Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f8f902afabbef3ca5bb0df7fa7ef8955d6e0251187f8c20f63be185400de5f9
+oid sha256:ead3639797250cf1ab69dd8bce1cdef404c6383747b5c7c08bad318585cf0a85
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:245a002355c2f4b67495ad20c3b200f1c38caa0af88b169c40536a035cffad2b
+oid sha256:9b3b9fb03b96260ee75018809b8ea867b66aa753d555e038af419cd1860f957c
 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": 0.015267175572519083,
+  "epoch": 0.022900763358778626,
   "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": 13.609,
       "eval_steps_per_second": 3.412,
       "step": 18
+    },
+    {
+      "epoch": 0.017811704834605598,
+      "grad_norm": NaN,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.020356234096692113,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.022900763358778626,
+      "eval_loss": NaN,
+      "eval_runtime": 72.9694,
+      "eval_samples_per_second": 13.608,
+      "eval_steps_per_second": 3.412,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1974469216108544e+16,
+  "total_flos": 1.7961703824162816e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null