Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73eb267d16bbbf5c8481e31e433eccf43fa4c0d767d0aacdd64de2f65cb7adc0
+oid sha256:1f7750ecd057873cb9d5219aaa02f321b6d7fbd275ba8bd6423cd1c422a1d5f6
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6122816c42780a868d77d7c48cf66d125e516c03075f49e683bda8693a41f3d6
+oid sha256:7c2114e917b04734ecf6d6c29e2dec4f37e3e775e81af5b53e52453122fa4372
 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": 0.1592920353982301,
+  "epoch": 0.23893805309734514,
   "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": 36.281,
       "eval_steps_per_second": 4.583,
       "step": 18
+    },
+    {
+      "epoch": 0.18584070796460178,
+      "grad_norm": NaN,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.21238938053097345,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.23893805309734514,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.23893805309734514,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2467,
+      "eval_samples_per_second": 36.213,
+      "eval_steps_per_second": 4.574,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4898605152337920.0,
+  "total_flos": 7347907728506880.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null