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:b36ec73cd9827ba8c91a0ea58ebc4faca053e31799036ef42ba948ded2c240c1
+oid sha256:9594cf01b1ea00530d1066c2f524ba25b54e3ad24a6a722af060784724fb47c3
 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": 0.0036127167630057803,
+  "epoch": 0.0072254335260115606,
   "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": 7.669,
       "eval_steps_per_second": 3.835,
       "step": 10
+    },
+    {
+      "epoch": 0.003973988439306358,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.004335260115606936,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.004696531791907515,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0050578034682080926,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.00541907514450867,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.00541907514450867,
+      "eval_loss": NaN,
+      "eval_runtime": 145.6861,
+      "eval_samples_per_second": 8.004,
+      "eval_steps_per_second": 4.002,
+      "step": 15
+    },
+    {
+      "epoch": 0.005780346820809248,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.006141618497109827,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.006502890173410405,
+      "grad_norm": NaN,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.006864161849710983,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.0072254335260115606,
+      "grad_norm": NaN,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.0072254335260115606,
+      "eval_loss": NaN,
+      "eval_runtime": 150.111,
+      "eval_samples_per_second": 7.768,
+      "eval_steps_per_second": 3.884,
+      "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": 2103206159056896.0,
+  "total_flos": 4162595523133440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null