Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c74d65c8209092a1d2196ea297c727e4b68830513f4d9e50a33a4466bbeb07f
+oid sha256:ada67b2650e8f9830868d3e43f079af4ff23185fd0493bb2316657c9c76e20e1
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a140be1f7d123ea9b7ad3e11cb880da31c48a32364dcc354c332d562e270fa
+oid sha256:7f6ecbaf452726da63a8f0a3ce966647efe7edb77a37960bbff28b39c85e7ad6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c4124609480e436091ddd8cf6353f844959c53776732ecdabe8e758275813f6
+oid sha256:245c446184f337880ab21d532d391b7fddbcdff08b1fe7c0a866b08a50c3b906
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c97e433f6b45ddae1a13ef0715194087b1045cef8b790ba97a7723677e3f3117
+oid sha256:8beaf52949563642b53522aa1914a3ebdd98186a1e23358b080b67be20f95227
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70a785605b24bc322b5f87cff2d745b8f0b821661528ac974fff3682225a8d93
+oid sha256:4f92793ee11f2c6048daa0f8c632cc0be7418b7cead6788d8260209487365393
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012716803843300717,
+  "epoch": 0.0014129782048111909,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 52.382,
       "eval_steps_per_second": 6.548,
       "step": 9
+    },
+    {
+      "epoch": 0.0014129782048111909,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7411455158648832.0,
+  "total_flos": 8234950176276480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null