Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37590be1ae659578c9ed83ddc3fd97b1988cfecc01ac3ea2ae77f26f3854ac10
+oid sha256:9e4548c53b2ab0c18851f77ff5febece20c4081a7d379ed8c6fe3b0ccc1734d2
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6111fe50bb7072a9fc81c519f2df9efc7c7a2aec062e4de4366ce5e5c0c22ca
+oid sha256:962d3889ea97c326954bb3e3aa3a35cc8e051c5d22c3d153cce779e37d6183e4
 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": 0.1323529411764706,
+  "epoch": 0.2647058823529412,
   "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": 6.871,
       "eval_steps_per_second": 0.896,
       "step": 9
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 16.8201,
+      "step": 12
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.7364,
+      "step": 15
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.6238,
+      "step": 18
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7549,
+      "eval_samples_per_second": 6.864,
+      "eval_steps_per_second": 0.895,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.559399633616896e+16,
+  "total_flos": 5.118799267233792e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null