Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095cdc2206915b13c91737914986a8e276b6aa2aeb7f585f2e2299aaef863431
+oid sha256:0a592fce447bb7dcfa95e6c2f459b48dd8f3bbbb2b6792342f3f5dd4f7b1e9b7
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0918f01fc281fe650a7f34ce320b16f41041a3828360539c10b1d1b26b82b5
+oid sha256:7a4e590112940d8f25a462fc21bc9495771d6dbcda763130af30c384c8af250a
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3753ab7977739b8eda494dd72defae5750f7283141b11a8f562160ba4c1a23
+oid sha256:12d8b6c71ec5842a7f720763e6312f0db9384dc999ad47a74f64d26d1c1cb7ce
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:022915fa8ac65fae0f13853519b8aa7ee79efd632a399c1f64c6b87bab0b057a
+oid sha256:793190053d1293f4ec72cd72bea61df6e622ffbc2a94ef18fbadb35cfca4423b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:178c6e38397a4175ef74b3ac48e86f590f2f5e0bc2e4d9b59014e014312512a2
+oid sha256:b64b4ee8ed3e0046a79e8a5ad65233e0a650bf33583438587eb37eed6953f429
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.018166666666666,
+  "epoch": 13.020066666666667,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1128,6 +1128,76 @@
       "learning_rate": 2.546561724000454e-05,
       "loss": 0.5749254608154297,
       "step": 8000
+    },
+    {
+      "epoch": 6.010633333333334,
+      "grad_norm": 1.794567584991455,
+      "learning_rate": 2.5408250964237518e-05,
+      "loss": 0.6101033782958984,
+      "step": 8050
+    },
+    {
+      "epoch": 6.0123,
+      "grad_norm": 1.645218849182129,
+      "learning_rate": 2.5350589586267645e-05,
+      "loss": 0.6382519149780274,
+      "step": 8100
+    },
+    {
+      "epoch": 6.013966666666667,
+      "grad_norm": 1.7477233409881592,
+      "learning_rate": 2.52926347409517e-05,
+      "loss": 0.5900593185424805,
+      "step": 8150
+    },
+    {
+      "epoch": 7.000866666666667,
+      "grad_norm": 1.5820660591125488,
+      "learning_rate": 2.5234388071467064e-05,
+      "loss": 0.5954227828979493,
+      "step": 8200
+    },
+    {
+      "epoch": 7.002533333333333,
+      "grad_norm": 1.5947580337524414,
+      "learning_rate": 2.517585122926512e-05,
+      "loss": 0.5810695266723633,
+      "step": 8250
+    },
+    {
+      "epoch": 7.0042,
+      "grad_norm": 1.4849404096603394,
+      "learning_rate": 2.511702587402444e-05,
+      "loss": 0.5662033843994141,
+      "step": 8300
+    },
+    {
+      "epoch": 7.005866666666667,
+      "grad_norm": 1.6737949848175049,
+      "learning_rate": 2.5057913673603722e-05,
+      "loss": 0.6508497619628906,
+      "step": 8350
+    },
+    {
+      "epoch": 7.007533333333333,
+      "grad_norm": 1.9604586362838745,
+      "learning_rate": 2.4998516303994502e-05,
+      "loss": 0.5735390090942383,
+      "step": 8400
+    },
+    {
+      "epoch": 7.0092,
+      "grad_norm": 1.8022760152816772,
+      "learning_rate": 2.493883544927365e-05,
+      "loss": 0.5821025848388672,
+      "step": 8450
+    },
+    {
+      "epoch": 7.010866666666667,
+      "grad_norm": 1.723585605621338,
+      "learning_rate": 2.4878872801555596e-05,
+      "loss": 0.5521516799926758,
+      "step": 8500
     }
   ],
   "logging_steps": 50,
@@ -1147,7 +1217,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.138017128514355e+17,
+  "total_flos": 7.58431423521448e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null