Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e561cfa2fb89ab5c8dfad03ba4a3ad5bbd7843bc54641bee70fb9421b08b4c76
+oid sha256:3cce1c0403f796f50b96c5888705b8fedad9e6ff41e1b19ad66e9020d81fdb90
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37e42e25bf748ad7dd191aff39e0a4d53e9b87f93d936c6d70d03406a047fe3
+oid sha256:2500323a43460211890b7e0b52df9c31e138aa542ecb0e21dfbcd59897076546
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015471585837548348,
+  "epoch": 0.01983536645839532,
   "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": 32.402,
       "eval_steps_per_second": 16.201,
       "step": 39
+    },
+    {
+      "epoch": 0.015868293166716254,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 5.5841,
+      "step": 40
+    },
+    {
+      "epoch": 0.01983536645839532,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 35.1975,
+      "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": 6942368854966272.0,
+  "total_flos": 8914165926199296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null