Training in progress, step 9851, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d4322e38448ea583429c9bb47133ec0c8191ec94a221b6525e236162a943474
+oid sha256:ba1ea5de7e6e1ee3ab127a1361b60e111ef964192f9d917aeb99ba87bb81d94b
 size 471641972

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346e1be8894c52628490e38d32835397c39586d241b17503aad0614b99c69820
+oid sha256:273b312cce6c6f505c1beee15f698791634f6f44e13c052df7ffb87553df48a6
 size 943408715

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02bf5604d96d55b809dd1552690250e2164168d4b80ec847e5101bd7d910b5f
+oid sha256:f846559439d6fa707e08e85521a12eee437c8cb62c3340d7028744e6838c14fa
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0069239ee428f0527072473131f7b7bb8f4123503b20bffc7561f20a6e3a9bd1
+oid sha256:b85e70b6d452f5f30cc5ff495c0e8e43b57320a47f9206eeead0202689789086
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7cd3679656ae98477cc816a6c7c865253dbb97497498a91f08c26ecf155e5b3
+oid sha256:b04e47ef60962624b2bf17f74185d606eb69ce81d5f67b919559d74716d67b80
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9136823938478719,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 9000,
+  "global_step": 9851,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -645,6 +645,62 @@
       "learning_rate": 9.104509510579184e-06,
       "loss": 1.6898,
       "step": 9000
+    },
+    {
+      "epoch": 0.9238344204461816,
+      "grad_norm": 6.083591938018799,
+      "learning_rate": 8.035905107929046e-06,
+      "loss": 1.6958,
+      "step": 9100
+    },
+    {
+      "epoch": 0.9339864470444913,
+      "grad_norm": 4.946804046630859,
+      "learning_rate": 6.9673007052789065e-06,
+      "loss": 1.6943,
+      "step": 9200
+    },
+    {
+      "epoch": 0.9441384736428009,
+      "grad_norm": 7.455060005187988,
+      "learning_rate": 5.898696302628767e-06,
+      "loss": 1.6465,
+      "step": 9300
+    },
+    {
+      "epoch": 0.9542905002411106,
+      "grad_norm": 6.197298526763916,
+      "learning_rate": 4.830091899978628e-06,
+      "loss": 1.6943,
+      "step": 9400
+    },
+    {
+      "epoch": 0.9644425268394203,
+      "grad_norm": 4.8244476318359375,
+      "learning_rate": 3.7614874973284893e-06,
+      "loss": 1.6418,
+      "step": 9500
+    },
+    {
+      "epoch": 0.97459455343773,
+      "grad_norm": 5.588303089141846,
+      "learning_rate": 2.69288309467835e-06,
+      "loss": 1.6407,
+      "step": 9600
+    },
+    {
+      "epoch": 0.9847465800360397,
+      "grad_norm": 8.230219841003418,
+      "learning_rate": 1.6242786920282113e-06,
+      "loss": 1.6901,
+      "step": 9700
+    },
+    {
+      "epoch": 0.9948986066343494,
+      "grad_norm": 8.50627613067627,
+      "learning_rate": 5.556742893780722e-07,
+      "loss": 1.664,
+      "step": 9800
     }
   ],
   "logging_steps": 100,
@@ -659,12 +715,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4893769911505920.0,
+  "total_flos": 5355046335700656.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null