Training in progress, step 26100, checkpoint

.gitattributes

@@ -52,3 +52,21 @@ checkpoint-24000/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs
 checkpoint-24000/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
 checkpoint-24000/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
 checkpoint-24000/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/.metadata filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/optimizer_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/.metadata filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__0_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__1_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__2_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__3_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__4_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__5_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__6_0.distcp filter=lfs diff=lfs merge=lfs -text
+checkpoint-26100/pytorch_model_fsdp_0/__7_0.distcp filter=lfs diff=lfs merge=lfs -text

checkpoint-26100/optimizer_0/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5ac445be0c849ab3d16c91f6e3a242d80c3cdf4f42194659ace28411f340b5
+size 1533608

checkpoint-26100/optimizer_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ce407663107fab2ba0837c6599b8d8887392858e7129cc9d3ed0a861351596
+size 4023049125

checkpoint-26100/optimizer_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec1d82c0c37a0d29b731958b19673cad0b92b3ef1287b635e1e57e7665b23c6
+size 4023141220

checkpoint-26100/optimizer_0/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2b7e82878b4e8a33371c07c54f7863bfe83c79e37bd59899a1f3c2da2aa659c
+size 4023141220

checkpoint-26100/optimizer_0/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6e313e1a62bd0cb9b2a4f027124ee7a3a5666a6fcc110d37d55e8e939e1b146
+size 4023141220

checkpoint-26100/optimizer_0/__4_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a31e135d50f544f2a852cfb792261bff89ef4cb238c49123c69b719eb9fcf51
+size 4023148068

checkpoint-26100/optimizer_0/__5_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8f384bd6ef5c7d4d002ad12c1d3512f3a8557e6071bbeb9b6207641e13d685
+size 4023151095

checkpoint-26100/optimizer_0/__6_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb377a698d3fede4c3768882c761f0848b8e3be3415d3e70eda28f238215bb07
+size 4023143426

checkpoint-26100/optimizer_0/__7_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80cdf6e610c0acccc58c48529e624f1453ce1a5a34ffe482a5cf60d3743e050
+size 4023102466

checkpoint-26100/pytorch_model_fsdp_0/.metadata

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32bffb1f7e243624ba827a4780a6b38540e0df39a3744803c47d5c102aa8dccd
+size 619643

checkpoint-26100/pytorch_model_fsdp_0/__0_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26500e96b56fb9fbf2189c783ac212c390b664260c214903e6be10593c6346d0
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__1_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d44471ad5c31a4913b3a1b794861afd31e7a2b1aed06f6b7d73c199b34fab5d
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__2_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8798e53184af3f53312ca950ac3dda35917dd0262653918bef8b9210ce77ba5b
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__3_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89d670917e7256135d5c95e126bcc1e6ebb8b9aff96a0423f73d6275fdee4fad
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__4_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e92e811380a0d1bc542bbf510fa5e0cb3560ccdd4f26c3a69ab3dfde9da4c
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__5_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b26058c63191d8484a5b66a61eccc5f29c5f9ea1a81fc89b054b0b71979b24
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__6_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82ced3fc71ccba585a2c5a35a969c89a99014970261afe30d7c7193a7f7ac7ba
+size 2205665511

checkpoint-26100/pytorch_model_fsdp_0/__7_0.distcp

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe5198c76edce051d010c9a279f52668e8c45ea7cf6b9c6c4ae664c3b4e59a4
+size 2205624551

checkpoint-26100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a871dd968c22a84fe75f774660bee660ef8b2bdc16f686f8123820acd9331d7c
+size 16389

checkpoint-26100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:897a7c5c7e6cd8a20298fc2f1521c050fd9e118980779cc083d28db73a00cccf
+size 16389

checkpoint-26100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cb4f8a5bbeaab3f4b96bf3d83013dc2a56e44b751dedf25bc3b231106168aa
+size 16389

checkpoint-26100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ff0a0f0c507060ad98c47b640211d1dfc789550d7fd955e9b2c6c1b716ae7b
+size 16389

checkpoint-26100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29156c7b6ab7a631914e14485f3567e091a291d6e33c55ff26f51c6ec0a3b738
+size 16389

checkpoint-26100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62262466efc2ff9c692fdee3fbb6322b1072f64bd038e932480dc37ff8918518
+size 16389

checkpoint-26100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb0977ba62eb61b6d22916eb72dda234c6b87852080edfa0b8ccdced99a0683
+size 16389

checkpoint-26100/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d75a52420432c9e563040c959a6f6b650e618100e51563ac8a07abcdbb2457
+size 16389

