Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b61ed4bb6349ac7ff7a292543142d7efa0a2edb4059c8eed24f92ca37e80b522
+oid sha256:451dc696ca47b662f42bdd46ae84ed0cc31cd892582d1c4cc7f9c74310a649f5
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df95a8fd63a7092f7be8371fa0ae1eccbaaab2d5d0a1792a8177e43e78dcb069
+oid sha256:60f79636116057c47696167825c53e6ae4d41a84f512baf7860522f2175dd1e2
 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": 0.0007083658000991712,
+  "epoch": 0.0010625487001487569,
   "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": 0.0007437840901041298,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008500389601190055,
+      "grad_norm": NaN,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0008500389601190055,
+      "eval_loss": NaN,
+      "eval_runtime": 1144.3034,
+      "eval_samples_per_second": 7.792,
+      "eval_steps_per_second": 3.896,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009562938301338811,
+      "grad_norm": NaN,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0010625487001487569,
+      "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": 8648082308726784.0,
+  "total_flos": 1.3234186563354624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null