Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5cbf9be2528537b3aecfae681dd99e30ef7610ed01a8720122f68853fc0d306
+oid sha256:ea7710a75730569f98a6adc3483a2d2f58ae60a84e4b6eb48842d2ec22942000
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:8cabb6b01ce970e65857bc8a45a4246041144893c5d0e711162a6d8107f251e8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b7c6b205e1552be0830a6d7bc56be5230d8f9d9a142f3205ff3e7dff8c8730a
+oid sha256:fd82e2c4dd46a0c4163e78a1bb05a9e321fb40a1c884136f2f4f92fe2449cbde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8791208791208791,
+  "epoch": 1.054945054945055,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,27 @@
       "eval_samples_per_second": 26.577,
       "eval_steps_per_second": 13.747,
       "step": 15
+    },
+    {
+      "epoch": 0.9377289377289377,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.9963369963369964,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 1.054945054945055,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -158,12 +179,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4776857928990720.0,
+  "total_flos": 5732229514788864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null