Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6592512f3b66d0be05591525897ff53f54682a02dc7a391352a80ae3eb928e8
+oid sha256:88d961f4426935bd2debb5040c18f2d17c6bd0756c374cada8361086a8038ae3
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354fcbfab35beb320321fc72abe28e2ba17d63b820a2c10b34cfe337af85be52
+oid sha256:cd9f9fa4f12eb656180c05ab6d0e11868fa1b817f9a6c422f3c0302601735f4e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006940829429116779,
+  "epoch": 0.0008898499268098436,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 21.367,
       "eval_steps_per_second": 10.684,
       "step": 39
+    },
+    {
+      "epoch": 0.0007118799414478749,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008898499268098436,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.23758343880704e+16,
+  "total_flos": 1.586645434368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null