Training in progress, step 13, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c4551385431dfdc82f28d91a18f3e519edae20c75dc3e50a0705a36b3cb8a0
+oid sha256:01c3258ede87b5c06abc3994b7a4d6dc97219fa0d3b371cbdc255adc4900b5f4
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967959e8851c5d28aa2bac805fef41d59582f9afffc3400db2f209b7aa2cdee
+oid sha256:2ef5dbacddbd820cd8c9035f24b64869d607f53c9149f70fd789eec3c2b8e070
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfe8596e793c9868898cdf32c45d526c71b84747acc34fcd4850d4d300b785c9
+oid sha256:f4ce727f61f5d9aa40ac931b900ded550a7ecf0a9badefe770d52a66c5ef2ab1
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f96fac9738bd743d88f80ce88e146114dc2ab55ff1e159bd8b01a0222db339
+oid sha256:339b579a534790054eb28e51de35d1a47ad1a4526ec1be6232e5e2a340410148
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9721518987341772,
+  "epoch": 1.058227848101266,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,13 @@
       "eval_samples_per_second": 42.171,
       "eval_steps_per_second": 10.543,
       "step": 12
+    },
+    {
+      "epoch": 1.058227848101266,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 13
     }
   ],
   "logging_steps": 1,
@@ -137,12 +144,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.384232257585152e+16,
+  "total_flos": 1.499584945717248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null