Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae8a46d58c63f88a1bc72322a26cb93b75081168f9d6b045f4346803f9f5ef9
+oid sha256:0d2da722d9084155b5ca3d2384fd39c2e33a2db3e5e940d85709d5965779ebef
 size 39428606

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f6f60d7436712414026e198adde54c241e0c60308f58cfe993f25dc2fc5f0d
+oid sha256:9e7cfee7f5b3f3729aa38b02a5f0e27fbcc2e4f705b9e75a53dd0fff4583931a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004279035933204249,
+  "epoch": 0.0008558071866408498,
   "eval_steps": 7,
-  "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": 0.00018,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0005134843119845099,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005990650306485949,
+      "eval_loss": NaN,
+      "eval_runtime": 364.3929,
+      "eval_samples_per_second": 27.004,
+      "eval_steps_per_second": 13.502,
+      "step": 14
+    },
+    {
+      "epoch": 0.0006418553899806374,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007702264679767648,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 96918447587328.0,
+  "total_flos": 193836895174656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null