Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ebdf5f266083a24f8b372ea9bae2afcaaa7822c749a05e993ecb8e6c3ee544
+oid sha256:f765b9632202c0efb7a5d3cedf9a340b9d6f815a1474dfc1563bea017423a632
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a996b0afeb762013a5d1bbc12322068270ba60f6975cd7e0cb0252d24278e9
+oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009992505620784412,
+  "epoch": 0.019985011241568824,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 31.725,
       "eval_steps_per_second": 15.862,
       "step": 10
+    },
+    {
+      "epoch": 0.011991006744941295,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "eval_loss": NaN,
+      "eval_runtime": 13.544,
+      "eval_samples_per_second": 31.158,
+      "eval_steps_per_second": 15.579,
+      "step": 15
+    },
+    {
+      "epoch": 0.017986510117411942,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.019985011241568824,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3627,
+      "eval_samples_per_second": 31.58,
+      "eval_steps_per_second": 15.79,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 180238575206400.0,
+  "total_flos": 360477150412800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null