Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173696c59d3591c2f13db21771ec38a075521a4ba7425c574ad6e67713f5a6d5
+oid sha256:c2c882bdeaabe3467b5f4b5dca292a4232321a671e1c1235accf741e0c961657
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9061af35648c16177befb37989a792d0fa2295aad4f920f4e0bc355d216d96fb
+oid sha256:ee4c7f2a46d0b84c0628d15310b3f57cd1f62d5ee3fdd16d98febe3a0d30db33
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81507c2a0ab25cc1ee5935c0a7cd6954f6d7f17227a3cb9309d33091d54ce928
+oid sha256:9dec92b71fc8c1dfb91931a9135a28b39ea9ad0cb5c9f09fe8c4b0b99361a30c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8351955e7184f99bf36af744b41bdd5fbc14ad1d855d1e7b33123608702ae683
+oid sha256:d46e6102550fd6076acfaf4470867ff29a574b751c670909c6b46651895b2619
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cb2d3e54c368ca191c99678df9921fbe09e67eb5a919a4a5dbf6c4f932c7da
+oid sha256:a802901d63c69df0d6fd8bee9eda251ae3098be39bb1b5c3e2d2f2d9b39bab83
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0478220dc1c61b501af7edfe8fa4a46b7ebe1a2bbd0ae4d7514712a0c8b72900
+oid sha256:3192059420211edc26748a07e2699e00ee3be65f92a2cf84ef56d22611d9eb5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16842105263157894,
+  "epoch": 0.3368421052631579,
   "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": 23.127,
       "eval_steps_per_second": 2.891,
       "step": 25
+    },
+    {
+      "epoch": 0.1751578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.18189473684210528,
+      "grad_norm": NaN,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.18863157894736843,
+      "grad_norm": NaN,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.19536842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 8.506183921362443e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.20884210526315788,
+      "grad_norm": NaN,
+      "learning_rate": 8.262928807620843e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.21557894736842106,
+      "grad_norm": NaN,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.22231578947368422,
+      "grad_norm": NaN,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.22905263157894737,
+      "grad_norm": NaN,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": NaN,
+      "learning_rate": 7.734740790612136e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.24252631578947367,
+      "grad_norm": NaN,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.24926315789473685,
+      "grad_norm": NaN,
+      "learning_rate": 7.452117519152542e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": NaN,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.26273684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 7.158771761692464e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": NaN,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.27621052631578946,
+      "grad_norm": NaN,
+      "learning_rate": 6.855986244591104e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.2829473684210526,
+      "grad_norm": NaN,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.28968421052631577,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.296421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 6.227427435703997e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.3098947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.31663157894736843,
+      "grad_norm": NaN,
+      "learning_rate": 5.90440267166055e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.3233684210526316,
+      "grad_norm": NaN,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.33010526315789473,
+      "grad_norm": NaN,
+      "learning_rate": 5.577423184847932e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": NaN,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_loss": NaN,
+      "eval_runtime": 43.3832,
+      "eval_samples_per_second": 23.05,
+      "eval_steps_per_second": 2.881,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null