Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2545d47f4e3ecf027655288bf76418a1684f635e52753dd42423c5069420288a
+oid sha256:e181fb560390a2851d10f792127992395611aee470597f74db3cb106b890400c
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df02a040079a629976f0e33beb5a0359da350c1908108f0a21ebfb56bb2077b5
+oid sha256:eb6a79165f04c95155eea3cef232d7ad5b7fcc152b03a61b93df3fbc7438c096
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011472275334608031,
+  "epoch": 0.022944550669216062,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.48,
       "eval_steps_per_second": 1.82,
       "step": 9
+    },
+    {
+      "epoch": 0.015296367112810707,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.019120458891013385,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.022944550669216062,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.022944550669216062,
+      "eval_loss": NaN,
+      "eval_runtime": 91.264,
+      "eval_samples_per_second": 14.474,
+      "eval_steps_per_second": 1.819,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2078365817176064e+16,
+  "total_flos": 2.415673163435213e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null