Training in progress, step 348, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa94ec7fc25e7a6ee26ffbbee034689965f336821b064b9f9e0f5dc2f6c05a21
+oid sha256:99fe370c2f00762cd74b9cb5aec9aa42f07d787132197749629db88fcf2aec33
 size 27566236

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442607c5229133e53cd00ee913ff5d44cebaf82c6c20f843b24d268fb4a436af
+oid sha256:6f3036f71fb4fd6c846f1cdc90056395da95de0fd5098ff1e73a878cada04312
 size 27630900

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8d46607d03e57c5376b8610387ec2fcd94514faf917ee762afcbbb96dc811b
+oid sha256:6af6def5736b32ebbd0c4bfff61dd50ea286783ffbdf0a68f88ecc4fd9de8fac
 size 27622392

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459e2897a31e6241cdd6bb0e2e2ba82db83a9a33d01874d52b25108986341565
+oid sha256:854e6cd413fe017412c2a23609972d95a9f49d7b17bbf96772c906a93d68179a
 size 27622392

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4cd00ad97e87fe831d1bdd5ce43db8c2cd9365cf21907f488bae601ba88367
+oid sha256:a0e39d219947f97fb0697e09ca03ada80fea6ebd2d2f7398d49d92cd29fba84b
 size 13782528

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6299f59ecc2a7b18770108f685e07e657c3c9e93ace7b10cbbaeca1a530f4c90
+oid sha256:44eadd3bf4caa7c7cd81bf6e5ef4ed2272c95a1d6750dd0c1ce498f64f5df152
 size 13782528

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9868d8cd622192535fce3348430733d8e14fcbe9d92ed5bbb4ad802e3299996
+oid sha256:2dd2651be51deeb4f5349f12e8814303c3186d56477216518cd4eba83ad053ca
 size 13782528

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b8d30fea35f5dc3498b7f3e5ffb9dd3408ba45c34eb925feec55d7455ab343f
+oid sha256:6162de5d036d94f4c618c02a3e3791f8579e2111accaf85f18eb469017f56675
 size 13782528

