Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134299681f447f0506736826c60de0a6b972ee7872ae46c6fe1e5b57e7986f01
+oid sha256:0b442a91fc494b07873529d6928b70c5e77e161054706215bf2b40cf296857b3
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3473831319acd1f19ea5dbd52d066d329e9a6f7043d9845dfe2e32621e9577dd
+oid sha256:34f513574defcc14447e1117b1976ca76da5057f596dc39cd6e9bb96a587fcab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05546995377503852,
+  "epoch": 0.11093990755007704,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 61.375,
       "eval_steps_per_second": 15.68,
       "step": 9
+    },
+    {
+      "epoch": 0.07395993836671803,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.09244992295839753,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.11093990755007704,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.11093990755007704,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2477,
+      "eval_samples_per_second": 60.952,
+      "eval_steps_per_second": 15.572,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 347781709430784.0,
+  "total_flos": 705224021901312.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null