Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64a93a41f1c3817388bad69351cf9a02bac0491dc62c5c9bb6f800c8957a37ae
+oid sha256:2be978ea3aa3bf4fb80637d5eb5190db3a440ec4fb55227a506ae80ae8cb8d39
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aab86dd95a356f1542dbcd0bf2738b6f7c908ceaab868ac8fbc768a1bbc33c9c
+oid sha256:f06dc400444691b20cd0161805e955b193c9256e8e96477d1c3f4ece92014368
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013763796054951955,
+  "epoch": 0.0017204745068689945,
   "eval_steps": 13,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -130,6 +130,27 @@
       "eval_samples_per_second": 47.673,
       "eval_steps_per_second": 23.838,
       "step": 39
+    },
+    {
+      "epoch": 0.0014451985857699553,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.001548427056182095,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016516555265942347,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
     }
   ],
   "logging_steps": 3,
@@ -144,12 +165,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 720954300825600.0,
+  "total_flos": 901192876032000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null