Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0afc1e49e4037e69d81f7751bf3f22d68cbc4050cb1487205a8f6f81a911f0ca
+oid sha256:82209303d278d3c86028b7bbe8fafb8e51159ba71f3c5b237cf7aca61bb58255
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f95a0103aec5dac5623ccbb1f735c6ca191a6502802b33144b1a7429632de6
+oid sha256:9d5139c1d644db4d208508be1f228f3f5154076227bfa84151f171852e1351d3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18da12ca78175c6d3c2c3cb862eec36224f116d73ca134a0fca56e89ce26eb08
+oid sha256:016818bb8b1fb10139ad6a5f274d55ae2ad4410cddb30a53a8b9fe9c873d8620
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5807c653d01548204d52a39b7041ab535cd4656553f3f9c9b3c5c962bb2fe970
+oid sha256:10a74d864a26b32c75d69c44345c9b7a8f1f321205137928fe83ad7becf322e5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b0fd54d69971ec313ae534999c64440dd1d5f9bf9233cf6b228d978033ba06
+oid sha256:f66a9628c5db5ea9ed26a8a54261e4f51b06b5fa84c1b39739f20c0174db4ff2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3421727972626176,
+  "epoch": 0.6843455945252352,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 15.998,
       "eval_steps_per_second": 4.159,
       "step": 25
+    },
+    {
+      "epoch": 0.3558597091531223,
+      "grad_norm": NaN,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.369546621043627,
+      "grad_norm": NaN,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": NaN,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.39692044482463645,
+      "grad_norm": NaN,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.41060735671514115,
+      "grad_norm": NaN,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.42429426860564584,
+      "grad_norm": NaN,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.43798118049615054,
+      "grad_norm": NaN,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.4516680923866553,
+      "grad_norm": NaN,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.46535500427716,
+      "grad_norm": NaN,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": NaN,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.49272882805816937,
+      "grad_norm": NaN,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.5064157399486741,
+      "grad_norm": NaN,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.5201026518391788,
+      "grad_norm": NaN,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.5337895637296834,
+      "grad_norm": NaN,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": NaN,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.561163387510693,
+      "grad_norm": NaN,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": NaN,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.5885372112917023,
+      "grad_norm": NaN,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.602224123182207,
+      "grad_norm": NaN,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": NaN,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.6295979469632165,
+      "grad_norm": NaN,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.6432848588537211,
+      "grad_norm": NaN,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.6569717707442259,
+      "grad_norm": NaN,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": NaN,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "eval_loss": NaN,
+      "eval_runtime": 3.1319,
+      "eval_samples_per_second": 15.965,
+      "eval_steps_per_second": 4.151,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.629553998528512e+17,
+  "total_flos": 5.259107997057024e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null