Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
+oid sha256:d3198af97fd8cfcdad00f14309da038efe5e49694545c548255fddfa9f700511
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5045e6b5041e0d82aaa1f35e39116d9580228034dda2b0205d3a7a9d6f6a181a
+oid sha256:436b3ae1600b35e58c15b8d4e7a27b57fd3a761313e5a31cd36c608b15ad7bfd
 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": 0.005399231647803967,
+  "epoch": 0.010798463295607933,
   "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": 23.157,
       "eval_steps_per_second": 11.579,
       "step": 10
+    },
+    {
+      "epoch": 0.006229882670543038,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.008306510227390717,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.008306510227390717,
+      "eval_loss": NaN,
+      "eval_runtime": 43.782,
+      "eval_samples_per_second": 23.16,
+      "eval_steps_per_second": 11.58,
+      "step": 20
+    },
+    {
+      "epoch": 0.010383137784238397,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 810745646284800.0,
+  "total_flos": 1580954010255360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null