Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b180053fb5b80d9b8d5416d16744ea598106e22cdf92b17f74691344ed112311
+oid sha256:f20830c6caf4c7dca95f08a3c501b829938736d1cacc80dd700af419bb1e9ac7
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53d645ede4d879dfdacf196da80e0fcc385e952923e33d856fdefa597b33f22
+oid sha256:f76e123acfda2786d4800d79a98e4806fa0178234cf8d24804c284042464c169
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016172733781640017,
+  "epoch": 0.0024259100672460025,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 26.778,
       "eval_steps_per_second": 13.389,
       "step": 18
+    },
+    {
+      "epoch": 0.0018868189411913353,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.002156364504218669,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0024259100672460025,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0024259100672460025,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.5792,
+      "eval_samples_per_second": 26.825,
+      "eval_steps_per_second": 13.412,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.879975837827072e+16,
+  "total_flos": 2.819963756740608e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null