Training in progress, step 300, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e408bfee6bc720f2626f42236cb7ed47eed15851394e64745280cda47346a24
+oid sha256:0828710b640dbf68298e27271b529b25b9633dd7711dad19568b25686b79955f
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff316f99046dc065f6573097972dede0370afbf132b27b8c0122d95e707ef46
+oid sha256:09c7ac02ae4e3a773215b98acf254fe48c4e7de8555cfc804e4c8564253462d5
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff619163df21cd3fce301b8caa1204b04f12d8929b430f9ba8a93cc2b633db21
+oid sha256:9fe68aa5543c7e1858414222033d21efd3626ac60315b4e8919cae752773097c
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f0b1099d24eb7f394ea4f3fe171409b994687feddd6582b56703c5558366fc
+oid sha256:29b26a714efa8d1e7798d4d1a8c5ead91c9c253836ae76c8074e3b2d998b12ff
 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:ddc7713c77dfea2848b11f758cffc94b65fdb54736e77c0647082559d10aa06b
+oid sha256:c95f08281fb03852e4519ff6aa382f5c90ec236a0542a483b82c72cfa5ad848e
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6610841a05b9998513c9700bc4bead2bfbd262e59da6e4197d08b8fa080a9641
+oid sha256:dae344d3faf7510fb590a7e7eaf2cfc188c6927842e743a0272a1df1c56f789d
 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:f09233c56315737a8a0656ed9c80d92a6963808314b0fe48bf44cb8c6799ef3a
+oid sha256:d105c6f274366380374e805d8adf2ea780c3fcbf468ed3da0d30d931fdfebac8
 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:bebfedc8c1e6754606faa59b7c45e93ee3e4c7ec2913e3893c4695781b7892e7
+oid sha256:94b26738ea842513efa4609b1427f3c23b0d37d48ad0efdbd4bd1f4842bfb006
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f2fd9d1d3847bee68df39de96a06913e37dc3cacd6dcaa01e654f56e2f4eb49
+oid sha256:e68dcb3ef0e8b7c7d625ab213042156e023f2a245865d688db9dd4fe92f207dc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584d56bb430fe8df3c24eeab1822b6d753b2090cb92990956e81b8f8e3c6e416
+oid sha256:45b214c4a5ffd153814b8b271cfd3ef9fa8c2be4640619c8e4854dc05d7d1c97
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283174a53dfb12f541f1223f29dfd78957ef99fb6b3f708ac21ff4aa6e7733c3
+oid sha256:96a5e4dab35f0ee0b3a7f32c0e07341ebe72be8848c24cfaf9766b3fa46c7222
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f93a55b6907505dff041e23ee75d98392142bc1e2e39401947dac1e4fb011a
+oid sha256:8b62411f66602767298f963adc60824709fbed6ee64305b82501b466a1c44c9e
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ef6331ac4b2e8cf5bcc3f43391a2f41a0430eee842180c387f3d81fdad2fdc
+oid sha256:c8d986f9845c2c79697397af5a78c52fea0f5eb71ebc653676ec6d3ab1848325
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13531799729364005,
+  "epoch": 0.2029769959404601,
   "eval_steps": 20,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1539,6 +1539,766 @@
       "eval_samples_per_second": 5.74,
       "eval_steps_per_second": 0.193,
       "step": 200
+    },
+    {
+      "epoch": 0.13599458728010824,
+      "grad_norm": 2.476130247116089,
+      "learning_rate": 1.9921738005215687e-05,
+      "loss": 0.0617,
+      "step": 201
+    },
+    {
+      "epoch": 0.13667117726657646,
+      "grad_norm": 7.735743045806885,
+      "learning_rate": 1.9918760904111818e-05,
+      "loss": 0.252,
+      "step": 202
+    },
+    {
+      "epoch": 0.13734776725304465,
+      "grad_norm": 3.769490957260132,
