Training in progress, step 800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6f8a4c71659aafc5d698b24d92000166e62b98d0a890b89501b9a4781bc981
+oid sha256:61b1b69e894c3a7080e6a303a3f756090e3480cd7e3be305a93cc66efecd1d2c
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3418f7557da2479bea92e3d8f042da6bfcb9d9191cf39c8a909b1433e82c08
+oid sha256:1eedc85193f945c1312ff227d4d3c069d5e5469515ec4a1e7dd01999c483db02
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e153e7ac99a45d390bef333d0c839de8b829e6cf174508b6f317b3fb7550ce99
+oid sha256:1347e41739e6d97d50d223900089b55b6dd4a02d2dc85ec6e9aa6a312e93005a
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26190536bb49f49f7e44c120697c0e6b6c7e45ebca58eedf944e71fd9beb322d
+oid sha256:e10f9e65a9c24c381ff534d5df3cf5fdc8a240cae768aed7007c78e044f60c2a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014,
+  "epoch": 0.016,
   "eval_steps": 500,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -498,6 +498,76 @@
       "learning_rate": 0.0002963987975951904,
       "loss": 72.43441772460938,
       "step": 700
+    },
+    {
+      "epoch": 0.0142,
+      "grad_norm": 8.186079978942871,
+      "learning_rate": 0.00029633867735470937,
+      "loss": 69.34667358398437,
+      "step": 710
+    },
+    {
+      "epoch": 0.0144,
+      "grad_norm": 8.636640548706055,
+      "learning_rate": 0.0002962785571142284,
+      "loss": 71.52565307617188,
+      "step": 720
+    },
+    {
+      "epoch": 0.0146,
+      "grad_norm": 8.615554809570312,
+      "learning_rate": 0.00029621843687374747,
+      "loss": 66.20573120117187,
+      "step": 730
+    },
+    {
+      "epoch": 0.0148,
+      "grad_norm": 9.266575813293457,
+      "learning_rate": 0.0002961583166332665,
+      "loss": 66.66327514648438,
+      "step": 740
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 6.957458972930908,
+      "learning_rate": 0.00029609819639278556,
+      "loss": 69.37461547851562,
+      "step": 750
+    },
+    {
+      "epoch": 0.0152,
+      "grad_norm": 10.149578094482422,
+      "learning_rate": 0.0002960380761523046,
+      "loss": 75.38046264648438,
+      "step": 760
+    },
+    {
+      "epoch": 0.0154,
+      "grad_norm": 8.38595962524414,
+      "learning_rate": 0.0002959779559118236,
+      "loss": 72.13077392578126,
+      "step": 770
+    },
+    {
+      "epoch": 0.0156,
+      "grad_norm": 9.602531433105469,
+      "learning_rate": 0.00029591783567134265,
+      "loss": 73.194677734375,
+      "step": 780
+    },
+    {
+      "epoch": 0.0158,
+      "grad_norm": 11.321459770202637,
+      "learning_rate": 0.0002958577154308617,
+      "loss": 67.77056884765625,
+      "step": 790
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 9.131096839904785,
+      "learning_rate": 0.00029579759519038075,
+      "loss": 68.58425903320312,
+      "step": 800
     }
   ],
   "logging_steps": 10,
@@ -517,7 +587,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9442605667530240.0,
+  "total_flos": 1.00786682359296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null