Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3af1a16b061b7f5b92de242f0ba33b08816aad4f6e949c0b8772ac9dafb2dcb
+oid sha256:d7825181dc1b115dfb9ba64470adecc2fc108cec0772c8f3bbb182ef4026bb09
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee1305fcd17562353003de733920dc2a7a89f52a6271daebed80f894e9a5913
+oid sha256:d16e633c3d02ac43d7d5e423a5d431c222766f8bbc0f704e52759292d7ba1ea4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01609907120743034,
+  "epoch": 0.03219814241486068,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 14.789,
       "eval_steps_per_second": 7.394,
       "step": 10
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.02476780185758514,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.4791,
+      "step": 20
+    },
+    {
+      "epoch": 0.02476780185758514,
+      "eval_loss": NaN,
+      "eval_runtime": 23.0187,
+      "eval_samples_per_second": 14.771,
+      "eval_steps_per_second": 7.385,
+      "step": 20
+    },
+    {
+      "epoch": 0.030959752321981424,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2342259655704576.0,
+  "total_flos": 4661555981451264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null