Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f60fd1c49fb8a2ae1003130e7c2ae8697c2cfe3c1dd878bb49577834d2dab4b
+oid sha256:6bc236ab176f28d85c653f1b5dc31e8a23ac4e22ff2b35733f9854d7cdfbad49
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6be021fdd8df982fc338b86ca131cb94cea4b6c7fd8feb56712e7bdd4631a3d1
+oid sha256:0bdd8990c1a91d4727a2503d3b04a3e49e35b72bf5a65b445da84ad6dd041d3c
 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": 0.0008163098712271178,
+  "epoch": 0.0012244648068406767,
   "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": 0.0008571253647884737,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009795718454725414,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009795718454725414,
+      "eval_loss": NaN,
+      "eval_runtime": 261.1405,
+      "eval_samples_per_second": 39.504,
+      "eval_steps_per_second": 19.752,
+      "step": 24
+    },
+    {
+      "epoch": 0.001102018326156609,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012244648068406767,
+      "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": 1306268836823040.0,
+  "total_flos": 1959403255234560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null