+      "learning_rate": 1.991572846115666e-05,
+      "loss": 0.1439,
+      "step": 203
+    },
+    {
+      "epoch": 0.13802435723951287,
+      "grad_norm": 4.381724834442139,
+      "learning_rate": 1.9912640693269754e-05,
+      "loss": 0.2143,
+      "step": 204
+    },
+    {
+      "epoch": 0.13870094722598106,
+      "grad_norm": 3.511615037918091,
+      "learning_rate": 1.990949761767935e-05,
+      "loss": 0.1747,
+      "step": 205
+    },
+    {
+      "epoch": 0.13937753721244925,
+      "grad_norm": 5.647243499755859,
+      "learning_rate": 1.9906299251922273e-05,
+      "loss": 0.1904,
+      "step": 206
+    },
+    {
+      "epoch": 0.14005412719891747,
+      "grad_norm": 3.9160757064819336,
+      "learning_rate": 1.9903045613843844e-05,
+      "loss": 0.1816,
+      "step": 207
+    },
+    {
+      "epoch": 0.14073071718538566,
+      "grad_norm": 5.033432483673096,
+      "learning_rate": 1.9899736721597787e-05,
+      "loss": 0.141,
+      "step": 208
+    },
+    {
+      "epoch": 0.14140730717185385,
+      "grad_norm": 4.042255401611328,
+      "learning_rate": 1.9896372593646095e-05,
+      "loss": 0.2043,
+      "step": 209
+    },
+    {
+      "epoch": 0.14208389715832206,
+      "grad_norm": 7.3899149894714355,
+      "learning_rate": 1.989295324875897e-05,
+      "loss": 0.2182,
+      "step": 210
+    },
+    {
+      "epoch": 0.14276048714479025,
+      "grad_norm": 9.090564727783203,
+      "learning_rate": 1.9889478706014687e-05,
+      "loss": 0.2333,
+      "step": 211
+    },
+    {
+      "epoch": 0.14343707713125844,
+      "grad_norm": 4.3934526443481445,
+      "learning_rate": 1.9885948984799502e-05,
+      "loss": 0.2836,
+      "step": 212
+    },
+    {
+      "epoch": 0.14411366711772666,
+      "grad_norm": 3.89416766166687,
+      "learning_rate": 1.9882364104807536e-05,
+      "loss": 0.2256,
+      "step": 213
+    },
+    {
+      "epoch": 0.14479025710419485,
+      "grad_norm": 6.6705241203308105,
+      "learning_rate": 1.987872408604068e-05,
+      "loss": 0.2007,
+      "step": 214
+    },
+    {
+      "epoch": 0.14546684709066307,
+      "grad_norm": 9.201639175415039,
+      "learning_rate": 1.9875028948808457e-05,
+      "loss": 0.217,
+      "step": 215
+    },
+    {
+      "epoch": 0.14614343707713126,
+      "grad_norm": 3.3696377277374268,
+      "learning_rate": 1.9871278713727932e-05,
+      "loss": 0.1132,
+      "step": 216
+    },
+    {
+      "epoch": 0.14682002706359945,
+      "grad_norm": 3.9588944911956787,
+      "learning_rate": 1.9867473401723595e-05,
+      "loss": 0.2086,
+      "step": 217
+    },
+    {
+      "epoch": 0.14749661705006767,
+      "grad_norm": 5.10556173324585,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.1367,
+      "step": 218
+    },
+    {
+      "epoch": 0.14817320703653586,
+      "grad_norm": 3.8839104175567627,
+      "learning_rate": 1.9859697632177796e-05,
+      "loss": 0.1882,
+      "step": 219
+    },
+    {
+      "epoch": 0.14884979702300405,
+      "grad_norm": 3.7395753860473633,
+      "learning_rate": 1.985572721802134e-05,
+      "loss": 0.1228,
+      "step": 220
+    },
+    {
+      "epoch": 0.14884979702300405,
+      "eval_accuracy": 0.763302752293578,
+      "eval_f1": 0.3316062176165803,
