Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccaee9708f6919567a10a4b2c9d36dae410e47bad47fbdd7a3c8cef5912777a7
+oid sha256:a096f930017b2cc6ca9f4453405747a76258ade452c58dcd9be9992e9b0e8145
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f0358d597fb0fca6f6a99969647915e547badb020bef88901f2f1820489185
+oid sha256:573c37d754c57f351f52610af1b29e5d555d9acc27bf9c5bb466ea0338b1b941
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003150496809112206,
+  "epoch": 0.004039098473220777,
   "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": 35.226,
       "eval_steps_per_second": 17.616,
       "step": 39
+    },
+    {
+      "epoch": 0.0032312787785766218,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.004039098473220777,
+      "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": 6514932543651840.0,
+  "total_flos": 8347257321553920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null