Training in progress, step 36, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97706a8cfb463e03bc788d44dbdb93c3373a52789941d15cf9d2786a767f6af7
+oid sha256:5b390765ddd6d2367e2df9d01b65d75cabeee049367f967a6b89e59b61d4c28f
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a65919ba1b62930e485de33a282a6f780e1edb2114da03184d25e2e1f26b95a
+oid sha256:bd9b8b454a3a12de31f0095de92dbcd209883ef391cb6254e0cdac318f6f69dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15561959654178675,
+  "epoch": 0.207492795389049,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 9.504,
       "eval_steps_per_second": 1.2,
       "step": 27
+    },
+    {
+      "epoch": 0.1729106628242075,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.19020172910662825,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.207492795389049,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.207492795389049,
+      "eval_loss": NaN,
+      "eval_runtime": 30.797,
+      "eval_samples_per_second": 9.514,
+      "eval_steps_per_second": 1.201,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.38250267967488e+16,
+  "total_flos": 8.471321738477568e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null