Training in progress, step 720, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e60d06ecdfe43f0b55e6ac644b1de9800f43b1b23a3a18585b1c9018cc7bcd3e
+oid sha256:fa9b5d2dd613ca4d99e81442380c30bf12c8ba2f14c270da14b171cf62852182
 size 2159193648

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c22f133788f3e075f598f86e956bfd400fbcac7ff66fa521fbb15d9d50badc
+oid sha256:5ce398081a2efa7996c9a090549b8ffdfa9880b03117d8bb3d57da4bcb896f36
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6f9bff018ce78f5b3a049cb89d19a3641ea87206838bec0926c3ffbdd0de2bf
+oid sha256:5746b0636e67a6d9892f72fa927b5cd2167e489e9ea58bf2cfc7c8bd6ff1cdc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9958333333333333,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 717,
+  "global_step": 720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5026,6 +5026,27 @@
       "learning_rate": 5.776842425569973e-09,
       "loss": 0.0,
       "step": 717
+    },
+    {
+      "epoch": 0.9972222222222222,
+      "grad_norm": NaN,
+      "learning_rate": 2.5675129898206083e-09,
+      "loss": 0.0,
+      "step": 718
+    },
+    {
+      "epoch": 0.9986111111111111,
+      "grad_norm": NaN,
+      "learning_rate": 6.418823675857777e-10,
+      "loss": 0.0,
+      "step": 719
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 720
     }
   ],
   "logging_steps": 1,
@@ -5040,12 +5061,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.077446308874158e+17,
+  "total_flos": 1.0798413766616678e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null