+      "eval_loss": 0.49911028146743774,
+      "eval_precision": 0.7272727272727273,
+      "eval_recall": 0.21476510067114093,
+      "eval_runtime": 53.4724,
+      "eval_samples_per_second": 5.573,
+      "eval_steps_per_second": 0.187,
+      "step": 220
+    },
+    {
+      "epoch": 0.14952638700947227,
+      "grad_norm": 2.52254056930542,
+      "learning_rate": 1.9851701813710838e-05,
+      "loss": 0.1429,
+      "step": 221
+    },
+    {
+      "epoch": 0.15020297699594046,
+      "grad_norm": 2.212614059448242,
+      "learning_rate": 1.9847621441706076e-05,
+      "loss": 0.0924,
+      "step": 222
+    },
+    {
+      "epoch": 0.15087956698240865,
+      "grad_norm": 5.361288547515869,
+      "learning_rate": 1.9843486124773546e-05,
+      "loss": 0.1915,
+      "step": 223
+    },
+    {
+      "epoch": 0.15155615696887687,
+      "grad_norm": 5.06777286529541,
+      "learning_rate": 1.98392958859863e-05,
+      "loss": 0.2049,
+      "step": 224
+    },
+    {
+      "epoch": 0.15223274695534506,
+      "grad_norm": 2.5112369060516357,
+      "learning_rate": 1.9835050748723826e-05,
+      "loss": 0.1132,
+      "step": 225
+    },
+    {
+      "epoch": 0.15290933694181327,
+      "grad_norm": 3.829697847366333,
+      "learning_rate": 1.9830750736671923e-05,
+      "loss": 0.1766,
+      "step": 226
+    },
+    {
+      "epoch": 0.15358592692828146,
+      "grad_norm": 6.517053604125977,
+      "learning_rate": 1.982639587382256e-05,
+      "loss": 0.2742,
+      "step": 227
+    },
+    {
+      "epoch": 0.15426251691474965,
+      "grad_norm": 3.8287339210510254,
+      "learning_rate": 1.9821986184473757e-05,
+      "loss": 0.1686,
+      "step": 228
+    },
+    {
+      "epoch": 0.15493910690121787,
+      "grad_norm": 3.6989524364471436,
+      "learning_rate": 1.981752169322942e-05,
+      "loss": 0.1286,
+      "step": 229
+    },
+    {
+      "epoch": 0.15561569688768606,
+      "grad_norm": 4.2301788330078125,
+      "learning_rate": 1.981300242499924e-05,
+      "loss": 0.1242,
+      "step": 230
+    },
+    {
+      "epoch": 0.15629228687415425,
+      "grad_norm": 5.749031066894531,
+      "learning_rate": 1.9808428404998532e-05,
+      "loss": 0.2348,
+      "step": 231
+    },
+    {
+      "epoch": 0.15696887686062247,
+      "grad_norm": 4.1858744621276855,
+      "learning_rate": 1.9803799658748096e-05,
+      "loss": 0.1809,
+      "step": 232
+    },
+    {
+      "epoch": 0.15764546684709066,
+      "grad_norm": 2.808894157409668,
+      "learning_rate": 1.9799116212074077e-05,
+      "loss": 0.1228,
+      "step": 233
+    },
+    {
+      "epoch": 0.15832205683355885,
+      "grad_norm": 4.898924350738525,
+      "learning_rate": 1.9794378091107834e-05,
+      "loss": 0.1964,
+      "step": 234
+    },
+    {
+      "epoch": 0.15899864682002707,
+      "grad_norm": 4.328680038452148,
+      "learning_rate": 1.978958532228576e-05,
+      "loss": 0.1566,
+      "step": 235
+    },
+    {
+      "epoch": 0.15967523680649526,
+      "grad_norm": 4.020467758178711,
+      "learning_rate": 1.978473793234918e-05,
+      "loss": 0.2254,
+      "step": 236
+    },
+    {
+      "epoch": 0.16035182679296348,
+      "grad_norm": 2.9529521465301514,
+      "learning_rate": 1.977983594834416e-05,
