Training in progress, step 776, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8a9b5df6415cf6aaf2fbd963784ca2798906e60cec2a4d96cedf776b0170bd5
+oid sha256:9c9812233963d91f939967280f1fb8dadd8814b762a867032b3f1837b1d53052
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a477ffe7b31b769212a07b084cb1d6fd6244ebaf19a4d7d0e204d6e487b1aa1c
+oid sha256:7c88e2b1f68ece33ec06a916e5bb00b720c1f8a904961de7eb56d64a799fab9f
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bf1d290ebbe8581c52d47ca6e510d907a2305a5eebfef589fed6462f44754f
+oid sha256:f4d35b958384213145c1212e288e3c8343f840167644866a5b9157967625e8fb
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:863d7a925082ef890f7e9f5fe37f69a475fb3c8a749f7db0ba29e80f4b2757d1
+oid sha256:1899dca709a2035b39b51d9a6ee7e6219b311be55baca81d0f0aea25b360adcf
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f0fee06777bc54d20e8cfadf02e1fcf062878ec77c27273222f443590d3ca7
+oid sha256:eee5f9be012755d9da3db6b768bd75a664482268608ec40525ff012db7c716fa
 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:b6b4dadb656bd2f818f65eedb04bde289d144e274b64e185d6aa6038f82edc5b
+oid sha256:4101704947e1bc12f0b2d183919dbd5c6423744d74a9e9bced6f9f568c741cdd
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6714a698672b2edbe18148b125be564081dbe0c32820c4d2862c9ebbfc701d39
+oid sha256:69971347771fed00d279e6b4731b6a18fff227ba1765979d94a1881fd74613ed
 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:f9f0d3ac60ec2c909466305ff9424e3153bb7f95f5b685220572eb0bd2fe45e0
+oid sha256:23d8a7e8405e5f6c5c83bae18e57f014dc7bbbf960c7bbe1c96315c1f7b18576
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6a53af4113d719a74be72b9b96e06ddfcf589f1c186482a58b06d91bc3e4d34
+oid sha256:ecbf30739d47702ff1dc62fda61a8b804166ddf0362f853a15764a0f6ca810ca
 size 15088

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f79573df50dcf97b1bf70e5483cf9597da1b8a05214eb274fc3c3833cf3ad5
+oid sha256:62ea2caeae1f19550ff4c866c756827368743f8de236623a1b0db1ace7686574
 size 15088

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80c1cfb5ea86276cd48dd4a859d36d824a2fd5563d437a8a0c4be3eb6200b32
+oid sha256:c1c459f1b116355fb0f3bdc3f65b9adc53657df08c616f375c6b5ee9a3f2a5eb
 size 15088

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714110b482b507e1fb6219bf62e8ec1001b632b03d77db23a105560f7b48af04
+oid sha256:6e129f010772342f4e564c483d7381dc6b23561fca445914ea8c159bc5d7a2ed
 size 15088

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b38c3c47d3e1cfb698a7e53778b8d216b765546387a9e6bd3f149bea8249062
+oid sha256:836d724299dd150551400174e98221fb5b90ef0e07f83661da8beb5333f31043
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9020618556701031,
+  "epoch": 1.0,
   "eval_steps": 20,
-  "global_step": 700,
+  "global_step": 776,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5339,6 +5339,574 @@
       "eval_samples_per_second": 5.436,
       "eval_steps_per_second": 0.179,
       "step": 700
+    },
+    {
+      "epoch": 0.9033505154639175,
+      "grad_norm": 4.556031703948975,
+      "learning_rate": 5.643565211494285e-07,
+      "loss": 0.041,
+      "step": 701
+    },
+    {
+      "epoch": 0.904639175257732,
+      "grad_norm": 0.027816738933324814,
+      "learning_rate": 5.495458148283505e-07,
+      "loss": 0.0002,
+      "step": 702
+    },
+    {
+      "epoch": 0.9059278350515464,
+      "grad_norm": 0.04451802000403404,
+      "learning_rate": 5.349265521053603e-07,
+      "loss": 0.0002,
+      "step": 703
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 1.494473934173584,
