Training in progress, step 1900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5057c9842c32a69d89842ae1ea0f94292f62299087952cbb292a8939dab162b
+oid sha256:67ce32f079c2d9383c97ce4438a5a5face034e7833873ae3afffd266f5462b3e
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40095725fc0786a3c912798bc42b665ef77af7017cc5a4773c5369b9374cfaaf
+oid sha256:0be90ec704029e3eaf3dc6c2072631e4c181bf8dfa918714f1b12040f44358bb
 size 2471218763

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684e33945d5e9615d67982f907b4bd5b55d412c2b48b33613fdd4ef1c4d053c4
+oid sha256:e26e61de744c7fd53adae37853d7270aa3e689b6a223071467906f521252f455
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b3905bb99561ce66746740b1de5588d55bd3f6f12bc854dc34c827aebf5528
+oid sha256:e570f6dc930829ccb55ab7b4594c42b0febbb8bfc105ca4997eb5887dbba1959
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.002,
+  "epoch": 3.0018,
   "eval_steps": 500,
-  "global_step": 1600,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1128,6 +1128,216 @@
       "learning_rate": 0.00029098797595190375,
       "loss": 3103321489408.0,
       "step": 1600
+    },
+    {
+      "epoch": 1.0002,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002909278557114228,
+      "loss": 95.5510498046875,
+      "step": 1610
+    },
+    {
+      "epoch": 1.0004,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029086773547094184,
+      "loss": 98.69436645507812,
+      "step": 1620
+    },
+    {
+      "epoch": 1.0006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002908076152304609,
+      "loss": 99.0325439453125,
+      "step": 1630
+    },
+    {
+      "epoch": 1.0008,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029074749498997994,
+      "loss": 97.31904296875,
+      "step": 1640
+    },
+    {
+      "epoch": 1.001,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000290687374749499,
+      "loss": 98.40114135742188,
+      "step": 1650
+    },
+    {
+      "epoch": 1.0012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029062725450901803,
+      "loss": 99.31021728515626,
+      "step": 1660
+    },
+    {
+      "epoch": 1.0014,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029056713426853703,
+      "loss": 99.4878662109375,
+      "step": 1670
+    },
+    {
+      "epoch": 1.0016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002905070140280561,
+      "loss": 99.3884521484375,
+      "step": 1680
+    },
+    {
+      "epoch": 1.0018,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002904468937875751,
+      "loss": 99.46731567382812,
+      "step": 1690
+    },
+    {
+      "epoch": 1.002,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029038677354709417,
+      "loss": 99.4464599609375,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0001,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029032665330661317,
+      "loss": 104.66427001953124,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0003,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002902665330661322,
+      "loss": 98.24152221679688,
+      "step": 1720
+    },
+    {
+      "epoch": 2.0005,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002902064128256513,
+      "loss": 99.4651123046875,
+      "step": 1730
+    },
+    {
+      "epoch": 2.0007,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002901462925851703,
+      "loss": 99.3810546875,
+      "step": 1740
+    },
+    {
+      "epoch": 2.0009,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00029008617234468936,
+      "loss": 96.20846557617188,
+      "step": 1750
+    },
+    {
+      "epoch": 2.0011,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002900260521042084,
+      "loss": 99.44166259765625,
+      "step": 1760
+    },
+    {
+      "epoch": 2.0013,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028996593186372745,
+      "loss": 99.43170776367188,
+      "step": 1770
+    },
+    {
+      "epoch": 2.0015,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028990581162324644,
+      "loss": 99.37213134765625,
+      "step": 1780
+    },
+    {
+      "epoch": 2.0017,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002898456913827655,
+      "loss": 99.51829223632812,
+      "step": 1790
+    },
+    {
+      "epoch": 2.0019,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028978557114228454,
+      "loss": 99.27789306640625,
+      "step": 1800
+    },
+    {
+      "epoch": 2.0021,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002897254509018036,
+      "loss": 99.44300537109375,
+      "step": 1810
+    },
+    {
+      "epoch": 3.0002,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028966533066132264,
+      "loss": 103.58494873046875,
+      "step": 1820
+    },
+    {
+      "epoch": 3.0004,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002896052104208417,
+      "loss": 99.35955810546875,
+      "step": 1830
+    },
+    {
+      "epoch": 3.0006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028954509018036073,
+      "loss": 99.25761108398437,
+      "step": 1840
+    },
+    {
+      "epoch": 3.0008,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002894849699398797,
+      "loss": 97.34839477539063,
+      "step": 1850
+    },
+    {
+      "epoch": 3.001,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028942484969939877,
+      "loss": 98.359326171875,
+      "step": 1860
+    },
+    {
+      "epoch": 3.0012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002893647294589178,
+      "loss": 99.25703735351563,
+      "step": 1870
+    },
+    {
+      "epoch": 3.0014,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028930460921843687,
+      "loss": 99.42723388671875,
+      "step": 1880
+    },
+    {
+      "epoch": 3.0016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00028924448897795586,
+      "loss": 99.32404174804688,
+      "step": 1890
+    },
+    {
+      "epoch": 3.0018,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0002891843687374749,
+      "loss": 99.3990966796875,
+      "step": 1900
     }
   ],
   "logging_steps": 10,
@@ -1147,7 +1357,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.66012131885056e+16,
+  "total_flos": 2.680797189666816e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null