Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c810e4b0e90c8871150c0ae3ee438ac54f85426a030804b5d63ab2ce887491a
+oid sha256:1bb29438058ebbdb80d301b41f99282423828ab87918853dbee93e483ae88175
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6a629bcc4d1cf05d0ed241ade838414811cac61f7bea2bcdb22033b753ca109
+oid sha256:7e80e63932c8eae7c99e68576eba41b28c2be6da6d5728e9d2106b0941dfcd24
 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": 0.010645557526955098,
+  "epoch": 0.013648150675583458,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 62.974,
       "eval_steps_per_second": 31.508,
       "step": 39
+    },
+    {
+      "epoch": 0.010918520540466766,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.013648150675583458,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1552478826921984.0,
+  "total_flos": 1990357470412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null