Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f76a8de4a111f94e4874506056d5e56c27cb584b307fff785cefe3e47d1d2d
+oid sha256:a9fe7a1ad2abecd7be9e393d1a4a845b3727bdb38f157729e6f7ce7f17c32cca
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad3209f7fc1bdb861e4923739acfc722c77a5349923dec2c380bd0cae2010a0
+oid sha256:4abf5eb2d66429cb692e7b306531d0476382c91e4dcc46d150233bd759ebfa10
 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": 0.04317323259579061,
+  "epoch": 0.06475984889368591,
   "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": 8.536,
       "eval_steps_per_second": 4.29,
       "step": 20
+    },
+    {
+      "epoch": 0.04533189422558014,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.05180787911494873,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.053966540744738264,
+      "eval_loss": NaN,
+      "eval_runtime": 22.8366,
+      "eval_samples_per_second": 8.539,
+      "eval_steps_per_second": 4.291,
+      "step": 25
+    },
+    {
+      "epoch": 0.05828386400431732,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06475984889368591,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06475984889368591,
+      "eval_loss": NaN,
+      "eval_runtime": 22.8753,
+      "eval_samples_per_second": 8.524,
+      "eval_steps_per_second": 4.284,
+      "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": 7427286116597760.0,
+  "total_flos": 1.1097239256563712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null