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6185843c50764de20922699c89193c33e1e13037719a5d55479aa190e715e4fc
+oid sha256:269eae03847773cb4bd93a4517a905853bc54a68269b815c31577215fdc55d2d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e51ecf57078c2d652964726d8abc8157e10e9fdddf8cacb5700305b465147a
+oid sha256:d187c3af11ce3a881345c7efd9082ca0cb36a6949dfbe3343c996f42f2afc3e6
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe10fe55b3a58ae13fa7a58fca8f2486fa82c4aa360522ee9cde43cc43ba473
+oid sha256:344fb25f2c262f28ced1e24ddcd208e4806d9788cdec5b2a7f2397013b68c284
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcda73faaa8d5a9ab0a72d2fef1c1af0341c8e7f8ec0eede744acae39dd22f43
+oid sha256:805247d87233bfa93147263830dc68344cf75f632c10a49edc8486147debfef7
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e47edb1b664bc04c493b0996774157c1ffdb9f0b12df515a0b32829d748704
+oid sha256:2d015d34b7739a1124fe31968c605ff2948a6a921eb3374a8e282b0787486605
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8620689655172413,
+  "epoch": 1.0,
   "eval_steps": 20,
-  "global_step": 300,
+  "global_step": 348,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2299,6 +2299,366 @@
       "eval_samples_per_second": 6.3,
       "eval_steps_per_second": 0.238,
       "step": 300
+    },
+    {
+      "epoch": 0.8649425287356322,
+      "grad_norm": 1.617297649383545,
+      "learning_rate": 1.0922142398186097e-06,
+      "loss": 0.2681,
+      "step": 301
+    },
+    {
+      "epoch": 0.867816091954023,
+      "grad_norm": 2.8231587409973145,
+      "learning_rate": 1.0470516257959351e-06,
+      "loss": 0.2958,
+      "step": 302
+    },
+    {
+      "epoch": 0.8706896551724138,
+      "grad_norm": 1.7231059074401855,
+      "learning_rate": 1.00279094316854e-06,
+      "loss": 0.2739,
+      "step": 303
+    },
+    {
+      "epoch": 0.8735632183908046,
+      "grad_norm": 2.3094263076782227,
+      "learning_rate": 9.594366508138352e-07,
+      "loss": 0.3014,
+      "step": 304
+    },
+    {
+      "epoch": 0.8764367816091954,
+      "grad_norm": 2.9980764389038086,
+      "learning_rate": 9.169931162983137e-07,
+      "loss": 0.2781,
+      "step": 305
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 2.005481243133545,
+      "learning_rate": 8.754646154375801e-07,
+      "loss": 0.2592,
+      "step": 306
+    },
+    {
+      "epoch": 0.882183908045977,
+      "grad_norm": 2.7463858127593994,
+      "learning_rate": 8.348553318655795e-07,
+      "loss": 0.3159,
+      "step": 307
+    },
+    {
+      "epoch": 0.8850574712643678,
+      "grad_norm": 2.01882266998291,
+      "learning_rate": 7.951693566131325e-07,
+      "loss": 0.3136,
+      "step": 308
+    },
+    {
+      "epoch": 0.8879310344827587,
+      "grad_norm": 1.7923675775527954,
+      "learning_rate": 7.564106876958188e-07,
+      "loss": 0.2936,
+      "step": 309
+    },
+    {
+      "epoch": 0.8908045977011494,
+      "grad_norm": 2.2415239810943604,
+      "learning_rate": 7.185832297111939e-07,
+      "loss": 0.3882,
+      "step": 310
+    },
+    {
+      "epoch": 0.8936781609195402,
+      "grad_norm": 1.7161551713943481,
+      "learning_rate": 6.816907934454353e-07,
+      "loss": 0.2533,
+      "step": 311
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.019099712371826,
+      "learning_rate": 6.457370954894582e-07,
+      "loss": 0.2335,
+      "step": 312
+    },
+    {
+      "epoch": 0.8994252873563219,
+      "grad_norm": 2.187922477722168,
+      "learning_rate": 6.107257578644721e-07,
+      "loss": 0.2695,
+      "step": 313
+    },
+    {
+      "epoch": 0.9022988505747126,
+      "grad_norm": 1.7923535108566284,
+      "learning_rate": 5.766603076571164e-07,
+      "loss": 0.2652,
+      "step": 314
+    },
+    {
+      "epoch": 0.9051724137931034,
+      "grad_norm": 1.9885005950927734,
+      "learning_rate": 5.43544176664137e-07,
+      "loss": 0.2851,
+      "step": 315
+    },
+    {
+      "epoch": 0.9080459770114943,
+      "grad_norm": 1.9837305545806885,
+      "learning_rate": 5.113807010466432e-07,
+      "loss": 0.2884,
+      "step": 316
+    },
+    {
+      "epoch": 0.9109195402298851,
+      "grad_norm": 2.307769536972046,
+      "learning_rate": 4.801731209940375e-07,
+      "loss": 0.2827,
+      "step": 317
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 2.077484130859375,
+      "learning_rate": 4.499245803975927e-07,
+      "loss": 0.2686,
+      "step": 318
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 2.722639799118042,
+      "learning_rate": 4.206381265337189e-07,
+      "loss": 0.301,
+      "step": 319
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "grad_norm": 2.3338513374328613,
+      "learning_rate": 3.9231670975699354e-07,
+      "loss": 0.3223,
+      "step": 320
+    },
+    {
+      "epoch": 0.9195402298850575,
+      "eval_accuracy": 0.8613861386138614,
+      "eval_f1": 0.7407407407407407,
+      "eval_loss": 0.3157050609588623,
+      "eval_precision": 0.7272727272727273,
+      "eval_recall": 0.7547169811320755,
+      "eval_runtime": 16.7717,
+      "eval_samples_per_second": 6.32,
+      "eval_steps_per_second": 0.238,
+      "step": 320
+    },
+    {
+      "epoch": 0.9224137931034483,
+      "grad_norm": 3.109226942062378,
+      "learning_rate": 3.649631832029288e-07,
+      "loss": 0.3366,