+      "learning_rate": 5.204990291317535e-07,
+      "loss": 0.003,
+      "step": 704
+    },
+    {
+      "epoch": 0.9085051546391752,
+      "grad_norm": 2.967031955718994,
+      "learning_rate": 5.062635381746362e-07,
+      "loss": 0.0254,
+      "step": 705
+    },
+    {
+      "epoch": 0.9097938144329897,
+      "grad_norm": 0.6380704045295715,
+      "learning_rate": 4.92220367611006e-07,
+      "loss": 0.0036,
+      "step": 706
+    },
+    {
+      "epoch": 0.9110824742268041,
+      "grad_norm": 0.40568777918815613,
+      "learning_rate": 4.783698019219118e-07,
+      "loss": 0.0014,
+      "step": 707
+    },
+    {
+      "epoch": 0.9123711340206185,
+      "grad_norm": 3.13850736618042,
+      "learning_rate": 4.647121216866857e-07,
+      "loss": 0.0343,
+      "step": 708
+    },
+    {
+      "epoch": 0.913659793814433,
+      "grad_norm": 1.518782377243042,
+      "learning_rate": 4.512476035772628e-07,
+      "loss": 0.0098,
+      "step": 709
+    },
+    {
+      "epoch": 0.9149484536082474,
+      "grad_norm": 0.19677811861038208,
+      "learning_rate": 4.3797652035257544e-07,
+      "loss": 0.0016,
+      "step": 710
+    },
+    {
+      "epoch": 0.9162371134020618,
+      "grad_norm": 1.9592320919036865,
+      "learning_rate": 4.248991408530279e-07,
+      "loss": 0.0126,
+      "step": 711
+    },
+    {
+      "epoch": 0.9175257731958762,
+      "grad_norm": 0.1629909873008728,
+      "learning_rate": 4.1201572999505e-07,
+      "loss": 0.0004,
+      "step": 712
+    },
+    {
+      "epoch": 0.9188144329896907,
+      "grad_norm": 5.022075653076172,
+      "learning_rate": 3.9932654876573164e-07,
+      "loss": 0.0158,
+      "step": 713
+    },
+    {
+      "epoch": 0.9201030927835051,
+      "grad_norm": 0.3693143427371979,
+      "learning_rate": 3.8683185421753313e-07,
+      "loss": 0.0014,
+      "step": 714
+    },
+    {
+      "epoch": 0.9213917525773195,
+      "grad_norm": 1.231784462928772,
+      "learning_rate": 3.74531899463082e-07,
+      "loss": 0.0082,
+      "step": 715
+    },
+    {
+      "epoch": 0.9226804123711341,
+      "grad_norm": 0.04480728134512901,
+      "learning_rate": 3.6242693367004365e-07,
+      "loss": 0.0002,
+      "step": 716
+    },
+    {
+      "epoch": 0.9239690721649485,
+      "grad_norm": 0.14905039966106415,
+      "learning_rate": 3.5051720205606877e-07,
+      "loss": 0.0009,
+      "step": 717
+    },
+    {
+      "epoch": 0.9252577319587629,
+      "grad_norm": 0.11093373596668243,
+      "learning_rate": 3.38802945883836e-07,
+      "loss": 0.0008,
+      "step": 718
+    },
+    {
+      "epoch": 0.9265463917525774,
+      "grad_norm": 1.7350820302963257,
+      "learning_rate": 3.2728440245615724e-07,
+      "loss": 0.0041,
+      "step": 719
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 4.958645343780518,
+      "learning_rate": 3.1596180511117235e-07,
+      "loss": 0.0122,
+      "step": 720
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.01316594984382391,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.875,
+      "eval_samples_per_second": 5.298,
+      "eval_steps_per_second": 0.175,
+      "step": 720
+    },
+    {
+      "epoch": 0.9291237113402062,
+      "grad_norm": 3.578312873840332,
+      "learning_rate": 3.048353832176221e-07,
+      "loss": 0.0234,
+      "step": 721
+    },
+    {
+      "epoch": 0.9304123711340206,
+      "grad_norm": 0.2854086756706238,
+      "learning_rate": 2.939053621702015e-07,
