Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714a8abbbe6aece9b922242f6257f6acffff4b5fb39fe90f02a5a2fe5ec13731
+oid sha256:fb9d670069f5e1c0ce2785196918d606a858de0cbe420f28be2ee827f071c481
 size 2611614300

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7c12e2108624aacd9b44967aa8bce9500b01cee814b27ed73f034dde9da5c2
+oid sha256:d7b35a1b319a7955d1cd726be6d2136954618d7589e16b936cfcb01809852964
 size 5213028466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae64ac8edb3492cfab66f6834f7bf23d78e5127a7e80ffb9ef09266673961768
+oid sha256:3aa3697ff1b2ae74cc2afbb785f0e442fac632ef2e496ff49793437a27b21de1
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3196e1bd0cad5443f60d9e65d9a945b437bc3fd7b64c46ff3ea07481067c828
+oid sha256:42629e0f223924c91cbbab007a8c6a2ef4e19563ca34c56935f96f1f89aa50d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07498110827545404,
+  "epoch": 0.09997481103393871,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -28,6 +28,13 @@
       "learning_rate": 9.625093726568358e-05,
       "loss": 24449237647.36,
       "step": 300
+    },
+    {
+      "epoch": 0.09997481103393871,
+      "grad_norm": 1.2044204473495483,
+      "learning_rate": 9.50012496875781e-05,
+      "loss": 3199597936.64,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -47,7 +54,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.834639198178509e+16,
+  "total_flos": 7.779518930904678e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null