Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bd9b75326e43ef632f144ed3db967683dffcb91a639a64f67d859901c06f531
+oid sha256:c4d36d1d036014fdf29af8ce4a167163f9c585b10538c145dbae1f5deb1c3ae4
 size 79866276

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d16e5ade4b2c40b2b56cc1779d956f655c9c297e34f8b9d0398c8d3f38636e
+oid sha256:330021ac70e91dee5090af7d2fab1900ffbc4e4d7fffc3a50e52877d126f757b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0026970170990884084,
+  "epoch": 0.005394034198176817,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 17.376,
       "eval_steps_per_second": 8.688,
       "step": 100
+    },
+    {
+      "epoch": 0.002966718808997249,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.00323642051890609,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.0035061222288149305,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.0037758239387237717,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.004045525648632612,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.004315227358541453,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.004584929068450294,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0048546307783591345,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.005124332488267975,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.005394034198176817,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.005394034198176817,
+      "eval_loss": NaN,
+      "eval_runtime": 898.4753,
+      "eval_samples_per_second": 17.376,
+      "eval_steps_per_second": 8.688,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -107,7 +185,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1595961638387712.0,
+  "total_flos": 3227627116560384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null