Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e56175de55139ea185be5495fcd119587d848c14badbf4c54f8580b4bac4781f
+oid sha256:46c83d72824791f09f1ae6b876cc319c2203a39f6cfc82829c7c7c3eefba305e
 size 1001863522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2878d45bc2877646035ade4e52b187c18d1ece71492648c73330bab09e9f9ce6
+oid sha256:4f42826cc5d41ad12a09555b550d003931192362d4513285685289a024faf7e1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
+oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035278265485280305,
+  "epoch": 0.047037687313707076,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 5.867,
       "eval_steps_per_second": 2.933,
       "step": 27
+    },
+    {
+      "epoch": 0.039198072761422564,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.04311788003756482,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018724960070727972,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.047037687313707076,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.047037687313707076,
+      "eval_loss": NaN,
+      "eval_runtime": 439.315,
+      "eval_samples_per_second": 5.868,
+      "eval_steps_per_second": 2.934,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7616575422988288e+17,
+  "total_flos": 3.6822100563984384e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null