Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5c9c0a64ab8fdbae53dac1dd1f9e56b81ae97f263cf783b5a88524601126b2
+oid sha256:b5b001a2fc939ecf43fb0d86edcd5bf104abdef1bc3131e002054358dce29e25
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116b9be2098e40bb27534c05f40050ba378d5645f092cb52dbca1e194fd5a781
+oid sha256:45d965a8183a13148716d4b122cea945c60bc9f5ac1bb607480c425d22ce2ec2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.015432098765432098,
+  "epoch": 0.030864197530864196,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 7.969,
       "eval_steps_per_second": 4.042,
       "step": 10
+    },
+    {
+      "epoch": 0.018518518518518517,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.023148148148148147,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.023148148148148147,
+      "eval_loss": NaN,
+      "eval_runtime": 8.9641,
+      "eval_samples_per_second": 7.697,
+      "eval_steps_per_second": 3.904,
+      "step": 15
+    },
+    {
+      "epoch": 0.027777777777777776,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.030864197530864196,
+      "eval_loss": NaN,
+      "eval_runtime": 10.4253,
+      "eval_samples_per_second": 6.618,
+      "eval_steps_per_second": 3.357,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -66,7 +103,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -75,12 +112,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 39729404313600.0,
+  "total_flos": 79458808627200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null