Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9793dc12925311f3dfd4942ebe6308a4af49657857c681896d679d75810f23c3
+oid sha256:241f7975c32a3801e4bf40fa15ff20263913b167a7d71f99dcf7f9d17aff0601
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:418854455ca892c2794144fe48486cade5b7abebf35b1ce28d443e59610205e5
+oid sha256:ed2d136b9e5b40846c6fe887d8761669e9518a569141bc45bf2dc6010a710f19
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030534351145038167,
+  "epoch": 0.03816793893129771,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 13.616,
       "eval_steps_per_second": 3.414,
       "step": 36
+    },
+    {
+      "epoch": 0.03307888040712468,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.035623409669211195,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "eval_loss": NaN,
+      "eval_runtime": 72.9623,
+      "eval_samples_per_second": 13.61,
+      "eval_steps_per_second": 3.413,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.394893843221709e+16,
+  "total_flos": 2.993617304027136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null