Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5ba4b98176cb6f867ce577ee3ce841f53e16fca2f79ce8c5ac66ab23f80e60
+oid sha256:97706a8cfb463e03bc788d44dbdb93c3373a52789941d15cf9d2786a767f6af7
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6348a493fcfdbf7bdbd4d898957add20d5f39f4a3ba3bc86aa50523a2dfb1f4
+oid sha256:2a65919ba1b62930e485de33a282a6f780e1edb2114da03184d25e2e1f26b95a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
+oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1037463976945245,
+  "epoch": 0.15561959654178675,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 9.502,
       "eval_steps_per_second": 1.2,
       "step": 18
+    },
+    {
+      "epoch": 0.12103746397694524,
+      "grad_norm": NaN,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.138328530259366,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.15561959654178675,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.15561959654178675,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8287,
+      "eval_samples_per_second": 9.504,
+      "eval_steps_per_second": 1.2,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.235660869238784e+16,
+  "total_flos": 6.38250267967488e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null