Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eb24f8916d7d1653746d40409f0668d46e875d4337228061a96e1bde68658a2
+oid sha256:588031339b5de9b3ea98d51426343071d246ece3f8daf16cf691744c0fd09f02
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6373884c409fa797b7259c6d64c1de3929dfd27f38b8f95c7509cd031abd5ec
+oid sha256:ca3c1de581a0daca6b2e6f170eac9e4d1a25aac1c30727383c2fe2ead7db79c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
+oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004851820134492005,
+  "epoch": 0.005660456823574005,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 26.826,
       "eval_steps_per_second": 13.413,
       "step": 54
+    },
+    {
+      "epoch": 0.005121365697519338,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.005390911260546672,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.005660456823574005,
+      "grad_norm": NaN,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.005660456823574005,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.6931,
+      "eval_samples_per_second": 26.823,
+      "eval_steps_per_second": 13.411,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.639927513481216e+16,
+  "total_flos": 6.573477158977536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null