Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8c2c76b2af6161081d482f52bf213543512394491d116e6825476f517b88d68
+oid sha256:61dad3c0f491f3d02b8684a5e5ed4e8300eb9b98ff3fd6c73c7f9f6c55b3750a
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98d0dc8a323e35694dd8d2b73ddcc61302fe5580936a3cc2762ec9e18b76f71
+oid sha256:e7837767d045f85ec3bdbe5b6776505cec21edbec966ad3302d1afdf1c2114b1
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b7476485e31d3ae54029159afe6ba29b64be20b981bfb2216839a09160d527
+oid sha256:302f2f7fdc29c0383368649af008e380436c23813655adf189ffb5786fe23276
 size 14512

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": 0.016423357664233577,
+  "epoch": 0.01824817518248175,
   "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": 4.138,
       "eval_steps_per_second": 1.039,
       "step": 9
+    },
+    {
+      "epoch": 0.01824817518248175,
+      "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": 2.531269094355763e+16,
+  "total_flos": 2.812521215950848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null