Training in progress, step 25, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c442f487f31da25849612c596e750f93d0b99cea274d2f0afa6af8c359a279b
+oid sha256:e9b96ff3a673bca37dd5ec03cd29299632d908444a3faa8cfba4e3a9d574960c
 size 168149074

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acb9fd3cd40b93d827cef35176b136ebfcff0a85392669cbba985d6a46a72ec
+oid sha256:6a538a696e4e49b1acff76268e693ce8454e346e3ac17da27552fa60fcf786ef
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3332bdf7751c129ba04742b6c210403664d870a018de0043b448c2fd6ea64aa
+oid sha256:61a3594e8fc167ff7fa5e99c5d789b86736c3a7a83071053fe3aea243809f47b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce64e7780b2072ccd84409b1c359b07229c176404a7b1256903349bbed6a3a69
+oid sha256:78a6fd2f773c2f14cb7fb3983d7fd82d32d1f7e845de9582ab4c8d34c1eb5d47
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4aee443be8ec26ee3ffa4e3fa4e90473bca5b8b297158b5fff588f0919696c
+oid sha256:ce84198b43daeb90ac138947e02707eb2476b09ac2a535f0d42294a77a1a8c75
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9be43866b7a112efbf8125d7bbc11610819a4fb8c7f205bdfffb33dc32734ab8
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10367170626349892,
+  "epoch": 0.1079913606911447,
   "eval_steps": 3,
-  "global_step": 24,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,13 @@
       "eval_samples_per_second": 26.744,
       "eval_steps_per_second": 6.72,
       "step": 24
+    },
+    {
+      "epoch": 0.1079913606911447,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -261,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.161519615370854e+16,
+  "total_flos": 4.346476046896333e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null