+      "step": 321
+    },
+    {
+      "epoch": 0.9252873563218391,
+      "grad_norm": 1.830435872077942,
+      "learning_rate": 3.385803025005463e-07,
+      "loss": 0.277,
+      "step": 322
+    },
+    {
+      "epoch": 0.9281609195402298,
+      "grad_norm": 2.406721591949463,
+      "learning_rate": 3.1317072549477246e-07,
+      "loss": 0.3517,
+      "step": 323
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.0932199954986572,
+      "learning_rate": 2.887370119786792e-07,
+      "loss": 0.2832,
+      "step": 324
+    },
+    {
+      "epoch": 0.9339080459770115,
+      "grad_norm": 2.193326473236084,
+      "learning_rate": 2.6528162343561593e-07,
+      "loss": 0.3269,
+      "step": 325
+    },
+    {
+      "epoch": 0.9367816091954023,
+      "grad_norm": 2.217686653137207,
+      "learning_rate": 2.4280692279122554e-07,
+      "loss": 0.2642,
+      "step": 326
+    },
+    {
+      "epoch": 0.9396551724137931,
+      "grad_norm": 1.9883277416229248,
+      "learning_rate": 2.2131517417540937e-07,
+      "loss": 0.2929,
+      "step": 327
+    },
+    {
+      "epoch": 0.9425287356321839,
+      "grad_norm": 2.0583817958831787,
+      "learning_rate": 2.00808542694233e-07,
+      "loss": 0.2886,
+      "step": 328
+    },
+    {
+      "epoch": 0.9454022988505747,
+      "grad_norm": 1.7167632579803467,
+      "learning_rate": 1.8128909421180506e-07,
+      "loss": 0.2528,
+      "step": 329
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 1.9056061506271362,
+      "learning_rate": 1.6275879514217052e-07,
+      "loss": 0.3133,
+      "step": 330
+    },
+    {
+      "epoch": 0.9511494252873564,
+      "grad_norm": 2.4173924922943115,
+      "learning_rate": 1.4521951225120345e-07,
+      "loss": 0.3712,
+      "step": 331
+    },
+    {
+      "epoch": 0.9540229885057471,
+      "grad_norm": 1.6717036962509155,
+      "learning_rate": 1.2867301246854757e-07,
+      "loss": 0.2764,
+      "step": 332
+    },
+    {
+      "epoch": 0.9568965517241379,
+      "grad_norm": 1.7265243530273438,
+      "learning_rate": 1.1312096270961525e-07,
+      "loss": 0.2683,
+      "step": 333
+    },
+    {
+      "epoch": 0.9597701149425287,
+      "grad_norm": 1.933962345123291,
+      "learning_rate": 9.856492970766296e-08,
+      "loss": 0.3035,
+      "step": 334
+    },
+    {
+      "epoch": 0.9626436781609196,
+      "grad_norm": 1.7811708450317383,
+      "learning_rate": 8.50063798559475e-08,
+      "loss": 0.2747,
+      "step": 335
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 2.420718193054199,
+      "learning_rate": 7.244667906001202e-08,
+      "loss": 0.2595,
+      "step": 336
+    },
+    {
+      "epoch": 0.9683908045977011,
+      "grad_norm": 2.360978841781616,
+      "learning_rate": 6.088709260007153e-08,
+      "loss": 0.2845,
+      "step": 337
+    },
+    {
+      "epoch": 0.9712643678160919,
+      "grad_norm": 1.8564136028289795,
+      "learning_rate": 5.032878500355498e-08,
+      "loss": 0.2868,
+      "step": 338
+    },
+    {
+      "epoch": 0.9741379310344828,
+      "grad_norm": 3.320560932159424,
+      "learning_rate": 4.07728199277857e-08,
+      "loss": 0.298,
+      "step": 339
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "grad_norm": 3.1737234592437744,
+      "learning_rate": 3.2220160052828245e-08,
+      "loss": 0.3448,
+      "step": 340
+    },
+    {
+      "epoch": 0.9770114942528736,
+      "eval_accuracy": 0.8613861386138614,
+      "eval_f1": 0.7407407407407407,
+      "eval_loss": 0.31532150506973267,
+      "eval_precision": 0.7272727272727273,
+      "eval_recall": 0.7547169811320755,
+      "eval_runtime": 17.2915,
+      "eval_samples_per_second": 6.13,
+      "eval_steps_per_second": 0.231,
+      "step": 340
+    },
+    {
+      "epoch": 0.9798850574712644,
+      "grad_norm": 1.8069976568222046,
+      "learning_rate": 2.467166698450485e-08,
+      "loss": 0.2825,
+      "step": 341
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 2.923757314682007,
+      "learning_rate": 1.812810116760044e-08,
+      "loss": 0.2836,
+      "step": 342
+    },
+    {
+      "epoch": 0.985632183908046,
+      "grad_norm": 3.138817310333252,
+      "learning_rate": 1.2590121809247235e-08,
+      "loss": 0.3312,
+      "step": 343
+    },
+    {
+      "epoch": 0.9885057471264368,
+      "grad_norm": 1.6502025127410889,
+      "learning_rate": 8.05828681252452e-09,
+      "loss": 0.2625,
+      "step": 344
+    },
+    {
+      "epoch": 0.9913793103448276,
+      "grad_norm": 2.4544200897216797,
+      "learning_rate": 4.5330527202480656e-09,
+      "loss": 0.3451,
+      "step": 345
+    },
+    {
+      "epoch": 0.9942528735632183,
+      "grad_norm": 1.9814451932907104,
+      "learning_rate": 2.014774668979147e-09,
+      "loss": 0.2715,
+      "step": 346
+    },
+    {
+      "epoch": 0.9971264367816092,
+      "grad_norm": 2.851459503173828,
+      "learning_rate": 5.037063532498109e-10,
+      "loss": 0.3053,
+      "step": 347
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.8435858488082886,
+      "learning_rate": 0.0,
+      "loss": 0.2909,
+      "step": 348
     }
   ],
   "logging_steps": 1,
@@ -2313,12 +2673,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.4768839882965e+16,
+  "total_flos": 1.1002361050405274e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null