Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7876709536cc00039d760f19969d0d4cc00463afd7b9a639caf949d716e8d6
+oid sha256:1e7627d883c62daaa26528ac5de1db758728ffc0e798698cf9dc09e67f3713bd
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daaca9b56f59ca5bc9c2416a658398e3bf50376464d364157ba9fde5c8d9e3a4
+oid sha256:aeeb1d37c35dddc3499dfa65807e0f1e540a8c757e9ef0700cce98a54ce426b7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04893520616221115,
+  "epoch": 0.06524694154961486,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,28 @@
       "eval_samples_per_second": 284.997,
       "eval_steps_per_second": 35.734,
       "step": 27
+    },
+    {
+      "epoch": 0.05437245129134572,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06343452650657,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001373602209226909,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.06524694154961486,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8754,
+      "eval_samples_per_second": 285.366,
+      "eval_steps_per_second": 35.78,
+      "step": 36
     }
   ],
   "logging_steps": 5,
@@ -93,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 485350598246400.0,
+  "total_flos": 647134130995200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null