Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c14ef72fd930c73fbc26fc3420f1b13c63ccc5b96332055eb2b47ecef33f2f7
+oid sha256:e039ebe05cb930ee1a59445352389b9a33b0e5badc36a612ad4406a6f363f9f4
 size 82460660

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4515356287d7544b602531ccc5d9e82fedf8697d8579f0210c6ad36102f54d5
+oid sha256:8600863030bdb34e6ac945a8dda6c5bb6901bdcca2d40b383d702375ef09f904
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57d755f308498f85f0bf5b34c1f0b82fee5222b27e276699047f6c6be77c0807
+oid sha256:dfbb21e3472dd25820b1b1b014899753115f19b9ac09c6b51d2c9828ac8bf15c
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e59b38b7699f7635523e7ab6d478b4e9b420f110d0bbbef9f4bd629aa3d6cd28
+oid sha256:008d83c4f5ee0c3b0aa2ca88e92cb7f21d43acfd48a8bc37442b67fb3134fa7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8421052631578947,
+  "epoch": 1.0526315789473684,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,27 @@
       "eval_samples_per_second": 9.947,
       "eval_steps_per_second": 2.564,
       "step": 12
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": NaN,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": NaN,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -137,12 +158,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.684308517950587e+17,
+  "total_flos": 3.3553856474382336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null