Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d453adfeec162fcae1d51faec9781990a6f11ca56feaaf7524c454727cac8ae
+oid sha256:70c6de23f72a5267e5937466ab263d5f359bbeac5a26d0b83f5b5df36a5c678d
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8ba37149fb5ba6888e1e75e7556d4bbfc9463fa6ad5c97d19e9b9bcc52ebc0
+oid sha256:60703926fdd8218e185266dab0602db8b05177f05cec487ad299058263f626dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
+oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007993605115907274,
+  "epoch": 0.01598721023181455,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00027,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.009592326139088728,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.011990407673860911,
+      "grad_norm": NaN,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.012789768185451638,
+      "eval_loss": NaN,
+      "eval_runtime": 12.6257,
+      "eval_samples_per_second": 31.285,
+      "eval_steps_per_second": 15.682,
+      "step": 16
+    },
+    {
+      "epoch": 0.014388489208633094,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 489850813808640.0,
+  "total_flos": 979701627617280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null