checkpoint-26100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d453de2b36c589f53f028ce21cb207703bf4c423f10a56704c276ab7a7d5574
+size 1465

checkpoint-26100/trainer_state.json

@@ -0,0 +1,450 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "eval_steps": 500,
+  "global_step": 26100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28735632183908044,
+      "grad_norm": 0.27726614475250244,
+      "learning_rate": 1.9617624521072798e-05,
+      "loss": 0.237,
+      "mean_token_accuracy": 0.9094978541135788,
+      "step": 500
+    },
+    {
+      "epoch": 0.5747126436781609,
+      "grad_norm": 0.3931587040424347,
+      "learning_rate": 1.9234482758620693e-05,
+      "loss": 0.2304,
+      "mean_token_accuracy": 0.9114951363801956,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.370857834815979,
+      "learning_rate": 1.8851340996168584e-05,
+      "loss": 0.2126,
+      "mean_token_accuracy": 0.9183068807125092,
+      "step": 1500
+    },
+    {
+      "epoch": 1.1494252873563218,
+      "grad_norm": 0.34739020466804504,
+      "learning_rate": 1.8468199233716476e-05,
+      "loss": 0.2058,
+      "mean_token_accuracy": 0.9208864206075669,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4367816091954024,
+      "grad_norm": 0.44222190976142883,
+      "learning_rate": 1.8085057471264368e-05,
+      "loss": 0.1941,
+      "mean_token_accuracy": 0.9255667915344238,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7241379310344827,
+      "grad_norm": 0.3851265609264374,
+      "learning_rate": 1.7701915708812263e-05,
+      "loss": 0.1864,
+      "mean_token_accuracy": 0.9283954718112946,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0114942528735633,
+      "grad_norm": 0.31711894273757935,
+      "learning_rate": 1.7318773946360154e-05,
+      "loss": 0.1848,
+      "mean_token_accuracy": 0.9288191899061203,
+      "step": 3500
+    },
+    {
+      "epoch": 2.2988505747126435,
+      "grad_norm": 0.5404093265533447,
+      "learning_rate": 1.693563218390805e-05,
+      "loss": 0.1723,
+      "mean_token_accuracy": 0.9336981619596482,
+      "step": 4000
+    },
+    {
+      "epoch": 2.586206896551724,
+      "grad_norm": 0.22831037640571594,
+      "learning_rate": 1.655249042145594e-05,
+      "loss": 0.1645,
+      "mean_token_accuracy": 0.9365380902290344,
+      "step": 4500
+    },
+    {
+      "epoch": 2.873563218390805,
+      "grad_norm": 0.22406116127967834,
+      "learning_rate": 1.6169348659003833e-05,
+      "loss": 0.1699,
+      "mean_token_accuracy": 0.9345249460935593,
+      "step": 5000
+    },
+    {
+      "epoch": 3.160919540229885,
+      "grad_norm": 0.42187097668647766,
+      "learning_rate": 1.5786206896551724e-05,
+      "loss": 0.1599,
+      "mean_token_accuracy": 0.9384886187314987,
+      "step": 5500
+    },
+    {
+      "epoch": 3.4482758620689653,
+      "grad_norm": 0.23665696382522583,
+      "learning_rate": 1.5403065134099616e-05,
+      "loss": 0.1579,
+      "mean_token_accuracy": 0.9392954226732254,
+      "step": 6000
+    },
+    {
+      "epoch": 3.735632183908046,
+      "grad_norm": 0.24368983507156372,
+      "learning_rate": 1.5019923371647511e-05,
+      "loss": 0.1587,
+      "mean_token_accuracy": 0.9390693799257278,
+      "step": 6500
+    },
+    {
+      "epoch": 4.022988505747127,
+      "grad_norm": 0.33987343311309814,
+      "learning_rate": 1.4636781609195403e-05,
+      "loss": 0.1502,
+      "mean_token_accuracy": 0.942336865067482,
+      "step": 7000
+    },
+    {
+      "epoch": 4.310344827586207,
+      "grad_norm": 0.24024857580661774,
+      "learning_rate": 1.4253639846743296e-05,
+      "loss": 0.1372,
+      "mean_token_accuracy": 0.9477886618375778,
+      "step": 7500
+    },
+    {
+      "epoch": 4.597701149425287,
+      "grad_norm": 0.4761509895324707,
+      "learning_rate": 1.3870498084291188e-05,
+      "loss": 0.1422,
+      "mean_token_accuracy": 0.9457951341867447,
+      "step": 8000
+    },
+    {
+      "epoch": 4.885057471264368,
+      "grad_norm": 0.326945424079895,
+      "learning_rate": 1.3487356321839083e-05,
+      "loss": 0.1381,
+      "mean_token_accuracy": 0.9473243873119355,
