Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd9a22c39a60a6cc083317dbc0475713c810652a8294d38c8cfdd55d18de9c5
+oid sha256:b62fd13a7dfab127dc4aee73e891c2c3a3dfff58e28ddcd385a0e207869db08f
 size 294324372

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf09056afaf0ae724fdb3ead56a66281448c913b2ca40943c6ea06f94c2a781
+oid sha256:c85027ccb3cbfd07885a93731d4088037863bdd3a9c4da70cb0ca80f8ab171bc
 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": 0.004025724378780407,
+  "epoch": 0.008051448757560814,
   "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": 7.359,
       "eval_steps_per_second": 3.68,
       "step": 100
+    },
+    {
+      "epoch": 0.004428296816658447,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.004830869254536488,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.005233441692414529,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.005636014130292569,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.00603858656817061,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.006441159006048651,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.006843731443926692,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.0072463038818047325,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.007648876319682773,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.008051448757560814,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.008051448757560814,
+      "eval_loss": NaN,
+      "eval_runtime": 1419.7108,
+      "eval_samples_per_second": 7.368,
+      "eval_steps_per_second": 3.684,
+      "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": 1.72564471087104e+16,
+  "total_flos": 3.45128942174208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null