Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94404b2a62563287121441c23a0830e8a0f0be10bec8e59401970c75e75fa270
+oid sha256:fa1fce88ead31b0401901d072e09d0e5300518666d1de7e27e41991ac24c3aad
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9339d686875cf5b19c60cbb0d7367a339d93c5205f11d10222c3bf6c1b0b85fb
+oid sha256:138a3283c03d4e73dd8886eff3f939c9846c712d4e1a6828573844bcc75a5d57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66cd58f55c60647a4e869c55ed470060819c163b712a243486095c77957c0c9c
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.17969451931716082,
+  "epoch": 0.23959269242288112,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,28 @@
       "eval_samples_per_second": 40.199,
       "eval_steps_per_second": 20.128,
       "step": 150
+    },
+    {
+      "epoch": 0.1916741539383049,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.23959269242288112,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.23959269242288112,
+      "eval_loss": NaN,
+      "eval_runtime": 17.4628,
+      "eval_samples_per_second": 40.257,
+      "eval_steps_per_second": 20.157,
+      "step": 200
     }
   ],
   "logging_steps": 40,
@@ -74,7 +96,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -83,12 +105,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9933153317683200.0,
+  "total_flos": 1.32442044235776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null