Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e2ba35399fe9673946ea87f9a443c5a834d99c7926afc416fe3689e082ef32
+oid sha256:e988b05dfff85f104c92be8d1a8d6486e85556511744e4c255c08761e3ed1bd8
 size 294753940

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29f9f214d70b0ff79d9d2c923d0cabe811546022872b273f3c1f37238dabc68
+oid sha256:939654c49b74b56fd2a8565f977213c8a464f3543e1cb9586d09bc7fbd071817
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
+oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05670809508057275,
+  "epoch": 0.07561079344076367,
   "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": 8.959,
       "eval_steps_per_second": 4.479,
       "step": 150
+    },
+    {
+      "epoch": 0.06048863475261094,
+      "grad_norm": NaN,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.07561079344076367,
+      "grad_norm": NaN,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.07561079344076367,
+      "eval_loss": NaN,
+      "eval_runtime": 248.3165,
+      "eval_samples_per_second": 8.972,
+      "eval_steps_per_second": 4.486,
+      "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": 9.837084363718656e+16,
+  "total_flos": 1.3118833670121062e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null