Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060f48fcb919eff7f1e0407050f947b2b241fab41b0aa9bf321c0411a78ebde8
+oid sha256:6808f6bdf611bae5732b11f0f93562c1aa8bc2f831b2faa67778fb05cd5e6908
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4fbddabce322af725c7b0ef0cf1c126009cf8604b184c0c50c2938b4e5f6dd
+oid sha256:1ea5d4c56f10ff9c8c246d4f0f2c092cc38ff2833f609071c68fde65e94b3f9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00029550063347948304,
+  "epoch": 0.00044325095021922455,
   "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": 49.508,
       "eval_steps_per_second": 24.754,
       "step": 20
+    },
+    {
+      "epoch": 0.00031027566515345715,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0003546007601753796,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0003693757918493538,
+      "eval_loss": NaN,
+      "eval_runtime": 574.4066,
+      "eval_samples_per_second": 49.613,
+      "eval_steps_per_second": 24.806,
+      "step": 25
+    },
+    {
+      "epoch": 0.0003989258551973021,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.00044325095021922455,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.00044325095021922455,
+      "eval_loss": NaN,
+      "eval_runtime": 550.6746,
+      "eval_samples_per_second": 51.751,
+      "eval_steps_per_second": 25.876,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null