Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dec04aa73633790ed823134db0568c930e8388551718782453273669858d23e
+oid sha256:96c58e4260bfcc3a43fdc809034b30790dfbc567c316c9bcf8d6c1eea25d8d4d
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99b4fe45c231a8abd11d09d8ed2ed03f7cc8a5f9b6b8a77eef4dd5b704d68d16
+oid sha256:9d4518d62a67ac697059d4fc7f592151f627d1c9020a58df554eb897a246e350
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d291cee2d93195736fcf3b4639627b7f20896c3352f7062cb763bb6ff6bf17d8
+oid sha256:2e3e00ac45983e3f3b18b0a35bc5f49bfdc14b5a98eb9031c068377ea5a38632
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec7dd949d35f48dc8fb27535e4827834a15e6e3a364a22af8ae0bcf2b10765e
+oid sha256:e16c200580b7602b0b15f8ef887984614d32d1cb9f81496bb019539a5f882ad5
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37315ef08bfa8057ff315cea8e5349272ef9591e350519ec1b303f17a237220b
+oid sha256:b911940bdf86ae7e1f217f9bf9f400780319e842159e75db8115406aa532903a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001168613381791835,
+  "epoch": 0.00233722676358367,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,146 @@
       "learning_rate": 0.00013266666666666667,
       "loss": 19.71117401123047,
       "step": 200
+    },
+    {
+      "epoch": 0.0012270440508814267,
+      "grad_norm": 264.33056640625,
+      "learning_rate": 0.00013933333333333335,
+      "loss": 19.4333984375,
+      "step": 210
+    },
+    {
+      "epoch": 0.0012854747199710183,
+      "grad_norm": 667.041259765625,
+      "learning_rate": 0.000146,
+      "loss": 19.633015441894532,
+      "step": 220
+    },
+    {
+      "epoch": 0.0013439053890606102,
+      "grad_norm": 269.3677673339844,
+      "learning_rate": 0.00015266666666666667,
+      "loss": 20.40240020751953,
+      "step": 230
+    },
+    {
+      "epoch": 0.0014023360581502018,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015933333333333332,
+      "loss": 19.42903289794922,
+      "step": 240
+    },
+    {
+      "epoch": 0.0014607667272397936,
+      "grad_norm": 34716.453125,
+      "learning_rate": 0.000166,
+      "loss": 19.334349060058592,
+      "step": 250
+    },
+    {
+      "epoch": 0.0015191973963293855,
+      "grad_norm": 64080.4921875,
+      "learning_rate": 0.00017266666666666667,
+      "loss": 20.815042114257814,
+      "step": 260
+    },
+    {
+      "epoch": 0.001577628065418977,
+      "grad_norm": 6061549.5,
+      "learning_rate": 0.00017933333333333332,
+      "loss": 21.26500701904297,
+      "step": 270
+    },
+    {
+      "epoch": 0.001636058734508569,
+      "grad_norm": 886888.875,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 21.720132446289064,
+      "step": 280
+    },
+    {
+      "epoch": 0.0016944894035981605,
+      "grad_norm": 4256860.0,
+      "learning_rate": 0.0001926666666666667,
+      "loss": 22.704322814941406,
+      "step": 290
+    },
+    {
+      "epoch": 0.0017529200726877523,
+      "grad_norm": 7430499.0,
+      "learning_rate": 0.00019933333333333334,
+      "loss": 23.518629455566405,
+      "step": 300
+    },
+    {
+      "epoch": 0.0018113507417773442,
+      "grad_norm": 894349.75,
+      "learning_rate": 0.00019999999996000412,
+      "loss": 23.982521057128906,
+      "step": 310
+    },
+    {
+      "epoch": 0.0018697814108669358,
+      "grad_norm": 2417416.0,
+      "learning_rate": 0.00019999999982174674,
+      "loss": 24.528610229492188,
+      "step": 320
+    },
+    {
+      "epoch": 0.0019282120799565276,
+      "grad_norm": 3199948.5,
+      "learning_rate": 0.00019999999958473402,
+      "loss": 24.749864196777345,
+      "step": 330
+    },
+    {
+      "epoch": 0.0019866427490461192,
+      "grad_norm": 444.504150390625,
+      "learning_rate": 0.00019999999924896604,
+      "loss": 23.710609436035156,
+      "step": 340
+    },
+    {
+      "epoch": 0.002045073418135711,
+      "grad_norm": 70555.0390625,
+      "learning_rate": 0.00019999999881444277,
+      "loss": 22.891081237792967,
+      "step": 350
+    },
+    {
+      "epoch": 0.002103504087225303,
+      "grad_norm": 284.5023193359375,
+      "learning_rate": 0.00019999999828116422,
+      "loss": 22.034759521484375,
+      "step": 360
+    },
+    {
+      "epoch": 0.0021619347563148947,
+      "grad_norm": 1010.1900024414062,
+      "learning_rate": 0.00019999999764913037,
+      "loss": 21.432949829101563,
+      "step": 370
+    },
+    {
+      "epoch": 0.002220365425404486,
+      "grad_norm": 4254.8564453125,
+      "learning_rate": 0.00019999999691834125,
+      "loss": 21.196998596191406,
+      "step": 380
+    },
+    {
+      "epoch": 0.002278796094494078,
+      "grad_norm": 17355.26171875,
+      "learning_rate": 0.00019999999608879683,
+      "loss": 20.504833984375,
+      "step": 390
+    },
+    {
+      "epoch": 0.00233722676358367,
+      "grad_norm": 2989.653564453125,
+      "learning_rate": 0.00019999999516049713,
+      "loss": 20.668417358398436,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -167,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1598220482291712.0,
+  "total_flos": 3201253176450048.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null