Training in progress, step 16, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a19c638649457d3901c4adfb5502e8231a386bd7be7c5ab6cf83fdd4761fc4d
+oid sha256:4cee0d6491f9026774a6d9cd8a412424b4e6e47352f6e9ee68df6d69fead2788
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86b1ad26c5f6ca85b77986c94e2a291261672373a5c28e198faf4370e14f324
+oid sha256:30166bd87f4c4553fff3f7c7a9090aefef1c513a71a55ec852c88b086c058939
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380805505206fcae9055c4a9e78aed7a5dda390c746cad96ecf2259c970f0ba0
+oid sha256:28c50acebbdd320cdbda27b93feb5d91578ce2eb03d7fc0517b7bfffd55baef8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027237354085603113,
+  "epoch": 0.0311284046692607,
   "eval_steps": 2,
-  "global_step": 14,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 28.723,
       "eval_steps_per_second": 14.427,
       "step": 14
+    },
+    {
+      "epoch": 0.029182879377431907,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0311284046692607,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0311284046692607,
+      "eval_loss": NaN,
+      "eval_runtime": 7.491,
+      "eval_samples_per_second": 28.968,
+      "eval_steps_per_second": 14.551,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 720558140424192.0,
+  "total_flos": 823495017627648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null