Training in progress, step 18500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68baf906fea8389f8e8559a8decd0ab2b60bfca8f3d8f028d93b109d6d36a5c5
+oid sha256:714af7538b26941d0b6c17002355149620e21924a5a9fe7c385b2ccb6626063f
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d5029f735a686d99c7ee71d90b3734881048580cc5fb383880200df26eabe22
+oid sha256:b1ac067e345f81cabef3eb89bc66c3a5091a9bf0420b422934f2d70beb62e94f
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63aab5945fa6a4f19ef11eca5b6add2fab56216a2af2a42b2f4db10b37425e8e
+oid sha256:87b07b911601d04abcbcc91c12340e18730f0dbec6517e92e9000c51517972c9
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f00b18c22d88348c8087e818de79203b3e3b7bc34baa496b7a99bac8f2b2926
+oid sha256:00b7a5d99d77c7deb7d1fd1da36a8f1a552b9340e346793754509d7c962ffe38
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a69ec5a2f174981f959eb44ef9f358dd4df695a387539e1ef6b96f489d42e404
+oid sha256:bae61de7eccc1d6ebf06b52a6d36b904579ed066577d4884e6d61bab2772f130
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.001333333333333,
+  "epoch": 6.000233333333333,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 18500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2528,6 +2528,76 @@
       "learning_rate": 1.0678798103921991e-05,
       "loss": 1.088599395751953,
       "step": 18000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.7369530200958252,
+      "learning_rate": 1.0602374751164265e-05,
+      "loss": 1.2541021728515624,
+      "step": 18050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.7617831230163574,
+      "learning_rate": 1.0526076083034415e-05,
+      "loss": 1.2021905517578124,
+      "step": 18100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.7245622873306274,
+      "learning_rate": 1.0449904262807043e-05,
+      "loss": 1.1469745635986328,
+      "step": 18150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.8544925451278687,
+      "learning_rate": 1.0373861450160277e-05,
+      "loss": 1.1247216033935548,
+      "step": 18200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 1.7715084552764893,
+      "learning_rate": 1.0297949801114521e-05,
+      "loss": 1.1083958435058594,
+      "step": 18250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 1.976885199546814,
+      "learning_rate": 1.0222171467971355e-05,
+      "loss": 1.0610853576660155,
+      "step": 18300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 1.7652332782745361,
+      "learning_rate": 1.0146528599252468e-05,
+      "loss": 1.0758203125,
+      "step": 18350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.835084319114685,
+      "learning_rate": 1.0071023339638775e-05,
+      "loss": 1.1495576477050782,
+      "step": 18400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 1.7060741186141968,
+      "learning_rate": 9.995657829909594e-06,
+      "loss": 1.2754519653320313,
+      "step": 18450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.588921308517456,
+      "learning_rate": 9.920434206881963e-06,
+      "loss": 1.1839189910888672,
+      "step": 18500
     }
   ],
   "logging_steps": 50,
@@ -2547,7 +2617,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5722381772810486e+18,
+  "total_flos": 1.6201828336082289e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null