Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
+oid sha256:a8befb927b0459522648c6fcf57de10da75b9a53f28e928d3121927e85b9e705
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bffb95207e454317005251409e1fce413a0e78de132250843c0b5a306d73a333
+oid sha256:d835ae41e77b2e2d61f8845d386de278e3b57db7670f80c463c9b943bf86f172
 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": 0.020061728395061727,
+  "epoch": 0.040123456790123455,
   "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": 27.674,
       "eval_steps_per_second": 13.887,
       "step": 10
+    },
+    {
+      "epoch": 0.023148148148148147,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "eval_loss": NaN,
+      "eval_runtime": 9.8733,
+      "eval_samples_per_second": 27.65,
+      "eval_steps_per_second": 13.876,
+      "step": 20
+    },
+    {
+      "epoch": 0.038580246913580245,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153590832562176.0,
+  "total_flos": 309407619219456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null