+      "step": 8500
+    },
+    {
+      "epoch": 5.172413793103448,
+      "grad_norm": 0.9344919919967651,
+      "learning_rate": 1.3104214559386974e-05,
+      "loss": 0.1167,
+      "mean_token_accuracy": 0.9559659276008606,
+      "step": 9000
+    },
+    {
+      "epoch": 5.459770114942529,
+      "grad_norm": 0.5047450065612793,
+      "learning_rate": 1.2721072796934868e-05,
+      "loss": 0.1123,
+      "mean_token_accuracy": 0.957923208117485,
+      "step": 9500
+    },
+    {
+      "epoch": 5.747126436781609,
+      "grad_norm": 0.6128556728363037,
+      "learning_rate": 1.233793103448276e-05,
+      "loss": 0.1172,
+      "mean_token_accuracy": 0.9561160520315171,
+      "step": 10000
+    },
+    {
+      "epoch": 6.0344827586206895,
+      "grad_norm": 0.7909197211265564,
+      "learning_rate": 1.1954789272030651e-05,
+      "loss": 0.109,
+      "mean_token_accuracy": 0.9592113490104676,
+      "step": 10500
+    },
+    {
+      "epoch": 6.32183908045977,
+      "grad_norm": 0.6463600993156433,
+      "learning_rate": 1.1571647509578544e-05,
+      "loss": 0.0783,
+      "mean_token_accuracy": 0.9713092336654663,
+      "step": 11000
+    },
+    {
+      "epoch": 6.609195402298851,
+      "grad_norm": 1.0739723443984985,
+      "learning_rate": 1.1188505747126436e-05,
+      "loss": 0.0806,
+      "mean_token_accuracy": 0.9704036431312562,
+      "step": 11500
+    },
+    {
+      "epoch": 6.896551724137931,
+      "grad_norm": 0.4464154541492462,
+      "learning_rate": 1.0805363984674331e-05,
+      "loss": 0.0828,
+      "mean_token_accuracy": 0.9695826562643051,
+      "step": 12000
+    },
+    {
+      "epoch": 7.183908045977011,
+      "grad_norm": 0.8025017976760864,
+      "learning_rate": 1.0422222222222223e-05,
+      "loss": 0.0621,
+      "mean_token_accuracy": 0.9774264923334122,
+      "step": 12500
+    },
+    {
+      "epoch": 7.471264367816092,
+      "grad_norm": 0.5045526027679443,
+      "learning_rate": 1.0039080459770116e-05,
+      "loss": 0.0498,
+      "mean_token_accuracy": 0.9821003634929657,
+      "step": 13000
+    },
+    {
+      "epoch": 7.758620689655173,
+      "grad_norm": 1.7900103330612183,
+      "learning_rate": 9.655938697318008e-06,
+      "loss": 0.0512,
+      "mean_token_accuracy": 0.9815057872533798,
+      "step": 13500
+    },
+    {
+      "epoch": 8.045977011494253,
+      "grad_norm": 1.2213754653930664,
+      "learning_rate": 9.272796934865901e-06,
+      "loss": 0.0465,
+      "mean_token_accuracy": 0.983227198600769,
+      "step": 14000
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 1.0093538761138916,
+      "learning_rate": 8.889655172413794e-06,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9910121623277665,
+      "step": 14500
+    },
+    {
+      "epoch": 8.620689655172415,
+      "grad_norm": 0.4820902347564697,
+      "learning_rate": 8.506513409961686e-06,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9902000530958176,
+      "step": 15000
+    },
+    {
+      "epoch": 8.908045977011493,
+      "grad_norm": 1.4471999406814575,
+      "learning_rate": 8.12337164750958e-06,
+      "loss": 0.0279,
+      "mean_token_accuracy": 0.990046201467514,
+      "step": 15500
+    },
+    {
+      "epoch": 9.195402298850574,
+      "grad_norm": 1.0422757863998413,
+      "learning_rate": 7.740229885057473e-06,
+      "loss": 0.0178,
+      "mean_token_accuracy": 0.9936608210802078,
+      "step": 16000
+    },
+    {
+      "epoch": 9.482758620689655,
+      "grad_norm": 0.7313858866691589,
+      "learning_rate": 7.3570881226053644e-06,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.9951526633501053,
+      "step": 16500
+    },
+    {
+      "epoch": 9.770114942528735,
+      "grad_norm": 1.0549014806747437,
+      "learning_rate": 6.973946360153258e-06,
+      "loss": 0.0151,
+      "mean_token_accuracy": 0.9946176511049271,
+      "step": 17000
+    },
+    {
+      "epoch": 10.057471264367816,
+      "grad_norm": 0.4364485740661621,
+      "learning_rate": 6.59080459770115e-06,
+      "loss": 0.0132,
+      "mean_token_accuracy": 0.9953484191894532,
+      "step": 17500
