Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61d3f2ada93b32b762a915bb35e3db9a0185d6c4d8005bc220ff73718ec88225
+oid sha256:9ca5b93deb20a5537d93ad4f696d2ba8f77fc6a03a245b1c7dee471fd4501f94
 size 228536930

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3884bf4df45023b2ec53e6c84865f5490daa664ce66a17c1e53d636fa55ca89f
+oid sha256:5cb058602a57d46ef04a4898ea79efe69d5de2bbaa20e76e0fa1b40f8254ab8a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020782819535850364,
+  "epoch": 0.004156563907170073,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 8.072,
       "eval_steps_per_second": 4.037,
       "step": 15
+    },
+    {
+      "epoch": 0.0024939383443020437,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0027710426047800486,
+      "eval_loss": NaN,
+      "eval_runtime": 376.5179,
+      "eval_samples_per_second": 8.071,
+      "eval_steps_per_second": 4.037,
+      "step": 20
+    },
+    {
+      "epoch": 0.002909594735019051,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0033252511257360583,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0034638032559750607,
+      "eval_loss": NaN,
+      "eval_runtime": 376.5643,
+      "eval_samples_per_second": 8.07,
+      "eval_steps_per_second": 4.036,
+      "step": 25
+    },
+    {
+      "epoch": 0.0037409075164530656,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.004156563907170073,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004156563907170073,
+      "eval_loss": NaN,
+      "eval_runtime": 376.6164,
+      "eval_samples_per_second": 8.069,
+      "eval_steps_per_second": 4.036,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9411911598735360.0,
+  "total_flos": 1.85386137550848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null