Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9d670069f5e1c0ce2785196918d606a858de0cbe420f28be2ee827f071c481
+oid sha256:fe3339bbe444834d964d18dcdba107a588b72b643d0efbec85b6451eab84dc13
 size 2611614300

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b35a1b319a7955d1cd726be6d2136954618d7589e16b936cfcb01809852964
+oid sha256:9bb2d2afabcba63a06fbc795b476d6ea07db6d592c0123b971f0e20e6022f4d7
 size 5213028466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa3697ff1b2ae74cc2afbb785f0e442fac632ef2e496ff49793437a27b21de1
+oid sha256:35597508a6f05cf5bbe64bbeb8123b65a03a9070967439b41c9f640a3f5b8fef
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42629e0f223924c91cbbab007a8c6a2ef4e19563ca34c56935f96f1f89aa50d2
+oid sha256:e15a2bef98421551121722ff5a1a1bf1ea7fd4b41a8ff180068d46d2588d0fae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09997481103393871,
+  "epoch": 0.1249685137924234,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,21 @@
       "learning_rate": 9.50012496875781e-05,
       "loss": 3199597936.64,
       "step": 400
+    },
+    {
+      "epoch": 0.1249685137924234,
+      "grad_norm": 1.2106974124908447,
+      "learning_rate": 9.375156210947263e-05,
+      "loss": 5333758443.52,
+      "step": 500
+    },
+    {
+      "epoch": 0.1249685137924234,
+      "eval_loss": NaN,
+      "eval_runtime": 904.9111,
+      "eval_samples_per_second": 17.153,
+      "eval_steps_per_second": 17.153,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -54,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.779518930904678e+16,
+  "total_flos": 9.724398663630848e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null