Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd43165a4902bd0688f1222eb4db27be82f207ea46772c4b8de3b2dfbec4a5e3
+oid sha256:b61ed4bb6349ac7ff7a292543142d7efa0a2edb4059c8eed24f92ca37e80b522
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1091a58fb8a1d4e3f2a18ae3f5b3147888d00cdb8bbb8f0b8fe8b499d5c52a
+oid sha256:df95a8fd63a7092f7be8371fa0ae1eccbaaab2d5d0a1792a8177e43e78dcb069
 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": 0.0003541829000495856,
+  "epoch": 0.0007083658000991712,
   "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": 0.00042501948005950273,
+      "grad_norm": NaN,
+      "learning_rate": 0.00029265847744427303,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005312743500743784,
+      "grad_norm": NaN,
+      "learning_rate": 0.00025606601717798207,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.000566692640079337,
+      "eval_loss": NaN,
+      "eval_runtime": 1144.3067,
+      "eval_samples_per_second": 7.792,
+      "eval_steps_per_second": 3.896,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006375292200892541,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001963525491562421,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4455072704495616.0,
+  "total_flos": 8648082308726784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null