Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269771c4ea644209ab53b0582aa151d3e997c80a60624ee287c6e3761e09c62c
+oid sha256:a299032b222875c4dfffeade9b88e04c5f46b4c30e2068fdbdb53b1423adf742
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a4d40f9c4bf65078886d54e1cfc54df5ccabb01b6dd112966b8979e806e106
+oid sha256:8d67ec2502bdc1e0e180e8abf6116d9abc6b553d1b08b70fa10e367a53ed7cc9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01450623023991073,
+  "epoch": 0.018597731076808628,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.0,
       "step": 35
+    },
+    {
+      "epoch": 0.014878184861446904,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.014878184861446904,
+      "eval_loss": NaN,
+      "eval_runtime": 197.0365,
+      "eval_samples_per_second": 5.745,
+      "eval_steps_per_second": 2.873,
+      "step": 40
+    },
+    {
+      "epoch": 0.016737957969127765,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.018597731076808628,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.018597731076808628,
+      "eval_loss": NaN,
+      "eval_runtime": 210.9812,
+      "eval_samples_per_second": 5.365,
+      "eval_steps_per_second": 2.683,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7305778780176384.0,
+  "total_flos": 9432777665544192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null