Training in progress, step 250, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ffd07052d7f4352c7e4e0d91ce0f53fb0a87cb8ed955dbacb04c2a552c8df7
+oid sha256:355d0fb424ee910ca70717875b65d481ea29cccff2e884293fd976c4f522a02e
 size 99235764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e09b663cb5753737b11e2902a597a1601be05851c5a3ca9fa0d2e767012315
+oid sha256:1d15335e6e0a2daefb60d7696e7ed406e498ceab641fd1204469d1c25adaf2f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
+oid sha256:1d1650f5062195d8ee65b24ab00a137ab48cccbff41f41ba060d4208547a763c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.13304506901712956,
+  "epoch": 0.16630633627141195,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 60.282,
       "eval_steps_per_second": 15.142,
       "step": 200
+    },
+    {
+      "epoch": 0.13969732246798602,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.1463495759188425,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.15300182936969897,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.15965408282055546,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.16630633627141195,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.16630633627141195,
+      "eval_loss": NaN,
+      "eval_runtime": 10.5139,
+      "eval_samples_per_second": 60.206,
+      "eval_steps_per_second": 15.123,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -201,7 +244,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.40937221111808e+16,
+  "total_flos": 1.7617152638976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null