Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4dacfba2ad6ea265c731eb7b0b4980ee795356ac0c37a1f0daca4023df1b3c
+oid sha256:64a93a41f1c3817388bad69351cf9a02bac0491dc62c5c9bb6f800c8957a37ae
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f2e0e81975bb9790d426cf1e81631aed9cf6bad42c0428d645bae0c8dcc89d
+oid sha256:aab86dd95a356f1542dbcd0bf2738b6f7c908ceaab868ac8fbc768a1bbc33c9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010322847041213967,
+  "epoch": 0.0013763796054951955,
   "eval_steps": 13,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,35 @@
       "learning_rate": 0.0001,
       "loss": 0.0,
       "step": 30
+    },
+    {
+      "epoch": 0.0011355131745335364,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.001238741644945676,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0013419701153578156,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0013419701153578156,
+      "eval_loss": NaN,
+      "eval_runtime": 256.6865,
+      "eval_samples_per_second": 47.673,
+      "eval_steps_per_second": 23.838,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -120,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 540715725619200.0,
+  "total_flos": 720954300825600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null