Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b0fb2a4e06971cd63cb72d81e4baefdbba8218bf5275a7cdfc1ac6046202af
+oid sha256:ff3f120d59b7c206f1786b2024c2809e25f1069f71e126421663fcf08108169b
 size 4545930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0617e52fb189a6c19a79d9b22736ed184f451f5c72c5c5607b7baa24e35f326c
+oid sha256:622d57c6b0c5b1a24f61bedfe63d21eb76045f722036af348d84b5211540ebbd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0042927666881305004,
+  "epoch": 0.008585533376261001,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.0051513200257566,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.00643915003219575,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0068684267010088,
+      "eval_loss": NaN,
+      "eval_runtime": 4.8587,
+      "eval_samples_per_second": 201.908,
+      "eval_steps_per_second": 101.057,
+      "step": 16
+    },
+    {
+      "epoch": 0.0077269800386349004,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 37322864197632.0,
+  "total_flos": 76809372696576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null