Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d7c837e85c31846ca557bf4f722fe15b4affc96b45d4219259fd45b13bbf7e8
+oid sha256:4e1f4b0e2d5eaa9acfed1cf94a9776eb6dfa0e7c102d7c0a148e4e61f59a3137
 size 26562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4efc6cecf5cdb5fc2d30b43439bbfe3d2e66075bd3ddab1b19c6553f69219b
+oid sha256:62799726ec41abcc2bd4f4509df5dc69917063df942179f8740a71402b9944ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014763779527559055,
+  "epoch": 0.002952755905511811,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 163.753,
       "eval_steps_per_second": 81.876,
       "step": 3
+    },
+    {
+      "epoch": 0.001968503937007874,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0024606299212598425,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.002952755905511811,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.002952755905511811,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2696,
+      "eval_samples_per_second": 162.44,
+      "eval_steps_per_second": 81.22,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 572030976.0,
+  "total_flos": 1019707392.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null