Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21180b175c986c194dccc0fc7d1ca497d83bef1ad2b6df9e7f95855268717a8e
+oid sha256:cd69c3e2e388b6972a3a5e1324cbdc812e5f7e64074bffa95ebe4daf350e7de4
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e655424d5066c15ba7f297c7618f3e195dee922b0815462cf032c10168c30577
+oid sha256:b5d5c2a52bca7e775ff397ea50632799d40f51decb42261c0d0c7b8cf7aba1b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04780876494023904,
+  "epoch": 0.06374501992031872,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 34.949,
       "eval_steps_per_second": 8.836,
       "step": 15
+    },
+    {
+      "epoch": 0.05737051792828685,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "eval_loss": NaN,
+      "eval_runtime": 7.5612,
+      "eval_samples_per_second": 35.047,
+      "eval_steps_per_second": 8.861,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1986630663536640.0,
+  "total_flos": 2648840884715520.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null