Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8d0a36fb50575f49f97243ee059409555be8514883e625550b48b21e2041061
+oid sha256:d98aba6b9b79fab9002d04281faefa5ca76f7ebe417692ec6e546d479ff2694a
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4919f9e090d9f8e271de1380c117d0157fb17ea9fdc9badf47200e3e7208939
+oid sha256:e0a29376b4a0610dc323ab928af56c154be3c922e14231f1fbcf9fffa8dee430
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005980219274706739,
+  "epoch": 0.007666947788085563,
   "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": 32.984,
       "eval_steps_per_second": 16.492,
       "step": 39
+    },
+    {
+      "epoch": 0.006133558230468451,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0833,
+      "step": 40
+    },
+    {
+      "epoch": 0.007666947788085563,
+      "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": 4678737482219520.0,
+  "total_flos": 6052790497443840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null