Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd0640ff674e6dc27304b8deba5b348cc35b5fb8b4b2d0ca2cfbb8fd3f5a5c3
+oid sha256:f46fd4b7b9744988c9a4f031b7ea7bc027165214a3e456814f568ab2a6bb99bf
 size 67209940

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c3908e9d070582097e74f8da47e0d666f751d6a81b830cd9725b9852b605ec
+oid sha256:bd03a75b78ff7d4ed55a6d1ffc0fd2c5bcd485c339cb758abf62afb754099e76
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011301890893284068,
+  "epoch": 0.01448960370933855,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.01159168296747084,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.01159168296747084,
+      "eval_loss": NaN,
+      "eval_runtime": 199.94,
+      "eval_samples_per_second": 7.267,
+      "eval_steps_per_second": 3.636,
+      "step": 40
+    },
+    {
+      "epoch": 0.013040643338404694,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.01448960370933855,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.01448960370933855,
+      "eval_loss": NaN,
+      "eval_runtime": 198.6452,
+      "eval_samples_per_second": 7.315,
+      "eval_steps_per_second": 3.66,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.32544437682176e+16,
+  "total_flos": 1.699287662592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null