+      "loss": 0.0011,
+      "step": 722
+    },
+    {
+      "epoch": 0.9317010309278351,
+      "grad_norm": 2.446420907974243,
+      "learning_rate": 2.83171963384995e-07,
+      "loss": 0.0121,
+      "step": 723
+    },
+    {
+      "epoch": 0.9329896907216495,
+      "grad_norm": 3.754582643508911,
+      "learning_rate": 2.7263540429498747e-07,
+      "loss": 0.0285,
+      "step": 724
+    },
+    {
+      "epoch": 0.9342783505154639,
+      "grad_norm": 1.2466968297958374,
+      "learning_rate": 2.6229589834566807e-07,
+      "loss": 0.0334,
+      "step": 725
+    },
+    {
+      "epoch": 0.9355670103092784,
+      "grad_norm": 4.552764415740967,
+      "learning_rate": 2.5215365499069446e-07,
+      "loss": 0.013,
+      "step": 726
+    },
+    {
+      "epoch": 0.9368556701030928,
+      "grad_norm": 0.8621684312820435,
+      "learning_rate": 2.4220887968765873e-07,
+      "loss": 0.0022,
+      "step": 727
+    },
+    {
+      "epoch": 0.9381443298969072,
+      "grad_norm": 3.7333528995513916,
+      "learning_rate": 2.3246177389392388e-07,
+      "loss": 0.0402,
+      "step": 728
+    },
+    {
+      "epoch": 0.9394329896907216,
+      "grad_norm": 0.3883923590183258,
+      "learning_rate": 2.229125350625394e-07,
+      "loss": 0.0012,
+      "step": 729
+    },
+    {
+      "epoch": 0.9407216494845361,
+      "grad_norm": 0.36370164155960083,
+      "learning_rate": 2.1356135663824328e-07,
+      "loss": 0.0017,
+      "step": 730
+    },
+    {
+      "epoch": 0.9420103092783505,
+      "grad_norm": 1.1851253509521484,
+      "learning_rate": 2.0440842805354522e-07,
+      "loss": 0.0178,
+      "step": 731
+    },
+    {
+      "epoch": 0.9432989690721649,
+      "grad_norm": 0.40920475125312805,
+      "learning_rate": 1.9545393472488738e-07,
+      "loss": 0.0024,
+      "step": 732
+    },
+    {
+      "epoch": 0.9445876288659794,
+      "grad_norm": 1.3488298654556274,
+      "learning_rate": 1.866980580488842e-07,
+      "loss": 0.0269,
+      "step": 733
+    },
+    {
+      "epoch": 0.9458762886597938,
+      "grad_norm": 1.7972975969314575,
+      "learning_rate": 1.7814097539865626e-07,
+      "loss": 0.0037,
+      "step": 734
+    },
+    {
+      "epoch": 0.9471649484536082,
+      "grad_norm": 0.23618119955062866,
+      "learning_rate": 1.6978286012023225e-07,
+      "loss": 0.0013,
+      "step": 735
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.15299421548843384,
+      "learning_rate": 1.6162388152903498e-07,
+      "loss": 0.0007,
+      "step": 736
+    },
+    {
+      "epoch": 0.9497422680412371,
+      "grad_norm": 0.8923954963684082,
+      "learning_rate": 1.5366420490645738e-07,
+      "loss": 0.0033,
+      "step": 737
+    },
+    {
+      "epoch": 0.9510309278350515,
+      "grad_norm": 0.06458217650651932,
+      "learning_rate": 1.4590399149650769e-07,
+      "loss": 0.0003,
+      "step": 738
+    },
+    {
+      "epoch": 0.9523195876288659,
+      "grad_norm": 2.2554473876953125,
+      "learning_rate": 1.3834339850254952e-07,
+      "loss": 0.0097,
+      "step": 739
+    },
+    {
+      "epoch": 0.9536082474226805,
+      "grad_norm": 1.226751685142517,
+      "learning_rate": 1.309825790841146e-07,
+      "loss": 0.0276,
+      "step": 740
+    },
+    {
+      "epoch": 0.9536082474226805,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013158504851162434,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 85.185,
+      "eval_samples_per_second": 5.341,
