Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca88aba86263a83030f8a808ba6f2bd70b8b5e4cd262be6bf0ba1587b807d7c4
+oid sha256:782f40b882d873bccc44095578d9a5e30c599b92616c9989f27ee8dca17213cc
 size 252224626

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f4db13d558b837e828a36bb531c071000828de4e88f9036510e838a7387f39
+oid sha256:7cdb61ae78461ad8cdd412a738ed10c617a5f252b98b05205b310b9b93e855b5
 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": 0.0014035087719298245,
+  "epoch": 0.002807017543859649,
   "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": 2.284,
       "eval_steps_per_second": 1.142,
       "step": 10
+    },
+    {
+      "epoch": 0.001543859649122807,
+      "grad_norm": NaN,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0016842105263157896,
+      "grad_norm": NaN,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.001824561403508772,
+      "grad_norm": NaN,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0019649122807017545,
+      "grad_norm": NaN,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.002105263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.002105263157894737,
+      "eval_loss": NaN,
+      "eval_runtime": 1224.1309,
+      "eval_samples_per_second": 2.451,
+      "eval_steps_per_second": 1.225,
+      "step": 15
+    },
+    {
+      "epoch": 0.002245614035087719,
+      "grad_norm": NaN,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.002385964912280702,
+      "grad_norm": NaN,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0025263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0026666666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.002807017543859649,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.002807017543859649,
+      "eval_loss": NaN,
+      "eval_runtime": 1225.6633,
+      "eval_samples_per_second": 2.448,
+      "eval_steps_per_second": 1.224,
+      "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": 4311281779605504.0,
+  "total_flos": 8883853364035584.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null