+      "loss": 0.1425,
+      "step": 237
+    },
+    {
+      "epoch": 0.16102841677943167,
+      "grad_norm": 3.5832724571228027,
+      "learning_rate": 1.9774879397621387e-05,
+      "loss": 0.1848,
+      "step": 238
+    },
+    {
+      "epoch": 0.16170500676589986,
+      "grad_norm": 6.061310768127441,
+      "learning_rate": 1.9769868307835996e-05,
+      "loss": 0.1344,
+      "step": 239
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "grad_norm": 4.559755325317383,
+      "learning_rate": 1.9764802706947423e-05,
+      "loss": 0.1678,
+      "step": 240
+    },
+    {
+      "epoch": 0.16238159675236807,
+      "eval_accuracy": 0.763302752293578,
+      "eval_f1": 0.32105263157894737,
+      "eval_loss": 0.5306172966957092,
+      "eval_precision": 0.7439024390243902,
+      "eval_recall": 0.20469798657718122,
+      "eval_runtime": 52.6664,
+      "eval_samples_per_second": 5.658,
+      "eval_steps_per_second": 0.19,
+      "step": 240
+    },
+    {
+      "epoch": 0.16305818673883626,
+      "grad_norm": 4.202253818511963,
+      "learning_rate": 1.975968262321925e-05,
+      "loss": 0.1828,
+      "step": 241
+    },
+    {
+      "epoch": 0.16373477672530445,
+      "grad_norm": 4.026851654052734,
+      "learning_rate": 1.9754508085219057e-05,
+      "loss": 0.2173,
+      "step": 242
+    },
+    {
+      "epoch": 0.16441136671177267,
+      "grad_norm": 3.136077404022217,
+      "learning_rate": 1.9749279121818235e-05,
+      "loss": 0.1614,
+      "step": 243
+    },
+    {
+      "epoch": 0.16508795669824086,
+      "grad_norm": 3.726810932159424,
+      "learning_rate": 1.974399576219186e-05,
+      "loss": 0.1667,
+      "step": 244
+    },
+    {
+      "epoch": 0.16576454668470908,
+      "grad_norm": 5.430721282958984,
+      "learning_rate": 1.9738658035818495e-05,
+      "loss": 0.2158,
+      "step": 245
+    },
+    {
+      "epoch": 0.16644113667117727,
+      "grad_norm": 2.940300226211548,
+      "learning_rate": 1.973326597248006e-05,
+      "loss": 0.1664,
+      "step": 246
+    },
+    {
+      "epoch": 0.16711772665764546,
+      "grad_norm": 3.436058282852173,
+      "learning_rate": 1.972781960226163e-05,
+      "loss": 0.1944,
+      "step": 247
+    },
+    {
+      "epoch": 0.16779431664411368,
+      "grad_norm": 3.708514928817749,
+      "learning_rate": 1.9722318955551307e-05,
+      "loss": 0.1869,
+      "step": 248
+    },
+    {
+      "epoch": 0.16847090663058187,
+      "grad_norm": 5.172970771789551,
+      "learning_rate": 1.971676406304001e-05,
+      "loss": 0.219,
+      "step": 249
+    },
+    {
+      "epoch": 0.16914749661705006,
+      "grad_norm": 4.198179721832275,
+      "learning_rate": 1.9711154955721338e-05,
+      "loss": 0.1606,
+      "step": 250
+    },
+    {
+      "epoch": 0.16982408660351828,
+      "grad_norm": 4.068305969238281,
+      "learning_rate": 1.9705491664891368e-05,
+      "loss": 0.1952,
+      "step": 251
+    },
+    {
+      "epoch": 0.17050067658998647,
+      "grad_norm": 4.898702144622803,
+      "learning_rate": 1.969977422214851e-05,
+      "loss": 0.1904,
+      "step": 252
+    },
+    {
+      "epoch": 0.17117726657645466,
+      "grad_norm": 3.666128158569336,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 0.177,
