Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bdd7a7ed125ee81e5cbb588cbfd3c9af804c9737e35f1ffb99dec44170b0b85
+oid sha256:7f963a7d2a9faf4b0d05ea3e85b3c81458944466b654abd7931df60aa5256dc0
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05c00ecbc39ad6d3b8acd20ff5f742532a970f1a2dc6f9d82c9bff99ab0d533
+oid sha256:fc161dc1cfb27c3b6281fb63092f5f6b8ac67f6d916e11b40ce7d923ee7d2dfa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.96,
+  "epoch": 1.28,
   "eval_steps": 1,
-  "global_step": 3,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 31.681,
       "eval_steps_per_second": 15.841,
       "step": 3
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1866,
+      "eval_samples_per_second": 32.155,
+      "eval_steps_per_second": 16.078,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -66,12 +81,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2091163255308288.0,
+  "total_flos": 2766434723168256.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null