Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f9ed3984bb015a1f07bbff5d61875af822f0306e75b4f3a8d45f7765a65bde
+oid sha256:24231d9f62d9453a30d95ed5d05b38409d367a52b64901ef92783ec18aa9614a
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a7f2192f9943370041dc8061e7f36329e4e9e09cb55d87866fb96eee2ca4e3
+oid sha256:4a07bcd6e3805a42226287625f87e8311850ad8dc250beea48e9b23cf7d8251d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25584255842558423,
+  "epoch": 0.3280032800328003,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 46.549,
       "eval_steps_per_second": 5.847,
       "step": 30
+    },
+    {
+      "epoch": 0.26240262402624026,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.26240262402624026,
+      "eval_loss": NaN,
+      "eval_runtime": 22.1093,
+      "eval_samples_per_second": 46.451,
+      "eval_steps_per_second": 5.835,
+      "step": 40
+    },
+    {
+      "epoch": 0.3280032800328003,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3280032800328003,
+      "eval_loss": NaN,
+      "eval_runtime": 22.0006,
+      "eval_samples_per_second": 46.681,
+      "eval_steps_per_second": 5.863,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1111962842759168e+16,
+  "total_flos": 1.42461062086656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null