Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6d64474ae15c5ee61a3103626ba8f664e331dfeaa3e2057587343951fe8575
+oid sha256:ddd06a1d51d594964d2231d0a9f1dcd7ce979116db8da9b5de5ff823411dcb44
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587615f9cf9077d1ee28075528630d66945d7de55b891451eb10d66f3696a130
+oid sha256:dec5fe9a4e7d0b0d0b5890a54362458d63f1aa0cd3805572b7c904b144470602
 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": 0.15979513444302176,
+  "epoch": 0.20486555697823303,
   "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": 19.631,
       "eval_steps_per_second": 2.458,
       "step": 30
+    },
+    {
+      "epoch": 0.16389244558258642,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.16389244558258642,
+      "eval_loss": NaN,
+      "eval_runtime": 83.923,
+      "eval_samples_per_second": 19.601,
+      "eval_steps_per_second": 2.455,
+      "step": 40
+    },
+    {
+      "epoch": 0.20486555697823303,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.20486555697823303,
+      "eval_loss": NaN,
+      "eval_runtime": 83.9791,
+      "eval_samples_per_second": 19.588,
+      "eval_steps_per_second": 2.453,
+      "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": 1.0874048927603098e+17,
+  "total_flos": 1.394108836872192e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null