Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe4df451852031c5d1ed570f7a3e56584c7000d526db5dcf0e524d883ce852f
+oid sha256:6bc236ab176f28d85c653f1b5dc31e8a23ac4e22ff2b35733f9854d7cdfbad49
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d87f363f91d931f5d7d83e608cf274dd75004fb36172dfc2bbdb110587846e
+oid sha256:8d291a024a00b1aa3b3c84b72d282fb9a12c696d949b4c79386b0b36f723c2d2
 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": 0.0023983371529073174,
+  "epoch": 0.004796674305814635,
   "eval_steps": 8,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0002,
       "loss": 0.0,
       "step": 15
+    },
+    {
+      "epoch": 0.0025582262964344723,
+      "eval_loss": NaN,
+      "eval_runtime": 63.0749,
+      "eval_samples_per_second": 31.312,
+      "eval_steps_per_second": 15.664,
+      "step": 16
+    },
+    {
+      "epoch": 0.002878004583488781,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0033576720140702444,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.003837339444651708,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.003837339444651708,
+      "eval_loss": NaN,
+      "eval_runtime": 63.0203,
+      "eval_samples_per_second": 31.339,
+      "eval_steps_per_second": 15.678,
+      "step": 24
+    },
+    {
+      "epoch": 0.0043170068752331715,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.004796674305814635,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 734776220712960.0,
+  "total_flos": 1469552441425920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null