Training in progress, step 19, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83d8f9b86d66836f17b257755770c9d3f579b3f4a97f357fc488ec275f4d504b
+oid sha256:fa60f2fb5b9eae867d3a8e175ca20215bcfe53fb87f92aad06f4fba376e9d6fe
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a39a41f912d3765e4194e7bf2d118cba79dcbe423e3417f95fa83853160b690
+oid sha256:ca4d77fad0062d5552d48c5dd5cfee2db36f1f2da83657c9ded4b16cc8020066
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d56d291cd18ad7810448a139510801dad1c82b4d3f55f294cbe92a611a910b6
+oid sha256:83e3bd115fb7914e3157d1cddd28d2440908da5dddf3ed8b9232586a56c11e23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7947019867549668,
+  "epoch": 1.0132450331125828,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 19,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,34 @@
       "eval_samples_per_second": 66.695,
       "eval_steps_per_second": 33.347,
       "step": 15
+    },
+    {
+      "epoch": 0.847682119205298,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.9006622516556292,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 1.0132450331125828,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 19
     }
   ],
   "logging_steps": 1,
@@ -158,12 +186,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 534228982824960.0,
+  "total_flos": 676690044911616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null