Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f765b9632202c0efb7a5d3cedf9a340b9d6f815a1474dfc1563bea017423a632
+oid sha256:81bed8336bc20b533adb47e471d0f5fd076f3d16bcc7557120e9fb5c886b2755
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24fd1fe6fc3fe53206005c2f017183a719041db145b778292496e5e79dd787f6
+oid sha256:665a4c0a78e89b78b5609bd45eff4d27923e57a061201ddd07c3914ca7c632ce
 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": 0.004558144835052133,
+  "epoch": 0.006837217252578201,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 30.619,
       "eval_steps_per_second": 15.31,
       "step": 20
+    },
+    {
+      "epoch": 0.00478605207680474,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.00546977380206256,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.005697681043815167,
+      "eval_loss": NaN,
+      "eval_runtime": 60.1726,
+      "eval_samples_per_second": 30.712,
+      "eval_steps_per_second": 15.356,
+      "step": 25
+    },
+    {
+      "epoch": 0.00615349552732038,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.006837217252578201,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.006837217252578201,
+      "eval_loss": NaN,
+      "eval_runtime": 60.2134,
+      "eval_samples_per_second": 30.691,
+      "eval_steps_per_second": 15.345,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 500162046197760.0,
+  "total_flos": 757002015866880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null