Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabdf806b6dc8aa08fcc47aa653cd3948303217ffc47cd4409799423b279d04f
+oid sha256:7e11f24ecffda164f06cdd9dacb4290900efeb52400fe498b008397704b1e153
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:3e2686563472cd649084082a2c329fd627ce86023a87d1ac3f5dd126e100dfda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0003919263178522438,
+  "epoch": 0.0007838526357044876,
   "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": 5.982,
       "eval_steps_per_second": 2.991,
       "step": 10
+    },
+    {
+      "epoch": 0.00047031158142269255,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005878894767783657,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005878894767783657,
+      "eval_loss": NaN,
+      "eval_runtime": 1798.0063,
+      "eval_samples_per_second": 5.976,
+      "eval_steps_per_second": 2.988,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007054673721340388,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0007838526357044876,
+      "eval_loss": NaN,
+      "eval_runtime": 1797.8378,
+      "eval_samples_per_second": 5.976,
+      "eval_steps_per_second": 2.988,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515647493406720.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null