Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a195bb2affd8b92355b3c3fbcdcbd8a8755d76f59c56edd91c1c227737ee85
+oid sha256:fec3e662918181e81fec2617a5f9f5de6a01b3e7022f265f73654bbc50438347
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e72953437bdac655e896c21e48e0325851505cdf5c9e67ff62fe154ccbd5a6
+oid sha256:38ffba74dde1d2bade94cf7d477b69f097fefa5eddd6cbfa453ed04630627cc1
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b33358d13198554488bc16b3454035cd57e8325ffb080d0773f728d9e98a2a6
+oid sha256:af6ae550ab924258b75cba7b10f460b254db57e2f0ee1e6652ad45c4ae51f55f
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be3090ef898425f736ce392d528a5e318dff0385f66de485a25e7ee90ff9432
+oid sha256:e216a9e826d4c344530b7e6d00074e0b36744d381337d9fe3838255770b48b79
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b622a9357894e5e2498db0562bf753e1b98ac7c3a28c1715b2965db7bdcc60b
+oid sha256:303505cecb97596e2f53b5d89a1eed07f741f9537510242aaeccaa44a51fbf19
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14285714285714285,
+  "epoch": 0.2857142857142857,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -236,6 +236,234 @@
       "eval_samples_per_second": 19.237,
       "eval_steps_per_second": 2.424,
       "step": 300
+    },
+    {
+      "epoch": 0.14761904761904762,
+      "grad_norm": 59.79628372192383,
+      "learning_rate": 3.897685737763927e-06,
+      "loss": 21.495401000976564,
+      "step": 310
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 52.11283874511719,
+      "learning_rate": 3.887506463638843e-06,
+      "loss": 21.374043273925782,
+      "step": 320
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 17.035280227661133,
+      "learning_rate": 3.876859138254304e-06,
+      "loss": 20.709390258789064,
+      "step": 330
+    },
+    {
+      "epoch": 0.1619047619047619,
+      "grad_norm": 47.00483322143555,
+      "learning_rate": 3.865746401863021e-06,
+      "loss": 20.654705810546876,
+      "step": 340
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 47.759559631347656,
+      "learning_rate": 3.854171010127219e-06,
+      "loss": 20.17596435546875,
+      "step": 350
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 47.72419738769531,
+      "learning_rate": 3.842135833435311e-06,
+      "loss": 20.0145751953125,
+      "step": 360
+    },
+    {
+      "epoch": 0.1761904761904762,
+      "grad_norm": 51.43965148925781,
+      "learning_rate": 3.829643856190115e-06,
+      "loss": 20.162620544433594,
+      "step": 370
+    },
+    {
+      "epoch": 0.18095238095238095,
+      "grad_norm": 77.80012512207031,
+      "learning_rate": 3.8166981760688015e-06,
+      "loss": 19.78917694091797,
+      "step": 380
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 51.120635986328125,
+      "learning_rate": 3.8033020032547535e-06,
+      "loss": 19.7965087890625,
+      "step": 390
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 35.47827911376953,
+      "learning_rate": 3.7894586596415266e-06,
+      "loss": 19.693804931640624,
+      "step": 400
+    },
+    {
+      "epoch": 0.19523809523809524,
+      "grad_norm": 36.45315933227539,
+      "learning_rate": 3.775171578009108e-06,
+      "loss": 19.68980255126953,
+      "step": 410
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 19.75481605529785,
+      "learning_rate": 3.7604443011726775e-06,
+      "loss": 19.586700439453125,
+      "step": 420
+    },
+    {
+      "epoch": 0.20476190476190476,
+      "grad_norm": 61.62051773071289,
+      "learning_rate": 3.7452804811040844e-06,
+      "loss": 19.429611206054688,
+      "step": 430
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 20.707780838012695,
+      "learning_rate": 3.7296838780262574e-06,
+      "loss": 19.41503143310547,
+      "step": 440
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 61.07346725463867,
+      "learning_rate": 3.713658359480768e-06,
+      "loss": 19.5462646484375,
+      "step": 450
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "eval_accuracy": 0.048236220472440944,
+      "eval_loss": 18.801279067993164,
+      "eval_runtime": 25.633,
+      "eval_samples_per_second": 19.506,
+      "eval_steps_per_second": 2.458,
+      "step": 450
+    },
+    {
+      "epoch": 0.21904761904761905,
+      "grad_norm": 20.04033088684082,
+      "learning_rate": 3.6972078993687815e-06,
+      "loss": 18.968704223632812,
+      "step": 460
+    },
+    {
+      "epoch": 0.22380952380952382,
+      "grad_norm": 65.65965270996094,
+      "learning_rate": 3.680336576965642e-06,
+      "loss": 18.938497924804686,
+      "step": 470
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 48.90804672241211,
+      "learning_rate": 3.663048575909311e-06,
+      "loss": 18.844175720214842,
+      "step": 480
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 17.749887466430664,
+      "learning_rate": 3.645348183162947e-06,
+      "loss": 18.766136169433594,
+      "step": 490
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 43.13874435424805,
+      "learning_rate": 3.627239787951847e-06,
+      "loss": 18.34910888671875,
+      "step": 500
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 29.883098602294922,
+      "learning_rate": 3.608727880675036e-06,
+      "loss": 18.39371337890625,
+      "step": 510
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 23.2874698638916,
+      "learning_rate": 3.58981705179177e-06,
+      "loss": 18.52344207763672,
+      "step": 520
+    },
+    {
+      "epoch": 0.2523809523809524,
+      "grad_norm": 28.679786682128906,
+      "learning_rate": 3.570511990683222e-06,
+      "loss": 18.389620971679687,
+      "step": 530
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 39.36701965332031,
+      "learning_rate": 3.550817484489643e-06,
+      "loss": 18.337835693359374,
+      "step": 540
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 14.972796440124512,
+      "learning_rate": 3.5307384169232777e-06,
+      "loss": 18.569638061523438,
+      "step": 550
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 20.092327117919922,
+      "learning_rate": 3.5102797670573345e-06,
+      "loss": 18.32196044921875,
+      "step": 560
+    },
+    {
+      "epoch": 0.2714285714285714,
+      "grad_norm": 42.83948516845703,
+      "learning_rate": 3.4894466080913077e-06,
+      "loss": 18.12080078125,
+      "step": 570
+    },
+    {
+      "epoch": 0.2761904761904762,
+      "grad_norm": 150.76181030273438,
+      "learning_rate": 3.4682441060929587e-06,
+      "loss": 18.27479248046875,
+      "step": 580
+    },
+    {
+      "epoch": 0.28095238095238095,
+      "grad_norm": 24.40485382080078,
+      "learning_rate": 3.446677518717271e-06,
+      "loss": 18.172178649902342,
+      "step": 590
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 21.843042373657227,
+      "learning_rate": 3.4247521939026897e-06,
+      "loss": 17.919189453125,
+      "step": 600
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "eval_accuracy": 0.05248031496062992,
+      "eval_loss": 17.725130081176758,
+      "eval_runtime": 25.3949,
+      "eval_samples_per_second": 19.689,
+      "eval_steps_per_second": 2.481,
+      "step": 600
     }
   ],
   "logging_steps": 10,