+      "step": 253
+    },
+    {
+      "epoch": 0.17185385656292287,
+      "grad_norm": 3.7936861515045166,
+      "learning_rate": 1.968817700882826e-05,
+      "loss": 0.1003,
+      "step": 254
+    },
+    {
+      "epoch": 0.17253044654939106,
+      "grad_norm": 3.3366808891296387,
+      "learning_rate": 1.9682297302957666e-05,
+      "loss": 0.1729,
+      "step": 255
+    },
+    {
+      "epoch": 0.17320703653585928,
+      "grad_norm": 4.625013828277588,
+      "learning_rate": 1.9676363574587414e-05,
+      "loss": 0.2212,
+      "step": 256
+    },
+    {
+      "epoch": 0.17388362652232747,
+      "grad_norm": 4.048298358917236,
+      "learning_rate": 1.9670375856824823e-05,
+      "loss": 0.1301,
+      "step": 257
+    },
+    {
+      "epoch": 0.17456021650879566,
+      "grad_norm": 3.388268232345581,
+      "learning_rate": 1.966433418307843e-05,
+      "loss": 0.091,
+      "step": 258
+    },
+    {
+      "epoch": 0.17523680649526388,
+      "grad_norm": 3.287910223007202,
+      "learning_rate": 1.9658238587057832e-05,
+      "loss": 0.1748,
+      "step": 259
+    },
+    {
+      "epoch": 0.17591339648173207,
+      "grad_norm": 4.814307689666748,
+      "learning_rate": 1.9652089102773487e-05,
+      "loss": 0.2111,
+      "step": 260
+    },
+    {
+      "epoch": 0.17591339648173207,
+      "eval_accuracy": 0.763302752293578,
+      "eval_f1": 0.29120879120879123,
+      "eval_loss": 0.5758374333381653,
+      "eval_precision": 0.803030303030303,
+      "eval_recall": 0.17785234899328858,
+      "eval_runtime": 52.5901,
+      "eval_samples_per_second": 5.666,
+      "eval_steps_per_second": 0.19,
+      "step": 260
+    },
+    {
+      "epoch": 0.17658998646820026,
+      "grad_norm": 6.4831461906433105,
+      "learning_rate": 1.9645885764536522e-05,
+      "loss": 0.2182,
+      "step": 261
+    },
+    {
+      "epoch": 0.17726657645466848,
+      "grad_norm": 6.477516174316406,
+      "learning_rate": 1.9639628606958535e-05,
+      "loss": 0.2462,
+      "step": 262
+    },
+    {
+      "epoch": 0.17794316644113667,
+      "grad_norm": 3.73384690284729,
+      "learning_rate": 1.9633317664951418e-05,
+      "loss": 0.1425,
+      "step": 263
+    },
+    {
+      "epoch": 0.17861975642760486,
+      "grad_norm": 4.063915252685547,
+      "learning_rate": 1.962695297372715e-05,
+      "loss": 0.1388,
+      "step": 264
+    },
+    {
+      "epoch": 0.17929634641407308,
+      "grad_norm": 4.379425048828125,
+      "learning_rate": 1.962053456879761e-05,
+      "loss": 0.1929,
+      "step": 265
+    },
+    {
+      "epoch": 0.17997293640054127,
+      "grad_norm": 3.696601629257202,
+      "learning_rate": 1.9614062485974364e-05,
+      "loss": 0.1795,
+      "step": 266
+    },
+    {
+      "epoch": 0.18064952638700948,
+      "grad_norm": 4.814270973205566,
+      "learning_rate": 1.9607536761368484e-05,
+      "loss": 0.1906,
+      "step": 267
+    },
+    {
+      "epoch": 0.18132611637347767,
+      "grad_norm": 4.517858028411865,
+      "learning_rate": 1.960095743139033e-05,
+      "loss": 0.1902,
+      "step": 268
+    },
+    {
+      "epoch": 0.18200270635994586,
+      "grad_norm": 4.473437309265137,
+      "learning_rate": 1.9594324532749353e-05,
+      "loss": 0.1581,
+      "step": 269
