Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb074fe076bf52fb6e0e3a1ef658cd7cc884a816563eaf9603f6686cdd9ce725
+oid sha256:51a33e59ade4b12b190e259d2285376e6a35ca94c776213d2b7f1385145b156b
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2971cbe0f61f3a458c833915f8f877a317595f1d6fd358e7da6a072617671769
+oid sha256:d8104de6a2f1276ba1e8b31f4f669dc9d2c24681ca0627b0ed97ed7771f0b4b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00036378518484834707,
+  "epoch": 0.0007275703696966941,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 9.126,
       "eval_steps_per_second": 4.563,
       "step": 10
+    },
+    {
+      "epoch": 0.00040016370333318177,
+      "grad_norm": NaN,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0004365422218180165,
+      "grad_norm": NaN,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0004729207403028512,
+      "grad_norm": NaN,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0005092992587876859,
+      "grad_norm": NaN,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0005456777772725206,
+      "grad_norm": NaN,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005456777772725206,
+      "eval_loss": NaN,
+      "eval_runtime": 1269.1316,
+      "eval_samples_per_second": 9.12,
+      "eval_steps_per_second": 4.561,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005820562957573553,
+      "grad_norm": NaN,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.00061843481424219,
+      "grad_norm": NaN,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0006548133327270247,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006911918512118594,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0007275703696966941,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0007275703696966941,
+      "eval_loss": NaN,
+      "eval_runtime": 2603.71,
+      "eval_samples_per_second": 4.446,
+      "eval_steps_per_second": 2.223,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -115,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -124,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3887281314201600.0,
+  "total_flos": 7377901269811200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null