Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afc560676338b53e5e72595c52be62bd67c90ab5ed739501823d9ed06a2297a
+oid sha256:fd43e27da8d835e5a7bff921d0275b21c02c89fc003834cc981a42fe4eb67ad9
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cfa2609992f2d18cdbb2b7c594424ee048ce4a989ec2c366fbb7e5e79ffd6f
+oid sha256:83fc2b481aacb6dcfe2b7f75c50cfb71ac2517ee8be6386c4610d669afe9c21e
 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": 0.00036499339034405307,
+  "epoch": 0.0004679402440308373,
   "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": 59.942,
       "eval_steps_per_second": 29.971,
       "step": 39
+    },
+    {
+      "epoch": 0.0003743521952246698,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0004679402440308373,
+      "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": 456320589496320.0,
+  "total_flos": 587651881107456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null