+    },
+    {
+      "epoch": 0.18267929634641408,
+      "grad_norm": 6.359562873840332,
+      "learning_rate": 1.95876381024539e-05,
+      "loss": 0.2641,
+      "step": 270
+    },
+    {
+      "epoch": 0.18335588633288227,
+      "grad_norm": 5.020825386047363,
+      "learning_rate": 1.958089817781099e-05,
+      "loss": 0.1734,
+      "step": 271
+    },
+    {
+      "epoch": 0.18403247631935046,
+      "grad_norm": 5.725416660308838,
+      "learning_rate": 1.9574104796426124e-05,
+      "loss": 0.2771,
+      "step": 272
+    },
+    {
+      "epoch": 0.18470906630581868,
+      "grad_norm": 3.2466204166412354,
+      "learning_rate": 1.956725799620305e-05,
+      "loss": 0.1493,
+      "step": 273
+    },
+    {
+      "epoch": 0.18538565629228687,
+      "grad_norm": 4.315434455871582,
+      "learning_rate": 1.9560357815343577e-05,
+      "loss": 0.1879,
+      "step": 274
+    },
+    {
+      "epoch": 0.18606224627875506,
+      "grad_norm": 4.0321245193481445,
+      "learning_rate": 1.9553404292347356e-05,
+      "loss": 0.1276,
+      "step": 275
+    },
+    {
+      "epoch": 0.18673883626522328,
+      "grad_norm": 3.7112905979156494,
+      "learning_rate": 1.9546397466011654e-05,
+      "loss": 0.173,
+      "step": 276
+    },
+    {
+      "epoch": 0.18741542625169147,
+      "grad_norm": 5.85778284072876,
+      "learning_rate": 1.9539337375431144e-05,
+      "loss": 0.3178,
+      "step": 277
+    },
+    {
+      "epoch": 0.1880920162381597,
+      "grad_norm": 5.455870151519775,
+      "learning_rate": 1.9532224059997693e-05,
+      "loss": 0.1971,
+      "step": 278
+    },
+    {
+      "epoch": 0.18876860622462788,
+      "grad_norm": 3.5191891193389893,
+      "learning_rate": 1.9525057559400134e-05,
+      "loss": 0.165,
+      "step": 279
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "grad_norm": 4.080350399017334,
+      "learning_rate": 1.9517837913624048e-05,
+      "loss": 0.115,
+      "step": 280
+    },
+    {
+      "epoch": 0.18944519621109607,
+      "eval_accuracy": 0.7706422018348624,
+      "eval_f1": 0.3315508021390374,
+      "eval_loss": 0.49153777956962585,
+      "eval_precision": 0.8157894736842105,
+      "eval_recall": 0.2080536912751678,
+      "eval_runtime": 53.3463,
+      "eval_samples_per_second": 5.586,
+      "eval_steps_per_second": 0.187,
+      "step": 280
+    },
+    {
+      "epoch": 0.19012178619756429,
+      "grad_norm": 3.4508748054504395,
+      "learning_rate": 1.9510565162951538e-05,
+      "loss": 0.1461,
+      "step": 281
+    },
+    {
+      "epoch": 0.19079837618403248,
+      "grad_norm": 5.258754253387451,
+      "learning_rate": 1.9503239347961006e-05,
+      "loss": 0.2396,
+      "step": 282
+    },
+    {
+      "epoch": 0.19147496617050067,
+      "grad_norm": 5.140385627746582,
+      "learning_rate": 1.9495860509526935e-05,
+      "loss": 0.1444,
+      "step": 283
+    },
+    {
+      "epoch": 0.19215155615696888,
+      "grad_norm": 1.9280897378921509,
+      "learning_rate": 1.948842868881964e-05,
+      "loss": 0.1426,
+      "step": 284
+    },
+    {
+      "epoch": 0.19282814614343707,
+      "grad_norm": 2.6845431327819824,
+      "learning_rate": 1.948094392730506e-05,
+      "loss": 0.1702,
+      "step": 285
+    },
+    {
