Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968a5423321ccbf3c99750c57ae6bcb715a0e3d08feb3b8b3d4dc66f71fd8ef3
+oid sha256:ec30ab19cccf4b8eea83d22d4615c44ac769b1d6c4cf2757a3e7a51ab3d218dc
 size 239452242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05956a05e8e5aa58141a86e1c295546e8baa402057d16dbbf1036cf433a8cb89
+oid sha256:49f5f14b3b395e92bacccf0f720797ba09cb01129b67f3cf08915bbfb42ea145
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00668281680728427,
+  "epoch": 0.010024225210926406,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.007016957647648484,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.008019380168741125,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.008019380168741125,
+      "eval_loss": NaN,
+      "eval_runtime": 67.3227,
+      "eval_samples_per_second": 18.731,
+      "eval_steps_per_second": 9.373,
+      "step": 24
+    },
+    {
+      "epoch": 0.009021802689833765,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.010024225210926406,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4979909134909440.0,
+  "total_flos": 7285422623293440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null