Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104644b1e0f4096a109aad6b9d45bf07fa33aa589ece5eafdd415bfdffce3ccf
+oid sha256:5c4cee0ffd291eff4feaada3417906c449ddbf8f215226cea7d23ee6a98e23eb
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bff4ab9696c1362d81fbf7848bd8c3940e7cbc2a87a971f78dc0b2f0693aa5c
+oid sha256:625a9d5db7bcf137fb3d761359a775a4b83094a3aa887804f9ee283959feb66a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
+oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.053265044814340586,
+  "epoch": 0.10653008962868117,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 19.611,
       "eval_steps_per_second": 2.456,
       "step": 10
+    },
+    {
+      "epoch": 0.08194622279129321,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.08194622279129321,
+      "eval_loss": NaN,
+      "eval_runtime": 83.8847,
+      "eval_samples_per_second": 19.61,
+      "eval_steps_per_second": 2.456,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.624682975867699e+16,
+  "total_flos": 7.249365951735398e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null