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:faf0dc22e6e7cfc21caf939f6f5ba34b2ea746154e5b7bf781c1e0980f42e839
+oid sha256:ccced6cc44df3508f197b5c98383c5ef725c63c1141d817c559cf95bee68f4cb
 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": 0.008506113769271665,
+  "epoch": 0.012759170653907496,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.008931419457735247,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.010207336523125997,
+      "eval_loss": NaN,
+      "eval_runtime": 76.7286,
+      "eval_samples_per_second": 12.903,
+      "eval_steps_per_second": 6.451,
+      "step": 24
+    },
+    {
+      "epoch": 0.011483253588516746,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.012759170653907496,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9961301379907584.0,
+  "total_flos": 1.5640990763188224e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null