Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f4652a8a4212c8f1501a662ffcf55252c83f097540e397346abee355579f72
+oid sha256:766c3dd91d242793b0b2c82ce4ef1c469e64021547bb0b179dc815b08dd4cfcb
 size 239340346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:678c400481616039f894e32e59dd728b53761820a51c11333c694ab96bb2b289
+oid sha256:896c8a0bd85c1e79501d04f0151c26e77a1ad551a0a41c7a369de3d1bc37992e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006791171477079796,
+  "epoch": 0.010186757215619695,
   "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": 0.00013090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.007130730050933786,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.008149405772495755,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.008149405772495755,
+      "eval_loss": NaN,
+      "eval_runtime": 217.3675,
+      "eval_samples_per_second": 5.705,
+      "eval_steps_per_second": 2.852,
+      "step": 24
+    },
+    {
+      "epoch": 0.009168081494057725,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.010186757215619695,
+      "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": 4380475627929600.0,
+  "total_flos": 6593768576778240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null