+      "eval_steps_per_second": 0.176,
+      "step": 740
+    },
+    {
+      "epoch": 0.9548969072164949,
+      "grad_norm": 0.9453576803207397,
+      "learning_rate": 1.2382168235379742e-07,
+      "loss": 0.001,
+      "step": 741
+    },
+    {
+      "epoch": 0.9561855670103093,
+      "grad_norm": 6.605914115905762,
+      "learning_rate": 1.1686085337423991e-07,
+      "loss": 0.0179,
+      "step": 742
+    },
+    {
+      "epoch": 0.9574742268041238,
+      "grad_norm": 3.2699971199035645,
+      "learning_rate": 1.1010023315518592e-07,
+      "loss": 0.0252,
+      "step": 743
+    },
+    {
+      "epoch": 0.9587628865979382,
+      "grad_norm": 2.245004415512085,
+      "learning_rate": 1.0353995865063138e-07,
+      "loss": 0.0321,
+      "step": 744
+    },
+    {
+      "epoch": 0.9600515463917526,
+      "grad_norm": 0.08078460395336151,
+      "learning_rate": 9.718016275604759e-08,
+      "loss": 0.0005,
+      "step": 745
+    },
+    {
+      "epoch": 0.961340206185567,
+      "grad_norm": 0.14461307227611542,
+      "learning_rate": 9.10209743056889e-08,
+      "loss": 0.0006,
+      "step": 746
+    },
+    {
+      "epoch": 0.9626288659793815,
+      "grad_norm": 2.124976396560669,
+      "learning_rate": 8.506251806997934e-08,
+      "loss": 0.0429,
+      "step": 747
+    },
+    {
+      "epoch": 0.9639175257731959,
+      "grad_norm": 0.512088418006897,
+      "learning_rate": 7.930491475299229e-08,
+      "loss": 0.0009,
+      "step": 748
+    },
+    {
+      "epoch": 0.9652061855670103,
+      "grad_norm": 0.8166017532348633,
+      "learning_rate": 7.37482809900003e-08,
+      "loss": 0.002,
+      "step": 749
+    },
+    {
+      "epoch": 0.9664948453608248,
+      "grad_norm": 0.9644703269004822,
+      "learning_rate": 6.839272934511143e-08,
+      "loss": 0.0045,
+      "step": 750
+    },
+    {
+      "epoch": 0.9677835051546392,
+      "grad_norm": 0.47802242636680603,
+      "learning_rate": 6.323836830899321e-08,
+      "loss": 0.0015,
+      "step": 751
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 4.951274871826172,
+      "learning_rate": 5.828530229667228e-08,
+      "loss": 0.0172,
+      "step": 752
+    },
+    {
+      "epoch": 0.970360824742268,
+      "grad_norm": 0.19146917760372162,
+      "learning_rate": 5.353363164541825e-08,
+      "loss": 0.0011,
+      "step": 753
+    },
+    {
+      "epoch": 0.9716494845360825,
+      "grad_norm": 1.4356184005737305,
+      "learning_rate": 4.898345261271531e-08,
+      "loss": 0.002,
+      "step": 754
+    },
+    {
+      "epoch": 0.9729381443298969,
+      "grad_norm": 2.761564254760742,
+      "learning_rate": 4.463485737430606e-08,
+      "loss": 0.0068,
+      "step": 755
+    },
+    {
+      "epoch": 0.9742268041237113,
+      "grad_norm": 3.234301805496216,
+      "learning_rate": 4.0487934022328533e-08,
+      "loss": 0.0142,
+      "step": 756
+    },
+    {
+      "epoch": 0.9755154639175257,
+      "grad_norm": 2.400604248046875,
+      "learning_rate": 3.654276656353206e-08,
+      "loss": 0.0098,
+      "step": 757
+    },
+    {
+      "epoch": 0.9768041237113402,
+      "grad_norm": 0.21227847039699554,
+      "learning_rate": 3.27994349175742e-08,
+      "loss": 0.0006,
+      "step": 758
+    },
+    {
+      "epoch": 0.9780927835051546,
+      "grad_norm": 1.0701520442962646,
+      "learning_rate": 2.9258014915399813e-08,
+      "loss": 0.0013,
+      "step": 759
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 1.216143250465393,
