Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013facad3f8d43facbd83e4a43b354a5c41cc0889700d8329c090bbf64d183ee
+oid sha256:1d6f610cac3847211b288a7eaabd00cbdf875b117c12f341a233f3ff1fd2b140
 size 67209940

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46701aacbf54025d1d0ab0c4ac8a896380e50265c94b575814dba5115273f574
+oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
 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": 0.0016469942355201758,
+  "epoch": 0.0032939884710403516,
   "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": 6.342,
       "eval_steps_per_second": 3.175,
       "step": 3
+    },
+    {
+      "epoch": 0.0021959923140269007,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.002744990392533626,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0032939884710403516,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0032939884710403516,
+      "eval_loss": NaN,
+      "eval_runtime": 120.9927,
+      "eval_samples_per_second": 6.339,
+      "eval_steps_per_second": 3.174,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1019572597555200.0,
+  "total_flos": 2039145195110400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null