Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a60ae7e290860499ec7f323547aa062ee1ec0de7e624bdd463e9eda875d7a7
+oid sha256:60d9dd7a962f874818ebfbca1e6c651b43dbb13b53ec20c040106a4020698db5
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8bc0ce22eefba3d598eb91b0d3394bbc395179cd2193aced6d837afdfcd354
+oid sha256:eb7c67821feeaa234c6c478af37337bb11cb486a1c28ab9734deba949ae773e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:95758e6aadaa863940ee26d7d4bc2716664c72b77251097ec968b5c9819c88ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.031413612565445025,
+  "epoch": 0.03926701570680628,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,28 @@
       "learning_rate": 9.372094804706867e-05,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.032984293193717276,
+      "grad_norm": NaN,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.03769633507853403,
+      "grad_norm": NaN,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.03769633507853403,
+      "eval_loss": NaN,
+      "eval_runtime": 50.4344,
+      "eval_samples_per_second": 7.991,
+      "eval_steps_per_second": 4.005,
+      "step": 24
     }
   ],
   "logging_steps": 3,
@@ -92,7 +114,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.90858892673024e+16,
+  "total_flos": 2.3857361584128e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null