Training in progress, step 9500, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45acde914a16a407e55b7d2b508b7db01a42376186d9562f9e09308d54c513be
+oid sha256:b8d8bc69c3349e64d8f9fa4edaea3af219dee28efac035b9ec3f828ffad0f2bd
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766bb63adb40e72dee36e8ba55a7005a6c044d86f2e3063c9807e4c1fff748dd
+oid sha256:4e9bcb333ef319912b0430383652e13e8203dccc1fd0ee8c8adbcf9ba8917b87
 size 14917

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9309119718745744,
+  "epoch": 0.940815290724304,
   "eval_steps": 500,
-  "global_step": 9400,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6588,6 +6588,76 @@
       "learning_rate": 0.0001,
       "loss": 0.0,
       "step": 9400
+    },
+    {
+      "epoch": 0.9319023037595474,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9410
+    },
+    {
+      "epoch": 0.9328926356445204,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9420
+    },
+    {
+      "epoch": 0.9338829675294933,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9430
+    },
+    {
+      "epoch": 0.9348732994144663,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9440
+    },
+    {
+      "epoch": 0.9358636312994392,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9450
+    },
+    {
+      "epoch": 0.9368539631844122,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9460
+    },
+    {
+      "epoch": 0.9378442950693852,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9470
+    },
+    {
+      "epoch": 0.938834626954358,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9480
+    },
+    {
+      "epoch": 0.939824958839331,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9490
+    },
+    {
+      "epoch": 0.940815290724304,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 9500
     }
   ],
   "logging_steps": 10,
@@ -6607,7 +6677,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.864198242850308e+18,
+  "total_flos": 1.8837425574316605e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null