Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65420dc23024954c09ae2fdb1de370afb893358eb85585a42d0afc7aa4f80df
+oid sha256:e6e350fe9f60d3b4ae10c95bbbc5a6311716f43b375c15711dde0718de71ef38
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18dd2199d5e0d9416c2842b5589094fc9a83859a64987d0121c7500805c3e2a
+oid sha256:2a8982d586e93ce3142da7f0637f3607b8d5e37db71b02b0ac7c550ca68a1572
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa382b905f4dad34ebe7abd59235e43278cf8532f9270f8693e820e99473115
+oid sha256:2248de37d2320ddbb576171cc6b8d719f7febfba0a31c5797625bd8cfe79c5ab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1326530612244898,
+  "epoch": 0.2653061224489796,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 36.486,
       "eval_steps_per_second": 4.644,
       "step": 13
+    },
+    {
+      "epoch": 0.15306122448979592,
+      "grad_norm": NaN,
+      "learning_rate": 9.968561049466214e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.1836734693877551,
+      "grad_norm": NaN,
+      "learning_rate": 9.919647942993148e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": NaN,
+      "learning_rate": 9.848447601883435e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.24489795918367346,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.2653061224489796,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5279,
+      "eval_samples_per_second": 36.441,
+      "eval_steps_per_second": 4.638,
+      "step": 26
     }
   ],
   "logging_steps": 3,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3537881498910720.0,
+  "total_flos": 7075762997821440.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null