Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
+oid sha256:f5b0f2517c02f83bc1369b687b2c7d09a6483d08f5bac14ea52ace5a911f8851
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3df8674bcbb55ceff09d645b71630daa303d76d8ef5af36424f71a998a68970a
+oid sha256:f592bf86b4fd2e71efe8302e785834bcc22f802bc4e707ef42478cdb4e0a73fb
 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": 0.0015345117596718505,
+  "epoch": 0.003069023519343701,
   "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": 14.099,
       "eval_steps_per_second": 7.049,
       "step": 10
+    },
+    {
+      "epoch": 0.0017705904919290583,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0023607873225720776,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0023607873225720776,
+      "eval_loss": NaN,
+      "eval_runtime": 315.3678,
+      "eval_samples_per_second": 11.314,
+      "eval_steps_per_second": 5.657,
+      "step": 20
+    },
+    {
+      "epoch": 0.002950984153215097,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2265426859917312.0,
+  "total_flos": 4574419620986880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null