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 sha256:24b3fa9427c043135df5032cea261a6a3e2e32da0b7e7a54546daafc21845f7d
+oid sha256:18707ede5c1cf87d952212e14b02c1cd9a04641ee8f98c77422de0de400ca8d8
 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": 0.0024351637647631805,
+  "epoch": 0.0036527456471447703,
   "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": 45.932,
       "eval_steps_per_second": 22.973,
       "step": 20
+    },
+    {
+      "epoch": 0.0025569219530013395,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0029221965177158166,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030439547059539756,
+      "eval_loss": NaN,
+      "eval_runtime": 74.6521,
+      "eval_samples_per_second": 46.335,
+      "eval_steps_per_second": 23.174,
+      "step": 25
+    },
+    {
+      "epoch": 0.0032874710824302936,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0036527456471447703,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0036527456471447703,
+      "eval_loss": NaN,
+      "eval_runtime": 74.9324,
+      "eval_samples_per_second": 46.162,
+      "eval_steps_per_second": 23.087,
+      "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": 486644153057280.0,
+  "total_flos": 775025873387520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null