Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2fe3ddb97ed5a3946d0cd6798bfb3c71cdf970e09bb12eaa4801982dea5a915
+oid sha256:293a71caa1df7cc26ae0e310c7dde7868cbf606062e96f282cd0290356b5417c
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39acb5a2530dc832149c5d18e7a15da6846a800c716036ccf187a7e397862da3
+oid sha256:22d0e0f373f425efa292dac5abf951f67103d9d788fea236fa7b5ab0e5d83fa6
 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": 0.009748832171146166,
+  "epoch": 0.012998442894861554,
   "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": 9.659,
       "eval_steps_per_second": 4.83,
       "step": 27
+    },
+    {
+      "epoch": 0.010832035745717962,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.011915239320289758,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018724960070727972,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.012998442894861554,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.012998442894861554,
+      "eval_loss": NaN,
+      "eval_runtime": 966.325,
+      "eval_samples_per_second": 9.654,
+      "eval_steps_per_second": 4.828,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4324267513334989e+17,
+  "total_flos": 1.909902335111332e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null