Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e12ef96034ad2097f1f42387fd4576db0d8ced23dc7aba4ebd2536cf84b7a3af
+oid sha256:5468e5d2d80f263493f09560866d2d94da1b628515c3a4df57334df3b22782b4
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc0af0558fc1c926455d798de9b7d1b8cf007f5ad3184db0e0746a0c75b7a51
+oid sha256:b4ce634aeb77334703b8688c85b4838749c302b28e47c3ac1c8e3a161d47c300
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02596559558584875,
+  "epoch": 0.03894839337877313,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.0001963525491562421,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.027263875365141188,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0311587147030185,
+      "grad_norm": NaN,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0311587147030185,
+      "eval_loss": NaN,
+      "eval_runtime": 107.3537,
+      "eval_samples_per_second": 13.6,
+      "eval_steps_per_second": 4.536,
+      "step": 24
+    },
+    {
+      "epoch": 0.035053554040895815,
+      "grad_norm": NaN,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.03894839337877313,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.164086367944704e+16,
+  "total_flos": 4.746129551917056e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null