+    },
+    {
+      "epoch": 10.344827586206897,
+      "grad_norm": 0.621101438999176,
+      "learning_rate": 6.207662835249043e-06,
+      "loss": 0.0068,
+      "mean_token_accuracy": 0.9976246099472046,
+      "step": 18000
+    },
+    {
+      "epoch": 10.632183908045977,
+      "grad_norm": 0.33462387323379517,
+      "learning_rate": 5.8245210727969344e-06,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.997280099272728,
+      "step": 18500
+    },
+    {
+      "epoch": 10.919540229885058,
+      "grad_norm": 0.539320170879364,
+      "learning_rate": 5.441379310344828e-06,
+      "loss": 0.0079,
+      "mean_token_accuracy": 0.9971861612796783,
+      "step": 19000
+    },
+    {
+      "epoch": 11.206896551724139,
+      "grad_norm": 0.15973538160324097,
+      "learning_rate": 5.05823754789272e-06,
+      "loss": 0.0048,
+      "mean_token_accuracy": 0.9982997093200684,
+      "step": 19500
+    },
+    {
+      "epoch": 11.494252873563218,
+      "grad_norm": 0.41210290789604187,
+      "learning_rate": 4.675095785440613e-06,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9986591664552689,
+      "step": 20000
+    },
+    {
+      "epoch": 11.781609195402298,
+      "grad_norm": 0.4738906919956207,
+      "learning_rate": 4.291954022988506e-06,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9985732196569442,
+      "step": 20500
+    },
+    {
+      "epoch": 12.068965517241379,
+      "grad_norm": 0.08584625273942947,
+      "learning_rate": 3.908812260536399e-06,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9987244753837585,
+      "step": 21000
+    },
+    {
+      "epoch": 12.35632183908046,
+      "grad_norm": 0.24842122197151184,
+      "learning_rate": 3.5256704980842915e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9993553450107574,
+      "step": 21500
+    },
+    {
+      "epoch": 12.64367816091954,
+      "grad_norm": 0.4292615056037903,
+      "learning_rate": 3.1425287356321844e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9992790446281433,
+      "step": 22000
+    },
+    {
+      "epoch": 12.931034482758621,
+      "grad_norm": 0.5820701718330383,
+      "learning_rate": 2.759386973180077e-06,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9992240278720855,
+      "step": 22500
+    },
+    {
+      "epoch": 13.218390804597702,
+      "grad_norm": 0.1409875601530075,
+      "learning_rate": 2.3762452107279694e-06,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9995475882291793,
+      "step": 23000
+    },
+    {
+      "epoch": 13.505747126436782,
+      "grad_norm": 0.20804591476917267,
+      "learning_rate": 1.993103448275862e-06,
+      "loss": 0.0009,
+      "mean_token_accuracy": 0.999629429936409,
+      "step": 23500
+    },
+    {
+      "epoch": 13.793103448275861,
+      "grad_norm": 0.15083467960357666,
+      "learning_rate": 1.6099616858237549e-06,
+      "loss": 0.001,
+      "mean_token_accuracy": 0.9996287471055985,
+      "step": 24000
+    },
+    {
+      "epoch": 14.080459770114942,
+      "grad_norm": 0.037589967250823975,
+      "learning_rate": 1.2268199233716476e-06,
+      "loss": 0.0008,
+      "mean_token_accuracy": 0.9996690965890884,
+      "step": 24500
+    },
+    {
+      "epoch": 14.367816091954023,
+      "grad_norm": 0.12593868374824524,
+      "learning_rate": 8.436781609195403e-07,
+      "loss": 0.0005,
+      "mean_token_accuracy": 0.9997922871112823,
+      "step": 25000
+    },
+    {
+      "epoch": 14.655172413793103,
+      "grad_norm": 0.3417894244194031,
+      "learning_rate": 4.60536398467433e-07,
+      "loss": 0.0005,
+      "mean_token_accuracy": 0.9997744873762131,
+      "step": 25500
+    },
+    {
+      "epoch": 14.942528735632184,
+      "grad_norm": 0.014274464920163155,
+      "learning_rate": 7.739463601532567e-08,
+      "loss": 0.0005,
+      "mean_token_accuracy": 0.9997661648988724,
+      "step": 26000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 26100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 24000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.537177528062444e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}