Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48e4a42d5b83281f75491c7b54216484f34e0a9099b433e9ea3709fa6f6bfee
+oid sha256:c79c881928c01183186d36cf8fc2b8a93d944f13824643ebc632285c19511fce
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86d4d3d0a78c26978bceb6fb890809281e7880acc2d2f16968f14b7cb63363f1
+oid sha256:f6693f1e33cdf223c814db48f62b95f98d28e4c42575a31a17aaaf14a3fedbae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552c84d0a2b312d5a5723cf82f589e8f9304c187d49902248a3039a1c46f9f88
+oid sha256:4b6d97cfa1fe914ae9198fef71f299bbf589be4a2231461bd092dbb50e517202
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29d77b6800134e82eec66264d0f92b64297871eb0f6d1061f3bbb350666436f6
+oid sha256:3735e84e1ba94f501806a4657b6384bc6278a9e25436557e952788d78d3518f1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0720eba0bdfd21ab59ef5bd9919af2421b3003fa95054a952cbf3b3ea4382cdb
+oid sha256:49c485a756bbfca7b9a6099f13e2f55679955ac2b059bf44a8b923d68b1f05b6
 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": 0.017947682505496478,
+  "epoch": 0.035895365010992955,
   "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": 67.636,
       "eval_steps_per_second": 17.585,
       "step": 25
+    },
+    {
+      "epoch": 0.018665589805716337,
+      "grad_norm": NaN,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.019383497105936197,
+      "grad_norm": NaN,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.020101404406156057,
+      "grad_norm": NaN,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.020819311706375913,
+      "grad_norm": NaN,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.021537219006595772,
+      "grad_norm": NaN,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.022255126306815632,
+      "grad_norm": NaN,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.02297303360703549,
+      "grad_norm": NaN,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.02369094090725535,
+      "grad_norm": NaN,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.02440884820747521,
+      "grad_norm": NaN,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.025126755507695067,
+      "grad_norm": NaN,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.025844662807914927,
+      "grad_norm": NaN,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.026562570108134786,
+      "grad_norm": NaN,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.027280477408354646,
+      "grad_norm": NaN,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.027998384708574506,
+      "grad_norm": NaN,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.028716292008794365,
+      "grad_norm": NaN,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.029434199309014225,
+      "grad_norm": NaN,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.03015210660923408,
+      "grad_norm": NaN,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.03087001390945394,
+      "grad_norm": NaN,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.031587921209673804,
+      "grad_norm": NaN,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.03230582850989366,
+      "grad_norm": NaN,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.033023735810113516,
+      "grad_norm": NaN,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.033741643110333376,
+      "grad_norm": NaN,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.034459550410553236,
+      "grad_norm": NaN,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.035177457710773095,
+      "grad_norm": NaN,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.035895365010992955,
+      "grad_norm": NaN,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.035895365010992955,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7524,
+      "eval_samples_per_second": 66.453,
+      "eval_steps_per_second": 17.278,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null