+      "epoch": 0.19350473612990526,
+      "grad_norm": 2.7291038036346436,
+      "learning_rate": 1.9473406266744518e-05,
+      "loss": 0.1525,
+      "step": 286
+    },
+    {
+      "epoch": 0.19418132611637348,
+      "grad_norm": 2.8851161003112793,
+      "learning_rate": 1.9465815749194482e-05,
+      "loss": 0.1419,
+      "step": 287
+    },
+    {
+      "epoch": 0.19485791610284167,
+      "grad_norm": 3.973231554031372,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.1782,
+      "step": 288
+    },
+    {
+      "epoch": 0.1955345060893099,
+      "grad_norm": 5.708676338195801,
+      "learning_rate": 1.9450476312826178e-05,
+      "loss": 0.1396,
+      "step": 289
+    },
+    {
+      "epoch": 0.19621109607577808,
+      "grad_norm": 3.4198830127716064,
+      "learning_rate": 1.9442727479594486e-05,
+      "loss": 0.1762,
+      "step": 290
+    },
+    {
+      "epoch": 0.19688768606224627,
+      "grad_norm": 5.898075103759766,
+      "learning_rate": 1.9434925960545978e-05,
+      "loss": 0.213,
+      "step": 291
+    },
+    {
+      "epoch": 0.1975642760487145,
+      "grad_norm": 5.121380805969238,
+      "learning_rate": 1.9427071799209335e-05,
+      "loss": 0.2684,
+      "step": 292
+    },
+    {
+      "epoch": 0.19824086603518268,
+      "grad_norm": 5.1736931800842285,
+      "learning_rate": 1.941916503940694e-05,
+      "loss": 0.2272,
+      "step": 293
+    },
+    {
+      "epoch": 0.19891745602165087,
+      "grad_norm": 3.988576650619507,
+      "learning_rate": 1.941120572525467e-05,
+      "loss": 0.2007,
+      "step": 294
+    },
+    {
+      "epoch": 0.19959404600811909,
+      "grad_norm": 6.444464683532715,
+      "learning_rate": 1.9403193901161614e-05,
+      "loss": 0.2243,
+      "step": 295
+    },
+    {
+      "epoch": 0.20027063599458728,
+      "grad_norm": 3.4448323249816895,
+      "learning_rate": 1.9395129611829844e-05,
+      "loss": 0.1175,
+      "step": 296
+    },
+    {
+      "epoch": 0.2009472259810555,
+      "grad_norm": 7.464962005615234,
+      "learning_rate": 1.9387012902254165e-05,
+      "loss": 0.2362,
+      "step": 297
+    },
+    {
+      "epoch": 0.20162381596752368,
+      "grad_norm": 4.778014183044434,
+      "learning_rate": 1.9378843817721856e-05,
+      "loss": 0.1657,
+      "step": 298
+    },
+    {
+      "epoch": 0.20230040595399187,
+      "grad_norm": 4.121883392333984,
+      "learning_rate": 1.937062240381243e-05,
+      "loss": 0.1339,
+      "step": 299
+    },
+    {
+      "epoch": 0.2029769959404601,
+      "grad_norm": 5.5182576179504395,
+      "learning_rate": 1.9362348706397374e-05,
+      "loss": 0.1785,
+      "step": 300
+    },
+    {
+      "epoch": 0.2029769959404601,
+      "eval_accuracy": 0.773394495412844,
+      "eval_f1": 0.35170603674540685,
+      "eval_loss": 0.5283112525939941,
+      "eval_precision": 0.8072289156626506,
+      "eval_recall": 0.22483221476510068,
+      "eval_runtime": 51.5451,
+      "eval_samples_per_second": 5.781,
+      "eval_steps_per_second": 0.194,
+      "step": 300
     }
   ],
   "logging_steps": 1,
@@ -1558,7 +2318,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.053734571520819e+16,
+  "total_flos": 9.054635921978163e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null