+      "learning_rate": 2.591857829770672e-08,
+      "loss": 0.0042,
+      "step": 760
+    },
+    {
+      "epoch": 0.979381443298969,
+      "eval_accuracy": 0.9980139026812314,
+      "eval_f1": 0.9642857142857143,
+      "eval_loss": 0.013023993000388145,
+      "eval_precision": 0.9818181818181818,
+      "eval_recall": 0.9473684210526315,
+      "eval_runtime": 86.4332,
+      "eval_samples_per_second": 5.264,
+      "eval_steps_per_second": 0.174,
+      "step": 760
+    },
+    {
+      "epoch": 0.9806701030927835,
+      "grad_norm": 3.9802327156066895,
+      "learning_rate": 2.278119271349466e-08,
+      "loss": 0.0287,
+      "step": 761
+    },
+    {
+      "epoch": 0.9819587628865979,
+      "grad_norm": 1.6140069961547852,
+      "learning_rate": 1.984592171869082e-08,
+      "loss": 0.0041,
+      "step": 762
+    },
+    {
+      "epoch": 0.9832474226804123,
+      "grad_norm": 0.06459134072065353,
+      "learning_rate": 1.711282477486642e-08,
+      "loss": 0.0003,
+      "step": 763
+    },
+    {
+      "epoch": 0.9845360824742269,
+      "grad_norm": 0.7752759456634521,
+      "learning_rate": 1.4581957248026579e-08,
+      "loss": 0.0037,
+      "step": 764
+    },
+    {
+      "epoch": 0.9858247422680413,
+      "grad_norm": 1.614241361618042,
+      "learning_rate": 1.2253370407495636e-08,
+      "loss": 0.0067,
+      "step": 765
+    },
+    {
+      "epoch": 0.9871134020618557,
+      "grad_norm": 0.4276859760284424,
+      "learning_rate": 1.0127111424872437e-08,
+      "loss": 0.0019,
+      "step": 766
+    },
+    {
+      "epoch": 0.9884020618556701,
+      "grad_norm": 3.409043788909912,
+      "learning_rate": 8.203223373078883e-09,
+      "loss": 0.016,
+      "step": 767
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 0.6996654868125916,
+      "learning_rate": 6.481745225485059e-09,
+      "loss": 0.0018,
+      "step": 768
+    },
+    {
+      "epoch": 0.990979381443299,
+      "grad_norm": 0.7112312912940979,
+      "learning_rate": 4.962711855120983e-09,
+      "loss": 0.0026,
+      "step": 769
+    },
+    {
+      "epoch": 0.9922680412371134,
+      "grad_norm": 4.281740665435791,
+      "learning_rate": 3.6461540339682855e-09,
+      "loss": 0.0217,
+      "step": 770
+    },
+    {
+      "epoch": 0.9935567010309279,
+      "grad_norm": 0.22678984701633453,
+      "learning_rate": 2.532098432341812e-09,
+      "loss": 0.0009,
+      "step": 771
+    },
+    {
+      "epoch": 0.9948453608247423,
+      "grad_norm": 2.139557123184204,
+      "learning_rate": 1.6205676183411733e-09,
+      "loss": 0.0065,
+      "step": 772
+    },
+    {
+      "epoch": 0.9961340206185567,
+      "grad_norm": 1.8708549737930298,
+      "learning_rate": 9.115800574022171e-10,
+      "loss": 0.0096,
+      "step": 773
+    },
+    {
+      "epoch": 0.9974226804123711,
+      "grad_norm": 1.9189296960830688,
+      "learning_rate": 4.0515011191621933e-10,
+      "loss": 0.0148,
+      "step": 774
+    },
+    {
+      "epoch": 0.9987113402061856,
+      "grad_norm": 1.2406359910964966,
+      "learning_rate": 1.0128804094233779e-10,
+      "loss": 0.0034,
+      "step": 775
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.146103858947754,
+      "learning_rate": 0.0,
+      "loss": 0.0056,
+      "step": 776
     }
   ],
   "logging_steps": 1,
@@ -5353,12 +5921,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3348483995572634e+17,
+  "total_flos": 2.5857289592242176e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null