": 0.06276310753922694,
+      "grad_norm": 2.382739543914795,
+      "learning_rate": 1.2519083969465651e-05,
+      "loss": 0.5988,
+      "step": 82
+    },
+    {
+      "epoch": 0.06352851128970533,
+      "grad_norm": 2.536407470703125,
+      "learning_rate": 1.2671755725190839e-05,
+      "loss": 0.6698,
+      "step": 83
+    },
+    {
+      "epoch": 0.0642939150401837,
+      "grad_norm": 3.341318130493164,
+      "learning_rate": 1.2824427480916032e-05,
+      "loss": 0.632,
+      "step": 84
+    },
+    {
+      "epoch": 0.06505931879066207,
+      "grad_norm": 2.605912446975708,
+      "learning_rate": 1.2977099236641223e-05,
+      "loss": 0.6817,
+      "step": 85
+    },
+    {
+      "epoch": 0.06582472254114045,
+      "grad_norm": 2.7820451259613037,
+      "learning_rate": 1.3129770992366414e-05,
+      "loss": 0.5941,
+      "step": 86
+    },
+    {
+      "epoch": 0.06659012629161883,
+      "grad_norm": 2.19356632232666,
+      "learning_rate": 1.3282442748091605e-05,
+      "loss": 0.5755,
+      "step": 87
+    },
+    {
+      "epoch": 0.06735553004209721,
+      "grad_norm": 2.6070029735565186,
+      "learning_rate": 1.3435114503816796e-05,
+      "loss": 0.6472,
+      "step": 88
+    },
+    {
+      "epoch": 0.06812093379257558,
+      "grad_norm": 3.145352363586426,
+      "learning_rate": 1.3587786259541987e-05,
+      "loss": 0.6356,
+      "step": 89
+    },
+    {
+      "epoch": 0.06888633754305395,
+      "grad_norm": 2.909482955932617,
+      "learning_rate": 1.3740458015267178e-05,
+      "loss": 0.5926,
+      "step": 90
+    },
+    {
+      "epoch": 0.06965174129353234,
+      "grad_norm": 2.7917375564575195,
+      "learning_rate": 1.3893129770992369e-05,
+      "loss": 0.5445,
+      "step": 91
+    },
+    {
+      "epoch": 0.07041714504401071,
+      "grad_norm": 2.8729193210601807,
+      "learning_rate": 1.4045801526717558e-05,
+      "loss": 0.6508,
+      "step": 92
+    },
+    {
+      "epoch": 0.0711825487944891,
+      "grad_norm": 3.1102027893066406,
+      "learning_rate": 1.4198473282442749e-05,
+      "loss": 0.6189,
+      "step": 93
+    },
+    {
+      "epoch": 0.07194795254496747,
+      "grad_norm": 3.4606645107269287,
+      "learning_rate": 1.435114503816794e-05,
+      "loss": 0.5364,
+      "step": 94
+    },
+    {
+      "epoch": 0.07271335629544584,
+      "grad_norm": 2.350576877593994,
+      "learning_rate": 1.4503816793893131e-05,
+      "loss": 0.5593,
+      "step": 95
+    },
+    {
+      "epoch": 0.07347876004592423,
+      "grad_norm": 3.097646474838257,
+      "learning_rate": 1.4656488549618322e-05,
+      "loss": 0.72,
+      "step": 96
+    },
+    {
+      "epoch": 0.0742441637964026,
+      "grad_norm": 2.978395938873291,
+      "learning_rate": 1.4809160305343513e-05,
+      "loss": 0.648,
+      "step": 97
+    },
+    {
+      "epoch": 0.07500956754688098,
+      "grad_norm": 3.397475004196167,
+      "learning_rate": 1.4961832061068704e-05,
+      "loss": 0.5215,
+      "step": 98
+    },
+    {
+      "epoch": 0.07577497129735936,
+      "grad_norm": 2.8847622871398926,
+      "learning_rate": 1.5114503816793895e-05,
+      "loss": 0.5677,
+      "step": 99
+    },
+    {
+      "epoch": 0.07654037504783773,
+      "grad_norm": 2.4467875957489014,
+      "learning_rate": 1.5267175572519086e-05,
+      "loss": 0.5551,
+      "step": 100
+    },
+    {
+      "epoch": 0.07654037504783773,
+      "eval_accuracy": 0.7256317689530686,
+      "eval_f1": 0.6346153846153846,
+      "eval_loss": 0.5565891265869141,
+      "eval_precision": 0.6139534883720931,
+      "eval_recall": 0.6567164179104478,
+      "eval_runtime": 44.3839,
+      "eval_samples_per_second": 6.782,
+      "eval_steps_per_second": 0.225,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1306,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5277223846084608e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}