Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee635ad3a22ac6e18aba519b2b82f8c050c77712bf48dbd8cbb558bc80245eee
+oid sha256:c6fc728622252fa436a1ea3cf2e118a0863119f37932f34417c626eb62e35428
 size 120213058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:462c231b5eb33cd1f6a4fffa642c29d96674aea5bf1ff703326a692426f1fac7
+oid sha256:d6b3f40fc94adf0db1d12430370de5342f75c8fe2163c2a50201a6818adf34cb
 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": 0.05198180636777128,
+  "epoch": 0.07797270955165692,
   "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": 12.689,
       "eval_steps_per_second": 6.384,
       "step": 20
+    },
+    {
+      "epoch": 0.05458089668615984,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.06237816764132553,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0649772579597141,
+      "eval_loss": NaN,
+      "eval_runtime": 12.8328,
+      "eval_samples_per_second": 12.702,
+      "eval_steps_per_second": 6.39,
+      "step": 25
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.07797270955165692,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07797270955165692,
+      "eval_loss": NaN,
+      "eval_runtime": 12.8013,
+      "eval_samples_per_second": 12.733,
+      "eval_steps_per_second": 6.406,
+      "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": 1909376365363200.0,
+  "total_flos": 2736772790353920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null