Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8da7c23b1e47f3ba2493fe93f0a278b94001ecbc454bc3d1cbd1c554efc7b6
+oid sha256:714a8abbbe6aece9b922242f6257f6acffff4b5fb39fe90f02a5a2fe5ec13731
 size 2611614300

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ac0399a1858e68abc023c3dbe79181914f8d84aea2858e11c819a6ec40a38a
+oid sha256:2e7c12e2108624aacd9b44967aa8bce9500b01cee814b27ed73f034dde9da5c2
 size 5213028466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a228e0231f77a60f74c7f1659cd80088fa76c53c8543bf03a2911226aa2f93d
+oid sha256:ae64ac8edb3492cfab66f6834f7bf23d78e5127a7e80ffb9ef09266673961768
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de616ad8f3978afcb9d1fe171a32410caa4a828d20b3ff6b27beb33aaba188b
+oid sha256:b3196e1bd0cad5443f60d9e65d9a945b437bc3fd7b64c46ff3ea07481067c828
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049987405516969355,
+  "epoch": 0.07498110827545404,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 9.750062484378905e-05,
       "loss": 11385077760.0,
       "step": 200
+    },
+    {
+      "epoch": 0.07498110827545404,
+      "grad_norm": 1.1592445373535156,
+      "learning_rate": 9.625093726568358e-05,
+      "loss": 24449237647.36,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -40,7 +47,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.889759465452339e+16,
+  "total_flos": 5.834639198178509e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null