Training in progress, step 10, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cdd1fadf4861107e876284fc76126b27363e928e424ba4c41bf13a06eb55c86
+oid sha256:7ff842a84c4ac23357e2481c34dafed25d32d0858c12088c45bbdb236d9ed4a3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1680d6054963db1bb6e4e92ac6a6242d5457f4dd0a8b34b36e385d38394429
+oid sha256:241955e34cb174da6417f562427e18265c628c8f60e97c6c45bf7b825de3a3cb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:272e2c8beff4e70c47fbbe3b0c3808da37a706bb9051b90bf4c439d64b5bcd5c
+oid sha256:c5d86908242db0a83e2c58281e7cc65d6174a3b9d69914f7e63e0bdd406bed3d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b7a593ab14dcd892c315f7df33b2772361aca7df55be4a25872d1fbb24ae3a
+oid sha256:8e247f10a91af8863468a39d9e8c968b207e26805180d9719f78bdcdf865ecb3
 size 15024

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004422604422604423,
+  "epoch": 0.0004914004914004914,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 27.28,
       "eval_steps_per_second": 6.821,
       "step": 9
+    },
+    {
+      "epoch": 0.0004914004914004914,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 10.3592,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.327975769309184e+16,
+  "total_flos": 1.47552863256576e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null