Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e07f600fb597088a902196bf21c0d0d7fba2f5afa28d2b50b63125f1fa85e4de
+oid sha256:1c09105556085216da7af29a1e24925d1809563eb8fb65beeb6fbe1bd1b65eda
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a13813b119121d652898d31d0955f6df4e3ecbfb5b46b3366a5ca49b8ffb35c
+oid sha256:4210117d98cf8b4ee559c4b86590197ff405b3d12bdce2c33cae43ff31f728a4
 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": 0.0005943006567022257,
+  "epoch": 0.0011886013134044513,
   "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": 7.142,
       "eval_steps_per_second": 3.571,
       "step": 10
+    },
+    {
+      "epoch": 0.0006537307223724483,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0007131607880426708,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 46.1278,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007725908537128933,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0008320209193831159,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0008914509850533385,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008914509850533385,
+      "eval_loss": NaN,
+      "eval_runtime": 996.6228,
+      "eval_samples_per_second": 7.109,
+      "eval_steps_per_second": 3.555,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009508810507235611,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010103111163937836,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.0010697411820640062,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.0011291712477342287,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0011886013134044513,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011886013134044513,
+      "eval_loss": NaN,
+      "eval_runtime": 998.9441,
+      "eval_samples_per_second": 7.092,
+      "eval_steps_per_second": 3.547,
+      "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": 2652819601489920.0,
+  "total_flos": 5305639202979840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null