Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75551c09d63fee18a1d1bce4b1b36094e9e12e8189bdcb9b64ce11980a270d0
+oid sha256:bb38fcc937c94e156f08a2e15f02d498d3b79358d9123cd2194a960ee6ef559f
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1306496ccfca656eaab46adb77fd726c90c2d7f9b6be493b3dad9a61a70c4b9e
+oid sha256:b14aba306d43aa11411cf19f21eb8eed734ad54f9d36f6deed699e0278723edf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020537395173712135,
+  "epoch": 0.02738319356494951,
   "eval_steps": 13,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,35 @@
       "learning_rate": 0.0001,
       "loss": 0.0,
       "step": 30
+    },
+    {
+      "epoch": 0.02259113469108335,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.02464487420845456,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.026698613725825774,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.026698613725825774,
+      "eval_loss": NaN,
+      "eval_runtime": 14.365,
+      "eval_samples_per_second": 42.812,
+      "eval_steps_per_second": 21.441,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -120,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 500590494351360.0,
+  "total_flos": 671426932899840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null