Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2a6195d93f3bf4d5e786f91b14774685db0d88bfdf1d40f20b80172f8864d4
+oid sha256:fea8bb5355166c87207a4dffc581f5cb112d6bb9649ac227692d69c6ca63c9fe
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e599ebf8c42bf4256978eb4e60b65fa52201162f66abf71b04010cf02aa5e2
+oid sha256:728673b92976f39bdf8edc770560e4ef6b61c1c501931d83ff4d3bf638d48bfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006001846722068329,
+  "epoch": 0.012003693444136657,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 20.873,
       "eval_steps_per_second": 10.437,
       "step": 10
+    },
+    {
+      "epoch": 0.006925207756232687,
+      "grad_norm": NaN,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.009233610341643583,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.009233610341643583,
+      "eval_loss": NaN,
+      "eval_runtime": 43.8145,
+      "eval_samples_per_second": 20.815,
+      "eval_steps_per_second": 10.408,
+      "step": 20
+    },
+    {
+      "epoch": 0.011542012927054479,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 891288626921472.0,
+  "total_flos": 1782577253842944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null