Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e979372950e66593bf65490e5131a70cd735b46ac9a5b491f3d452659b526af9
+oid sha256:5fbc31f895cb43b2fbf61441b4473d2cb8b833fec71ce0779fba7d0189727b7f
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dab5340cfb25b0761017fce38e1a8218249c264e8d9c0394206f6b46a50f5289
+oid sha256:0d5fb98da8a9f480baf5d2b95306b99d89e0e9d5228b7991cda12d800c4c375b
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30858f23bcb22d0baef45bd4add9d6fa474141308c12653c706077b87d932e49
+oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f27ab35eafa1557f14c8f132b7c335d27234d47afefaccafaf3ac5c005f12f76
+oid sha256:12afa616253873716385d59b59f53f0a26b35b0747a1fa754d94617f51e7fa69
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.125,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -288,6 +288,76 @@
       "learning_rate": 0.00027699999999999996,
       "loss": 89.13013305664063,
       "step": 400
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 13.759241104125977,
+      "learning_rate": 0.00027623076923076923,
+      "loss": 91.34515991210938,
+      "step": 410
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 12.553871154785156,
+      "learning_rate": 0.00027546153846153844,
+      "loss": 91.6295654296875,
+      "step": 420
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 15.209941864013672,
+      "learning_rate": 0.00027469230769230766,
+      "loss": 91.69887084960938,
+      "step": 430
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 12.605022430419922,
+      "learning_rate": 0.00027392307692307693,
+      "loss": 90.24617919921874,
+      "step": 440
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 14.718850135803223,
+      "learning_rate": 0.00027315384615384615,
+      "loss": 90.20364990234376,
+      "step": 450
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 12.55235767364502,
+      "learning_rate": 0.00027238461538461536,
+      "loss": 88.11900024414062,
+      "step": 460
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 14.204663276672363,
+      "learning_rate": 0.0002716153846153846,
+      "loss": 90.44221801757813,
+      "step": 470
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.577082633972168,
+      "learning_rate": 0.0002708461538461538,
+      "loss": 88.5084716796875,
+      "step": 480
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 10.324372291564941,
+      "learning_rate": 0.00027007692307692307,
+      "loss": 89.32081298828125,
+      "step": 490
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 13.348015785217285,
+      "learning_rate": 0.0002693076923076923,
+      "loss": 87.786767578125,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -307,7 +377,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6704562350822400.0,
+  "total_flos": 8373582374722560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null